mirror of
https://github.com/aaronpo97/the-biergarten-app.git
synced 2026-06-01 01:54:00 +00:00
Compare commits
22 Commits
a8e0ced8ba
...
main-2.0
| Author | SHA1 | Date | |
|---|---|---|---|
| 6a66619c70 | |||
| 2ee7b3d2a2 | |||
| b7c0b1c8d4 | |||
| b8ebe03921 | |||
| 26635ace84 | |||
| 031be8ad5d | |||
| f316fabcb0 | |||
| b1dc8e0b5d | |||
| 641a479b6a | |||
| d80e15b55e | |||
|
|
1fcaf6e174 | ||
|
|
ef97bf0a75 | ||
|
|
4c8a8e43ed | ||
|
|
8db6992296 | ||
|
|
7925fc6caf | ||
|
|
b1f4ff2641 | ||
|
|
a852beff21 | ||
|
|
e17afe909f | ||
|
|
9ed37806dd | ||
|
|
5a21589029 | ||
|
|
189bce040b | ||
| e8c5b8a80c |
@@ -1,13 +0,0 @@
|
||||
{
|
||||
"version": 1,
|
||||
"isRoot": true,
|
||||
"tools": {
|
||||
"csharpier": {
|
||||
"version": "1.2.1",
|
||||
"commands": [
|
||||
"csharpier"
|
||||
],
|
||||
"rollForward": false
|
||||
}
|
||||
}
|
||||
}
|
||||
1
.gitattributes
vendored
Normal file
1
.gitattributes
vendored
Normal file
@@ -0,0 +1 @@
|
||||
archive/** linguist-vendored
|
||||
20
.github/ISSUE_TEMPLATE/feature_request.md
vendored
20
.github/ISSUE_TEMPLATE/feature_request.md
vendored
@@ -7,6 +7,7 @@ assignees: []
|
||||
---
|
||||
|
||||
## User Story
|
||||
|
||||
**As a** (who wants to accomplish something)
|
||||
**I want to** (what they want to accomplish)
|
||||
**So that** (why they want to accomplish that thing)
|
||||
@@ -15,29 +16,18 @@ assignees: []
|
||||
|
||||
### Scenario 1
|
||||
|
||||
|
||||
Given ...
|
||||
When ...
|
||||
Then ...
|
||||
|
||||
Given ... When ... Then ...
|
||||
|
||||
### Scenario 2
|
||||
|
||||
|
||||
Given ...
|
||||
When ...
|
||||
Then ...
|
||||
|
||||
Given ... When ... Then ...
|
||||
|
||||
### Scenario 3
|
||||
|
||||
|
||||
Given ...
|
||||
When ...
|
||||
Then ...
|
||||
|
||||
Given ... When ... Then ...
|
||||
|
||||
## Subtasks
|
||||
|
||||
- [ ] Task 1
|
||||
- [ ] Task 2
|
||||
- [ ] Task 3
|
||||
962
LICENSE.md
962
LICENSE.md
File diff suppressed because it is too large
Load Diff
161
README.md
161
README.md
@@ -1,40 +1,56 @@
|
||||
# The Biergarten App
|
||||
|
||||
The Biergarten App is a multi-project monorepo with a .NET backend and an active React
|
||||
Router frontend in `src/Website`. The current website focuses on account flows, theme
|
||||
switching, shared UI components, Storybook coverage, and integration with the API.
|
||||
The Biergarten App is a full-stack directory and discovery platform for
|
||||
breweries. It features a robust user authentication system, a searchable
|
||||
database of brewery locations, and a custom offline data-generation pipeline
|
||||
that uses LLMs (Llama.cpp) and Wikipedia to synthesize realistic seed data.
|
||||
|
||||
## Documentation
|
||||
It features:
|
||||
|
||||
- [Getting Started](docs/getting-started.md) - Local setup for backend and active website
|
||||
- [Architecture](docs/architecture.md) - Current backend and frontend architecture
|
||||
- [Docker Guide](docs/docker.md) - Container-based backend development and testing
|
||||
- [Testing](docs/testing.md) - Backend and frontend test commands
|
||||
- [Environment Variables](docs/environment-variables.md) - Active configuration reference
|
||||
- [Token Validation](docs/token-validation.md) - JWT validation architecture
|
||||
- [Legacy Website Archive](docs/archive/legacy-website-v1.md) - Archived notes for the old Next.js frontend
|
||||
- A .NET backend (Web API + database migrations/seed) under `web/backend/`
|
||||
- A server-rendered React website (React Router + Vite) under `web/frontend/`
|
||||
- A C++20 “pipeline” CLI for generating seed data under `tooling/pipeline/`
|
||||
|
||||
Specialized documentation (setup, architecture, docker, testing, diagrams, and
|
||||
pipeline notes) lives under `docs/`.
|
||||
|
||||
## Documentation (Start Here)
|
||||
|
||||
Website + backend (active stack):
|
||||
|
||||
- [Getting Started](docs/website/getting-started.md)
|
||||
- [Architecture](docs/architecture.md)
|
||||
- [Docker Guide](docs/website/docker.md)
|
||||
- [Testing](docs/website/testing.md)
|
||||
- [Environment Variables](docs/website/environment-variables.md)
|
||||
- [Token Validation](docs/website/token-validation.md)
|
||||
|
||||
Data generation pipeline (C++):
|
||||
|
||||
- [Pipeline README](docs/pipeline/README.md)
|
||||
- [Ethics & Known Issues](docs/pipeline/ETHICS-AND-KNOWN-ISSUES.md)
|
||||
|
||||
## Diagrams
|
||||
|
||||
- [Architecture](docs/diagrams-out/architecture.svg) - Layered architecture
|
||||
- [Deployment](docs/diagrams-out/deployment.svg) - Docker topology
|
||||
- [Authentication Flow](docs/diagrams-out/authentication-flow.svg) - Auth sequence
|
||||
- [Database Schema](docs/diagrams-out/database-schema.svg) - Entity relationships
|
||||
- [Architecture](docs/website/diagrams-out/architecture.svg)
|
||||
- [Deployment](docs/website/diagrams-out/deployment.svg)
|
||||
- [Authentication Flow](docs/website/diagrams-out/authentication-flow.svg)
|
||||
- [Database Schema](docs/website/diagrams-out/database-schema.svg)
|
||||
|
||||
## Current Status
|
||||
|
||||
Active areas in the repository:
|
||||
|
||||
- .NET 10 backend with layered architecture and SQL Server
|
||||
- React Router 7 website in `src/Website`
|
||||
- Shared Biergarten theme system with a theme guide route
|
||||
- Storybook stories and browser-based checks for shared UI
|
||||
- Auth demo flows for home, login, register, dashboard, logout, and confirmation
|
||||
- Toast-based feedback for auth outcomes
|
||||
- .NET 10 backend (layered architecture) + SQL Server
|
||||
- React 19 website (React Router 7 + Vite)
|
||||
- Shared Biergarten theme system + Storybook coverage
|
||||
- Auth flows and account/email integration (local Mailpit in dev compose)
|
||||
- Data generation pipeline with C++ and Llama.cpp
|
||||
|
||||
Legacy area retained for reference:
|
||||
Archived/reference areas:
|
||||
|
||||
- `src/Website-v1` contains the archived Next.js frontend and is no longer the active website
|
||||
- `archive/next-js-web-app/` contains an older Next.js frontend retained for
|
||||
reference
|
||||
|
||||
## Tech Stack
|
||||
|
||||
@@ -43,36 +59,43 @@ Legacy area retained for reference:
|
||||
- **UI Documentation**: Storybook 10, Vitest browser mode, Playwright
|
||||
- **Testing**: xUnit, Reqnroll (BDD), FluentAssertions, Moq
|
||||
- **Infrastructure**: Docker, Docker Compose
|
||||
- **Security**: Argon2id password hashing, JWT access/refresh/confirmation tokens
|
||||
- **Security**: Argon2id password hashing, JWT access/refresh/confirmation
|
||||
tokens
|
||||
- **Data Pipeline**: C++20, CMake, Boost, libcurl, SQLite, llama.cpp
|
||||
|
||||
## Quick Start
|
||||
|
||||
### Backend
|
||||
For full setup details, use [Getting Started](docs/website/getting-started.md).
|
||||
This section is the shortest path to a working dev environment.
|
||||
|
||||
### Backend (Docker)
|
||||
|
||||
```bash
|
||||
git clone https://github.com/aaronpo97/the-biergarten-app
|
||||
cd the-biergarten-app
|
||||
cp .env.example .env.dev
|
||||
docker compose -f docker-compose.dev.yaml up -d
|
||||
|
||||
cp web/.env.example web/.env.dev
|
||||
docker compose --env-file web/.env.dev -f web/docker-compose.dev.yaml up --build -d
|
||||
```
|
||||
|
||||
Backend access:
|
||||
|
||||
- API Swagger: http://localhost:8080/swagger
|
||||
- Health Check: http://localhost:8080/health
|
||||
- Mailpit UI (dev SMTP): http://localhost:8025
|
||||
|
||||
### Frontend
|
||||
### Frontend (Node)
|
||||
|
||||
```bash
|
||||
cd src/Website
|
||||
cd web/frontend
|
||||
npm install
|
||||
API_BASE_URL=http://localhost:8080 SESSION_SECRET=dev-secret npm run dev
|
||||
API_BASE_URL=http://localhost:8080 SESSION_SECRET=dev-secret-change-me npm run dev
|
||||
```
|
||||
|
||||
Optional frontend tools:
|
||||
|
||||
```bash
|
||||
cd src/Website
|
||||
cd web/frontend
|
||||
npm run storybook
|
||||
npm run test:storybook
|
||||
npm run test:storybook:playwright
|
||||
@@ -81,62 +104,42 @@ npm run test:storybook:playwright
|
||||
## Repository Structure
|
||||
|
||||
```text
|
||||
src/Core/ Backend projects (.NET)
|
||||
src/Website/ Active React Router frontend
|
||||
src/Website-v1/ Archived legacy Next.js frontend
|
||||
docs/ Active project documentation
|
||||
docs/archive/ Archived legacy documentation
|
||||
web/
|
||||
backend/ .NET API + domain/service/infrastructure + DB projects
|
||||
frontend/ React Router website + Storybook + Playwright/Vitest
|
||||
|
||||
tooling/
|
||||
pipeline/ C++20 seed-data generation CLI (CMake)
|
||||
|
||||
docs/
|
||||
architecture.md High-level architecture overview
|
||||
website/ Backend/frontend setup, docker, testing, diagrams
|
||||
pipeline/ Pipeline docs, ethics notes, PlantUML diagrams
|
||||
|
||||
archive/
|
||||
next-js-web-app/ Older Next.js frontend (reference only)
|
||||
```
|
||||
|
||||
## Key Features
|
||||
|
||||
Implemented today:
|
||||
|
||||
- User registration and login against the API
|
||||
- JWT-based auth with access, refresh, and confirmation flows
|
||||
- SQL Server migrations and seed projects
|
||||
- Shared form components and auth screens
|
||||
- Theme switching with Lager, Stout, Cassis, and Weizen variants
|
||||
- Storybook documentation and automated story interaction tests
|
||||
- Toast feedback for auth-related outcomes
|
||||
|
||||
Planned next:
|
||||
|
||||
- Brewery discovery and management
|
||||
- Beer reviews and ratings
|
||||
- Social follow relationships
|
||||
- Geospatial brewery experiences
|
||||
- Additional frontend routes beyond the auth demo
|
||||
|
||||
## Testing
|
||||
|
||||
Backend suites:
|
||||
|
||||
- `API.Specs` - integration tests
|
||||
- `Infrastructure.Repository.Tests` - repository unit tests
|
||||
- `Service.Auth.Tests` - service unit tests
|
||||
|
||||
Frontend suites:
|
||||
|
||||
- Storybook interaction tests via Vitest
|
||||
- Storybook browser regression checks via Playwright
|
||||
|
||||
Run all backend tests with Docker:
|
||||
Run the backend test stack with Docker:
|
||||
|
||||
```bash
|
||||
docker compose -f docker-compose.test.yaml up --abort-on-container-exit
|
||||
docker compose --env-file web/.env.test -f web/docker-compose.test.yaml up --abort-on-container-exit
|
||||
```
|
||||
|
||||
See [Testing](docs/testing.md) for the full command list.
|
||||
See [Testing](docs/website/testing.md) for the full command list.
|
||||
|
||||
## Configuration
|
||||
|
||||
Common active variables:
|
||||
|
||||
- Backend: `DB_SERVER`, `DB_NAME`, `DB_USER`, `DB_PASSWORD`, `ACCESS_TOKEN_SECRET`, `REFRESH_TOKEN_SECRET`, `CONFIRMATION_TOKEN_SECRET`
|
||||
- Frontend: `API_BASE_URL`, `SESSION_SECRET`, `NODE_ENV`
|
||||
- Backend/Docker: `DB_SERVER`, `DB_NAME`, `DB_USER`, `DB_PASSWORD`,
|
||||
`ACCESS_TOKEN_SECRET`, `REFRESH_TOKEN_SECRET`, `CONFIRMATION_TOKEN_SECRET`,
|
||||
`WEBSITE_BASE_URL`
|
||||
- Frontend runtime: `API_BASE_URL`, `SESSION_SECRET`, `NODE_ENV`
|
||||
|
||||
See [Environment Variables](docs/environment-variables.md) for details.
|
||||
See [Environment Variables](docs/website/environment-variables.md) for details.
|
||||
|
||||
## Contributing
|
||||
|
||||
@@ -145,15 +148,3 @@ See [Environment Variables](docs/environment-variables.md) for details.
|
||||
3. Commit your changes (`git commit -m 'Add amazing feature'`)
|
||||
4. Push to the branch (`git push origin feature/amazing-feature`)
|
||||
5. Open a Pull Request
|
||||
|
||||
### Development Workflow
|
||||
|
||||
1. Start development environment: `docker compose -f docker-compose.dev.yaml up -d`
|
||||
2. Make changes to code
|
||||
3. Run tests: `docker compose -f docker-compose.test.yaml up --abort-on-container-exit`
|
||||
4. Rebuild if needed: `docker compose -f docker-compose.dev.yaml up -d --build api.core`
|
||||
|
||||
## Support
|
||||
|
||||
- **Documentation**: [docs/](docs/)
|
||||
- **Architecture**: See [Architecture Guide](docs/architecture.md)
|
||||
|
||||
@@ -4,24 +4,28 @@ This document describes the active architecture of The Biergarten App.
|
||||
|
||||
## High-Level Overview
|
||||
|
||||
The Biergarten App is a monorepo with a clear split between the backend and the active
|
||||
website:
|
||||
The Biergarten App is a monorepo with a clear split between the backend and the
|
||||
active website:
|
||||
|
||||
- **Backend**: .NET 10 Web API with SQL Server and a layered architecture
|
||||
- **Frontend**: React 19 + React Router 7 website in `src/Website`
|
||||
- **Architecture Style**: Layered backend plus server-rendered React frontend
|
||||
|
||||
The legacy Next.js frontend has been retained in `src/Website-v1` for reference only and is
|
||||
documented in [archive/legacy-website-v1.md](archive/legacy-website-v1.md).
|
||||
The legacy Next.js frontend has been retained in `src/Website-v1` for reference
|
||||
only and is documented in
|
||||
[archive/legacy-website-v1.md](archive/legacy-website-v1.md).
|
||||
|
||||
## Diagrams
|
||||
|
||||
For visual representations, see:
|
||||
|
||||
- [architecture.svg](diagrams-out/architecture.svg) - Layered architecture diagram
|
||||
- [architecture.svg](diagrams-out/architecture.svg) - Layered architecture
|
||||
diagram
|
||||
- [deployment.svg](diagrams-out/deployment.svg) - Docker deployment diagram
|
||||
- [authentication-flow.svg](diagrams-out/authentication-flow.svg) - Authentication workflow
|
||||
- [database-schema.svg](diagrams-out/database-schema.svg) - Database relationships
|
||||
- [authentication-flow.svg](diagrams-out/authentication-flow.svg) -
|
||||
Authentication workflow
|
||||
- [database-schema.svg](diagrams-out/database-schema.svg) - Database
|
||||
relationships
|
||||
|
||||
## Backend Architecture
|
||||
|
||||
@@ -218,7 +222,8 @@ public interface IAuthRepository
|
||||
|
||||
### Active Website (`src/Website`)
|
||||
|
||||
The current website is a React Router 7 application with server-side rendering enabled.
|
||||
The current website is a React Router 7 application with server-side rendering
|
||||
enabled.
|
||||
|
||||
```text
|
||||
src/Website/
|
||||
@@ -244,20 +249,22 @@ src/Website/
|
||||
|
||||
### Theme System
|
||||
|
||||
The active website uses semantic DaisyUI theme tokens backed by four Biergarten themes:
|
||||
The active website uses semantic DaisyUI theme tokens backed by four Biergarten
|
||||
themes:
|
||||
|
||||
- Biergarten Lager
|
||||
- Biergarten Stout
|
||||
- Biergarten Cassis
|
||||
- Biergarten Weizen
|
||||
|
||||
All component styling should prefer semantic tokens such as `primary`, `success`,
|
||||
`surface`, and `highlight` instead of hard-coded color values.
|
||||
All component styling should prefer semantic tokens such as `primary`,
|
||||
`success`, `surface`, and `highlight` instead of hard-coded color values.
|
||||
|
||||
### Legacy Frontend
|
||||
|
||||
The previous Next.js frontend has been archived at `src/Website-v1`. Active product and
|
||||
engineering documentation should point to `src/Website`, while legacy notes live in
|
||||
The previous Next.js frontend has been archived at `src/Website-v1`. Active
|
||||
product and engineering documentation should point to `src/Website`, while
|
||||
legacy notes live in
|
||||
[archive/legacy-website-v1.md](archive/legacy-website-v1.md).
|
||||
|
||||
## Security Architecture
|
||||
@@ -387,8 +394,8 @@ For details, see [Docker Guide](docker.md).
|
||||
|
||||
### Health Checks
|
||||
|
||||
**SQL Server**: Validates database connectivity **API**: Checks service health and
|
||||
dependencies
|
||||
**SQL Server**: Validates database connectivity **API**: Checks service health
|
||||
and dependencies
|
||||
|
||||
**Configuration**:
|
||||
|
||||
|
||||
@@ -1,56 +0,0 @@
|
||||
# Legacy Website Archive (`src/Website-v1`)
|
||||
|
||||
This archive captures high-level notes about the previous Biergarten frontend so active
|
||||
project documentation can focus on the current website in `src/Website`.
|
||||
|
||||
## Status
|
||||
|
||||
- `src/Website-v1` is retained for historical reference only
|
||||
- It is not the active frontend used by current setup, docs, or testing guidance
|
||||
- New product and engineering work should target `src/Website`
|
||||
|
||||
## Legacy Stack Summary
|
||||
|
||||
The archived frontend used a different application model from the current website:
|
||||
|
||||
- Next.js 14
|
||||
- React 18
|
||||
- Prisma
|
||||
- Postgres / Neon-hosted database workflows
|
||||
- Next.js API routes and server-side controllers
|
||||
- Additional third-party integrations such as Cloudinary, Mapbox, and SparkPost
|
||||
|
||||
## Why It Was Archived
|
||||
|
||||
The active website moved to a React Router-based frontend that talks directly to the .NET
|
||||
API. As part of that shift, the main docs were updated to describe:
|
||||
|
||||
- `src/Website` as the active frontend
|
||||
- React Router route modules and server rendering
|
||||
- Storybook-based component documentation and tests
|
||||
- Current frontend runtime variables: `API_BASE_URL`, `SESSION_SECRET`, and `NODE_ENV`
|
||||
|
||||
## Legacy Documentation Topics Moved Out of Active Docs
|
||||
|
||||
The following categories were removed from active documentation and intentionally archived:
|
||||
|
||||
- Next.js application structure guidance
|
||||
- Prisma and Postgres frontend setup
|
||||
- Legacy frontend environment variables
|
||||
- External service setup that only applied to `src/Website-v1`
|
||||
- Old frontend local setup instructions
|
||||
|
||||
## When To Use This Archive
|
||||
|
||||
Use this file only if you need to:
|
||||
|
||||
- inspect the historical frontend implementation
|
||||
- compare old flows against the current website
|
||||
- migrate or recover legacy logic from `src/Website-v1`
|
||||
|
||||
For all active work, use:
|
||||
|
||||
- [Getting Started](../getting-started.md)
|
||||
- [Architecture](../architecture.md)
|
||||
- [Environment Variables](../environment-variables.md)
|
||||
- [Testing](../testing.md)
|
||||
336
docs/pipeline/ETHICS-AND-KNOWN-ISSUES.md
Normal file
336
docs/pipeline/ETHICS-AND-KNOWN-ISSUES.md
Normal file
@@ -0,0 +1,336 @@
|
||||
# Ethics, Bias, and Known Issues
|
||||
|
||||
This document covers the ethical context of the Biergarten Pipeline's output,
|
||||
the model's biases, and known issues including hallucinated brewing science and
|
||||
low-resource language failures.
|
||||
|
||||
> Note that all testing was used using `google_gemma-4-E4B-it-Q6_K.gguf`.
|
||||
|
||||
## Table of Contents
|
||||
|
||||
- [What This Dataset Is](#what-this-dataset-is)
|
||||
- [What This Dataset Is Not](#what-this-dataset-is-not)
|
||||
- [Model Bias and Language Quality](#model-bias-and-language-quality)
|
||||
- [Western and Eurocentric Lens](#western-and-eurocentric-lens)
|
||||
- [Wikipedia Enrichment](#wikipedia-enrichment)
|
||||
- [The "Avoid AI Phrases" Prompt Instruction](#the-avoid-ai-phrases-prompt-instruction)
|
||||
- [Known Issues](#known-issues)
|
||||
- [Hallucinated Brewing Techniques](#hallucinated-brewing-techniques)
|
||||
- [Low-Resource Language Hallucination](#low-resource-language-hallucination)
|
||||
|
||||
---
|
||||
|
||||
## What This Dataset Is
|
||||
|
||||
This is AI-generated fixture data for a proof-of-concept version of The
|
||||
Biergarten App. Anyone who interacts with an application seeded from this
|
||||
pipeline must be told upfront that the content is AI-generated.
|
||||
|
||||
---
|
||||
|
||||
## What This Dataset Is Not
|
||||
|
||||
The pipeline is not intended to produce accurate brewing science, faithful
|
||||
cultural representation, or reliable local-language text. Hallucinations such as
|
||||
invented fermentation techniques, or incoherent local-language prose, are
|
||||
expected, observed, and partially documented in [Known Issues](#known-issues)
|
||||
below.
|
||||
|
||||
Human control sits at the context layer (i.e. prompt design, Wikipedia
|
||||
enrichment). Statistical output shapes in future pipeline stages (check-in
|
||||
distributions, rating skews, activity profiles) will be handled the same way.
|
||||
|
||||
**Treat this data as an exercise in prompt engineering and model behaviour, not
|
||||
as a source of truth for brewing techniques or cultural representation.**
|
||||
|
||||
**Natural language processing, although a powerful tool for data analysis and
|
||||
generation is to be taken with scrutiny. Human language is not simply just data
|
||||
points to be analyzed, but it also carries deep cultural and human meaning that
|
||||
artificial intelligence is incapable of.**
|
||||
|
||||
---
|
||||
|
||||
## Model Bias and Language Quality
|
||||
|
||||
The underlying model's training biases surface within this pipeline. Output
|
||||
quality tracks with how well a language is represented in the training corpus:
|
||||
standard French (`fr-FR`) produces coherent text; regional variants like `fr-CD`
|
||||
and `fr-CI` are noticeably weaker; low-resource languages like Welsh, Māori, and
|
||||
Sicilian produce output that is syntactically plausible but often semantically
|
||||
broken.
|
||||
|
||||
This is a property of the training distribution, not something that can be
|
||||
mitigated through prompt design. This is a well-documented characteristic of
|
||||
large language models trained predominantly on English-language
|
||||
material.[^llm-bias]
|
||||
|
||||
Mitigations are documented in
|
||||
[Known Issues: Low-Resource Language Hallucination](#low-resource-language-hallucination).
|
||||
|
||||
### Western and Eurocentric Lens
|
||||
|
||||
The model's training data skews heavily Western and North American. When
|
||||
generating brewery descriptions for Kinshasa, Abidjan, or Osaka, for example, it
|
||||
defaults to framing and cultural reference points drawn from that perspective
|
||||
rather than from the lived context of those cities. Wikipedia enrichment grounds
|
||||
some generation in city-specific material, but it does not eliminate the skew.
|
||||
|
||||
**Output should be read with an understanding of this bias.**
|
||||
|
||||
---
|
||||
|
||||
## Wikipedia Enrichment
|
||||
|
||||
City and beer context is fetched from the Wikipedia API. Wikipedia text is
|
||||
co-licensed under the **Creative Commons Attribution-ShareAlike 4.0
|
||||
International License (CC BY-SA 4.0)** and the **GNU Free Documentation License
|
||||
(GFDL)**.[^wp-license]
|
||||
|
||||
Wikipedia's own accuracy limitations and editorial biases can propagate into
|
||||
generated descriptions.
|
||||
|
||||
---
|
||||
|
||||
## The "Avoid AI Phrases" Prompt Instruction
|
||||
|
||||
The system prompt instructs the model to avoid common AI-generated phrasing
|
||||
patterns. This is a prompt engineering experiment:
|
||||
|
||||
> How far can a model be pushed against its own stylistic defaults?
|
||||
|
||||
This is not an attempt to disguise the content as human-written. All downstream
|
||||
consumers are informed of the AI-generated origin before engagement.
|
||||
|
||||
---
|
||||
|
||||
## Known Issues
|
||||
|
||||
### Hallucinated Brewing Techniques
|
||||
|
||||
When forced by the system prompt to generate a "highly specialized technical
|
||||
brewing detail," the model frequently hallucinates fermentation science and
|
||||
brewing chemistry. While the resulting sounds confident, it will be nonsensical
|
||||
to reader with brewing and/or scientific expertise.
|
||||
|
||||
Small-parameter models such as Gemma 4 E4B cannot reliably satisfy prompts
|
||||
calling for specialist brewing detail. This is consistent with the **CHOKE**
|
||||
failure mode (Certain Hallucinations Overriding Known Evidence) [^llm-choke]
|
||||
where a specific-sounding prompt causes a model to produce confident, coherent,
|
||||
and factually wrong output.
|
||||
|
||||
#### Example — Osaka, produced using Gemma 4 E4B
|
||||
|
||||
```log
|
||||
[2026-04-21 15:04:40.258] [info] 11. city="Osaka" country="Japan" state="Osaka" iso3166_2=JP-27 lat=34.6937 lon=135.5023
|
||||
[2026-04-21 15:04:40.258] [info] brewery_name_en="Kani-no-Kuni Brewing"
|
||||
[2026-04-21 15:04:40.258] [info] brewery_description_en="The humid scent of takoyaki and savory grilled squid always settles over the neighborhood early in the morning, mingling strangely with the metallic tang of spent grain outside our drying shed. We decided to build this place here because Osaka is a city that never pauses, a place built around the constant exchange of goods and tastes, and that is what we want our beer to reflect. Many people here are accustomed to the dependable, clean taste of the major pale lagers, but we are interested in exploring the deeper, more textured expressions of fermentation. Our base malts are specifically crafted by incorporating strains of local rice, like Yamada Nishiki, which we malt and use not for sake, but for its complex, buttery flavor profile during the mash. This combination, followed by a slow, anaerobic aging process, gives our beers a profound, satisfying depth that stands apart from the hurried mass-market style. The heavy, deep red brick of the original warehouse wall has absorbed decades of Kansai humidity and seasonal rains, creating a patina that tells the exact story of this district's tireless movement. We chose this structure not for its charm, but for its resilience and the sheer density of the local history held within its mortar. Our goal is simply to serve a drink worthy of this powerful trading city. If you are looking for a quiet spot away from the main thoroughfare, look for us just off the side street near Shinsekai."
|
||||
[2026-04-21 15:04:40.258] [info] brewery_name_local="カニの国ブルワリー"
|
||||
[2026-04-21 15:04:40.258] [info] brewery_description_local="早朝の、たこ焼きや香ばしいイカ焼きの湿った匂いは、いつも乾燥小屋の外にある使用済み麦芽の金属的な匂いと奇妙に混ざり合って近隣に漂います。私たちはこの場所に店を構えることを決めたのです。なぜなら、大阪は決して止まることのない都市であり、商品と味が絶え間なく交換されることで築かれた場所だからです。地元の多くの方々は、信頼できる大規模な淡麗ラガーの味が習慣になっていますが、私たちは発酵の、より深く、より複雑な表現を探求することに関心があります。私たちのベースモルトは、山田錦のような地元の米の品種を意図的に組み込んで作られています。この米を酒ではなく、麦芽として、仕込みの最中にその複雑でバターのような風味を引き出すために使用しています。この組み合わせを、ゆっくりとした嫌気的な熟成プロセスに続けることで、私たちのビールは、慌ただしい市場のスタイルとは一線を画す、深みのある、満足感のある複雑さを持っています。オリジナルの倉庫の重く深紅のレンガ壁は、関西特有の湿気と季節の雨を何十年も吸収し、この地区の絶え間ない動きの正確な物語を語るような古色を帯びています。私たちはこの構造物を、その魅力のためではなく、その回復力とモルタルに込められた地域の歴史の密度ゆえに選びました。私たちの目標は、ただこの力強い交易都市に値する飲み物を提供することだけです。もしメインの通りから離れた静かな場所をお探しなら、新世界近くの脇道にある私たちを探してください。"
|
||||
```
|
||||
|
||||
A review of the following text for brewing techniques reveals several
|
||||
inaccuracies, and no comments could be made on the local-language version due to
|
||||
my own lack of proficiency in Japanese:
|
||||
|
||||
#### 1. "Buttery flavours" framed as a desirable malt-derived flavour
|
||||
|
||||
**Incorrect.**
|
||||
|
||||
Diacetyl is a fermentation byproduct of yeast metabolism, not a malt-derived
|
||||
compound.[^diacetyl-source] Diacetyl produces a buttery or butterscotch
|
||||
off-flavour and is carefully managed in many beer styles, in particular lighter
|
||||
beers, through a process called a _diacetyl rest_. In this process, fermentation
|
||||
temperature is briefly raised to allow yeast to reabsorb the compound before
|
||||
packaging.[^diacetyl-rest]
|
||||
|
||||
The Oxford Companion to Beer claims that, while low levels are tolerable in some
|
||||
ales and stouts, diacetyl is considered undesirable at any perceptible
|
||||
concentration when it results from bacterial contamination or stressed
|
||||
fermentation.[^oxford-beer]
|
||||
|
||||
#### 2. Yamada Nishiki sake rice described as a self-saccharifying base malt
|
||||
|
||||
**Incorrect.**
|
||||
|
||||
Yamada Nishiki (_山田錦_) is a short-grain Japanese rice bred specifically for
|
||||
sake production.[^yn-wiki] Its value lies in its large starchy core
|
||||
(_shinpaku_), low protein content, and amenability to _koji_ mold penetration
|
||||
during saccharification.[^yn-sakestreet] Sake brewing does not use the grain's
|
||||
own enzymatic activity for saccharification — it relies on _Aspergillus oryzae_
|
||||
(koji mold) grown on a portion of the steamed rice to convert starches to
|
||||
fermentable sugars.[^yn-sakeonline]
|
||||
|
||||
#### 3. "Anaerobic aging" presented as a differentiating technique
|
||||
|
||||
**Misleading**
|
||||
|
||||
Anaerobic conditions during packaging and aging are not differentiating
|
||||
technique. Anaerobic conditions are the standard baseline for all commercial
|
||||
beer production. Breweries exclude oxygen as a top priority for packaging and
|
||||
shelf stability; published research in _Microbiology Spectrum_ confirms that
|
||||
packaged beer constitutes an anaerobic environment by definition.[^anaerobic]
|
||||
Professional packaging lines use CO_2 purges and closed transfers specifically
|
||||
to maintain this state.[^packaging] Framing anaerobic aging as a distinctive
|
||||
practice is misleading and suggests hallucinated output.
|
||||
|
||||
### Low-Resource Language Hallucination
|
||||
|
||||
The generation pipeline passes local language codes to the model to retrieve a
|
||||
translated `description_local`. Output quality is reliable for high-resource
|
||||
languages such as French, though it may struggle with regional variants and
|
||||
idiomatic phrasing.
|
||||
|
||||
```json
|
||||
[
|
||||
{
|
||||
"city": "Kinshasa",
|
||||
"state_province": "Kinshasa",
|
||||
"iso3166_2": "CD-KN",
|
||||
"country": "Democratic Republic of the Congo",
|
||||
"iso3166_1": "CD",
|
||||
"latitude": -4.4419,
|
||||
"longitude": 15.2663,
|
||||
"local_languages": ["fr-CD", "ln"]
|
||||
},
|
||||
{
|
||||
"city": "Paris",
|
||||
"state_province": "Île-de-France",
|
||||
"iso3166_2": "FR-IDF",
|
||||
"country": "France",
|
||||
"iso3166_1": "FR",
|
||||
"latitude": 48.8566,
|
||||
"longitude": 2.3522,
|
||||
"local_languages": ["fr-FR"]
|
||||
},
|
||||
{
|
||||
"city": "Abidjan",
|
||||
"state_province": "Abidjan",
|
||||
"iso3166_2": "CI-AB",
|
||||
"country": "Ivory Coast",
|
||||
"iso3166_1": "CI",
|
||||
"latitude": 5.36,
|
||||
"longitude": -4.0083,
|
||||
"local_languages": ["fr-CI"]
|
||||
},
|
||||
{
|
||||
"city": "Montreal",
|
||||
"state_province": "Quebec",
|
||||
"iso3166_2": "CA-QC",
|
||||
"country": "Canada",
|
||||
"iso3166_1": "CA",
|
||||
"latitude": 45.5017,
|
||||
"longitude": -73.5673,
|
||||
"local_languages": ["fr-CA"]
|
||||
},
|
||||
{
|
||||
"city": "Brussels",
|
||||
"state_province": "Brussels-Capital Region",
|
||||
"iso3166_2": "BE-BRU",
|
||||
"country": "Belgium",
|
||||
"iso3166_1": "BE",
|
||||
"latitude": 50.8503,
|
||||
"longitude": 4.3517,
|
||||
"local_languages": ["fr-BE", "nl-BE"]
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
This dataset, when fed into the pipeline will often times reason that a local
|
||||
variant of French is needed, but will often times just default to a standardized
|
||||
dialect of French, devoid of any cultural or linguistic nuance.
|
||||
|
||||
For languages such as Welsh (Wales), Māori (Aotearoa/New Zealand), or Sicilian
|
||||
(Sicily, Italy), the model can generate text that looks syntactically plausible
|
||||
but is semantically incoherent. This comes from limited training-data coverage
|
||||
rather than prompt engineering.
|
||||
|
||||
Output sample:
|
||||
[./out-sample/french-cities.example](out-sample/french-cities.example)
|
||||
|
||||
#### Proposed Mitigations
|
||||
|
||||
- **Prevention via allowlist:** introduce a high-resource language allowlist. If
|
||||
a location's code is unlisted, skip `description_local` generation and fall
|
||||
back to English.
|
||||
- **Upstream sanitization:** strip known low-resource language codes from the
|
||||
`locations.json` payload before generation.
|
||||
- **Downstream flagging:** add a `description_local_confidence` column to the
|
||||
SQLite schema so downstream applications can filter or flag potentially
|
||||
hallucinated text by language tier.
|
||||
|
||||
---
|
||||
|
||||
## Footnotes
|
||||
|
||||
[^llm-choke]:
|
||||
CHOKE (Certain Hallucinations Overriding Known Evidence) is a hallucination
|
||||
failure mode defined by Simhi et al. (2025), in which a model that can
|
||||
consistently answer a question correctly produces a confident, wrong
|
||||
response when the prompt is trivially perturbed. Source: Trust Me, I'm
|
||||
Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer — Adi
|
||||
Simhi, Itay Itzhak, Fazl Barez, Gabriel Stanovsky, Yonatan Belinkov.
|
||||
|
||||
[^llm-bias]:
|
||||
e.g., Blasi et al. (2022), "Systematic Inequalities in Language Technology
|
||||
Performance across the World's Languages," _ACL Anthology_. The pattern is
|
||||
consistent with models trained predominantly on English-language web
|
||||
corpora.
|
||||
|
||||
[^wp-license]:
|
||||
Source:
|
||||
[Wikipedia:FAQ/Copyright](https://en.wikipedia.org/wiki/Wikipedia:FAQ/Copyright).
|
||||
|
||||
[^cc-sa]:
|
||||
Creative Commons CC BY-SA 4.0 deed: "If you remix, transform, or build upon
|
||||
the material, you must distribute your contributions under the same license
|
||||
as the original." Source:
|
||||
[creativecommons.org/licenses/by-sa/4.0](https://creativecommons.org/licenses/by-sa/4.0/deed.en).
|
||||
|
||||
[^diacetyl-source]:
|
||||
White Labs confirms that diacetyl is a yeast-derived fermentation byproduct:
|
||||
specifically, a compound produced during amino acid metabolism that leaks
|
||||
out of the yeast cell and oxidises into its characteristic buttery
|
||||
off-flavour. It is generally considered undesirable at any perceived level
|
||||
in most styles, though low levels are tolerated in some English ales and
|
||||
European lagers. Source:
|
||||
[whitelabs.com — Compound Spotlight: Diacetyl](https://www.whitelabs.com/news-update-detail?id=54).
|
||||
|
||||
[^diacetyl-rest]:
|
||||
Brewing Science Institute: diacetyl "is produced during the fermentation
|
||||
process, primarily as a byproduct of yeast metabolism… generally considered
|
||||
a flaw in most beer styles." Source:
|
||||
[brewingscience.com — Diacetyl: Understanding Its Role as an Off-Flavor in Beer](https://brewingscience.com/diacetyl-understanding-its-role-as-an-off-flavor-in-beer/).
|
||||
|
||||
[^oxford-beer]:
|
||||
Oxford Companion to Beer via _Beer & Brewing_: "At low to moderate levels,
|
||||
diacetyl can be perceived as a positive flavor characteristic in some ales
|
||||
and stouts" but "particularly unwelcome in lager-style beers." Source:
|
||||
[beerandbrewing.com — diacetyl](https://www.beerandbrewing.com/dictionary/48TDqQibPi).
|
||||
|
||||
[^yn-wiki]:
|
||||
Wikipedia: "Yamada Nishiki (山田錦) is a short-grain Japanese rice famous
|
||||
for its use in high-quality sake." Source:
|
||||
[en.wikipedia.org/wiki/Yamada_Nishiki](https://en.wikipedia.org/wiki/Yamada_Nishiki).
|
||||
|
||||
[^yn-sakestreet]:
|
||||
Sake Street: Yamadanishiki's large _shinpaku_ allows koji mold to penetrate
|
||||
to the centre of the rice grain, making it "particularly suitable for
|
||||
producing good koji." Source:
|
||||
[sakestreet.com — What is Yamadanishiki?](https://sakestreet.com/en/media/what-is-yamadanishiki).
|
||||
|
||||
[^yn-sakeonline]:
|
||||
Sake Online: "Steamed rice is added to make koji (rice malt) and yeast
|
||||
starter, which promotes alcohol fermentation." Source:
|
||||
[sakeonline.com.au — Types of Sake Rice: Yamada Nishiki](https://sakeonline.com.au/blogs/news/types-of-sake-rice-yamada-nishiki-and-its-characteristics).
|
||||
|
||||
[^anaerobic]:
|
||||
Pai et al. (2022): "Breweries have recognized oxygen exclusion as a top
|
||||
priority for the proper packaging and aging of beer… packaged beer is an
|
||||
anaerobic environment." _Microbiology Spectrum._ Source:
|
||||
[journals.asm.org](https://journals.asm.org/doi/10.1128/spectrum.02656-22).
|
||||
|
||||
[^packaging]:
|
||||
Beer Production Processes (oboe.com): Professional packaging lines use
|
||||
double CO_2 pre-evacuation cycles and closed transfers "so the beer moves in
|
||||
a completely anaerobic environment." Source:
|
||||
[oboe.com — Flavor Quality Control](https://oboe.com/learn/beer-production-processes-308lmf/flavor-quality-control-4).
|
||||
439
docs/pipeline/README.md
Normal file
439
docs/pipeline/README.md
Normal file
@@ -0,0 +1,439 @@
|
||||
# Biergarten Pipeline
|
||||
|
||||
A C++20 command-line pipeline that samples city records from local JSON,
|
||||
enriches each with Wikipedia context, and generates bilingual brewery names and
|
||||
descriptions via a local GGUF model or a deterministic mock.
|
||||
|
||||
> **This pipeline produces AI-generated data.** It is not a source of truth for
|
||||
> brewing techniques, cultural representation, or local-language accuracy. See
|
||||
> [ETHICS-AND-KNOWN-ISSUES.md](./ETHICS-AND-KNOWN-ISSUES.md) for a full
|
||||
> documentation of limitations, hallucination patterns, and bias.
|
||||
|
||||
---
|
||||
|
||||
## Table of Contents
|
||||
|
||||
- [How It Fits The Main App](#how-it-fits-the-main-app)
|
||||
- [Quick Start](#quick-start)
|
||||
- [Build](#build)
|
||||
- [Model](#model)
|
||||
- [Run](#run)
|
||||
- [Docker / RunPod](#docker--runpod)
|
||||
- [Architecture](#architecture)
|
||||
- [Pipeline Stages](#pipeline-stages)
|
||||
- [Key Components](#key-components)
|
||||
- [Runtime Behaviour](#runtime-behaviour)
|
||||
- [Generated Output](#generated-output)
|
||||
- [Tech Stack](#tech-stack)
|
||||
- [Tested Hardware](#tested-hardware)
|
||||
- [Fixture Strategy](#fixture-strategy)
|
||||
- [Repo Layout](#repo-layout)
|
||||
- [Code Tour](#code-tour)
|
||||
- [Next Steps](#next-steps)
|
||||
|
||||
---
|
||||
|
||||
## How It Fits The Main App
|
||||
|
||||
The pipeline is a data ingestion layer. It sits outside the web app runtime and
|
||||
produces seed records the app imports at startup or during a dedicated seed
|
||||
step.
|
||||
|
||||
| Planned app area | Pipeline contribution |
|
||||
| -------------------------------- | ------------------------------------------------------------------ |
|
||||
| Brewery discovery and management | Sampled city records, localized names, long-form descriptions |
|
||||
| Beer reviews and ratings | Stable brewery fixtures with enough context to anchor review pages |
|
||||
| Social follow relationships | Repeatable brewery entities for feeds, follows, and saved lists |
|
||||
| Geospatial brewery experiences | Latitude, longitude, and country-level metadata |
|
||||
|
||||
---
|
||||
|
||||
## Quick Start
|
||||
|
||||
### Build
|
||||
|
||||
Requirements: C++20 compiler, CMake 3.31+, OpenSSL, Boost (JSON and
|
||||
ProgramOptions). SQLite is fetched from the upstream amalgamation, so no system
|
||||
SQLite package is required.
|
||||
|
||||
```bash
|
||||
cmake -S . -B build
|
||||
cmake --build build
|
||||
```
|
||||
|
||||
CMake automatically detects whether a compatible llama.cpp installation is
|
||||
present on the system (`libllama`, `libggml`, `libggml-base`, and `llama.h`
|
||||
visible on the default search paths). If found, it links against those
|
||||
libraries and skips the FetchContent build. If not found, it fetches and builds
|
||||
llama.cpp from source at tag `b9012`. No additional flags are required in
|
||||
either case.
|
||||
|
||||
Metal is enabled automatically on Apple Silicon. CUDA or HIP/ROCm is detected
|
||||
automatically on Linux when the relevant toolkit is present.
|
||||
|
||||
### Model
|
||||
|
||||
> Skip this step if you only need `--mocked`.
|
||||
|
||||
```bash
|
||||
mkdir -p models
|
||||
curl -L \
|
||||
-o models/google_gemma-4-E4B-it-Q6_K.gguf \
|
||||
https://huggingface.co/bartowski/google_gemma-4-E4B-it-GGUF/resolve/main/google_gemma-4-E4B-it-Q6_K.gguf?download=true
|
||||
```
|
||||
|
||||
### Run
|
||||
|
||||
Run from `build/` so the copied `locations.json` and `prompts/` are available.
|
||||
Each run writes a fresh dated SQLite file such as
|
||||
`biergarten_seed_2026-04-19T15-30-45.123456Z.sqlite` into the working directory.
|
||||
|
||||
```bash
|
||||
./biergarten-pipeline --mocked
|
||||
|
||||
./biergarten-pipeline \
|
||||
--model ../models/google_gemma-4-E4B-it-Q6_K.gguf \
|
||||
--prompt-dir prompts \
|
||||
--temperature 1.0 --top-p 0.95 --top-k 64 --n-ctx 8192 --seed -1
|
||||
```
|
||||
|
||||
#### CLI Flags
|
||||
|
||||
| Flag | Purpose |
|
||||
| --------------- | ---------------------------------------------------------------------------------------------------- |
|
||||
| `--mocked` | Deterministic mock generator, no model required. |
|
||||
| `--model, -m` | Path to a GGUF file. Required unless `--mocked` is set. |
|
||||
| `--prompt-dir` | Directory containing prompt files (e.g. `BREWERY_GENERATION.md`). Required unless `--mocked` is set. |
|
||||
| `--output, -o` | Directory for generated SQLite artifacts. Default: `output`. |
|
||||
| `--log-path` | Path for application logs. Default: `pipeline.log`. |
|
||||
| `--temperature` | Sampling temperature. Default: `1.0`. |
|
||||
| `--top-p` | Nucleus sampling. Default: `0.95`. |
|
||||
| `--top-k` | Top-k sampling. Default: `64`. |
|
||||
| `--n-ctx` | Context window size. Default: `8192`. |
|
||||
| `--seed` | Random seed. Default: `-1` (random at runtime). |
|
||||
| `--help, -h` | Print usage and exit. |
|
||||
|
||||
`--mocked` and `--model` are mutually exclusive. Omitting both exits with an
|
||||
error before the pipeline starts. Sampling flags are ignored when `--mocked` is
|
||||
set.
|
||||
|
||||
The post-build step copies `prompts/` into `build/prompts/`. Rebuild after
|
||||
editing any prompt file.
|
||||
|
||||
---
|
||||
|
||||
## Docker / RunPod
|
||||
|
||||
The `tooling/pipeline/runpod/` directory contains a GPU-ready container
|
||||
configuration for running the pipeline on RunPod or any Docker host with an
|
||||
NVIDIA GPU.
|
||||
|
||||
### How it works
|
||||
|
||||
The container uses a two-stage build. The first stage pulls prebuilt
|
||||
`libllama`, `libggml`, and backend plugin libraries (including `libggml-cuda.so`
|
||||
and the CPU variant plugins) from `ghcr.io/ggml-org/llama.cpp:full-cuda`. The
|
||||
second stage copies those libraries into `/usr/local/lib` and runs `ldconfig` so
|
||||
the dynamic linker and `dlopen` calls from `ggml_backend_load_all()` can resolve
|
||||
the CUDA backend plugin at runtime. llama.cpp headers are cloned at the matching
|
||||
tag and installed into `/usr/local/include`. CMake auto-detects both and skips
|
||||
the FetchContent source build entirely, keeping image build times short.
|
||||
|
||||
`GGML_BACKEND_PATH` is set to `/usr/local/lib` so llama.cpp knows where to scan
|
||||
for backend plugins.
|
||||
|
||||
### Build the image
|
||||
|
||||
Run from the `tooling/pipeline/` directory (the CMake project root), not from
|
||||
inside `runpod/`, so the `COPY . .` step picks up the full project context.
|
||||
|
||||
```bash
|
||||
docker build -t biergarten-pipeline:latest -f runpod/Dockerfile .
|
||||
```
|
||||
|
||||
To monitor the full build output and confirm CMake selects the system llama.cpp:
|
||||
|
||||
```bash
|
||||
docker build \
|
||||
--progress=plain \
|
||||
--no-cache \
|
||||
-t biergarten-pipeline:latest \
|
||||
-f runpod/Dockerfile \
|
||||
. 2>&1 | tee build.log
|
||||
```
|
||||
|
||||
Look for `[biergarten] Found system llama.cpp — skipping FetchContent` in the
|
||||
output to confirm the fast path was taken.
|
||||
|
||||
### Run in mocked mode
|
||||
|
||||
No model or GPU required. Useful for validating the pipeline logic and SQLite
|
||||
export path.
|
||||
|
||||
```bash
|
||||
docker run --rm \
|
||||
-e BIERGARTEN_MODE=mocked \
|
||||
-v "$PWD/output:/workspace/output" \
|
||||
-v "$PWD/logs:/workspace/logs" \
|
||||
biergarten-pipeline:latest
|
||||
```
|
||||
|
||||
### Run in live mode
|
||||
|
||||
Mount your GGUF model before starting. The container validates the model path
|
||||
before launching the binary.
|
||||
|
||||
```bash
|
||||
docker run --rm \
|
||||
--runtime=nvidia \
|
||||
-e BIERGARTEN_MODE=live \
|
||||
-e GGML_BACKEND_PATH="/usr/local/lib/libggml-cuda.so" \
|
||||
-v "$PWD/models:/workspace/models" \
|
||||
-v "$PWD/output:/workspace/output" \
|
||||
-v "$PWD/logs:/workspace/logs" \
|
||||
biergarten-pipeline:latest
|
||||
```
|
||||
|
||||
The model must be present at `./models/google_gemma-4-E4B-it-Q6_K.gguf` on the
|
||||
host. See [Model](#model) above for the download command.
|
||||
|
||||
### RunPod deployment
|
||||
|
||||
Use a GPU pod template. Mount persistent storage for `/workspace/models`,
|
||||
`/workspace/output`, and `/workspace/logs`. Set `BIERGARTEN_MODE=live` in the
|
||||
template environment. See `tooling/pipeline/runpod/pod-template.yaml` for a
|
||||
starter template.
|
||||
|
||||
---
|
||||
|
||||
## Architecture
|
||||
|
||||
### Pipeline Stages
|
||||
|
||||
| Stage | Implementation |
|
||||
| -------- | --------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| Load | `JsonLoader::LoadLocations()` reads `locations.json` into typed `Location` records. |
|
||||
| Sample | `BiergartenDataGenerator::QueryCitiesWithCountries()` samples up to 50 locations per run. |
|
||||
| Enrich | `WikipediaService` fetches city and beer context. Keeps going when a lookup fails. |
|
||||
| Generate | `MockGenerator` or `LlamaGenerator` produces brewery names and descriptions in English and the local language. |
|
||||
| Store | `SqliteExportService` writes each successful brewery into a fresh dated `.sqlite` database with normalized location and brewery tables. |
|
||||
| Log | `spdlog` writes results and warnings to the console. |
|
||||
|
||||
If enrichment or generation fails for a city, that city is skipped and the
|
||||
pipeline continues.
|
||||
|
||||
### Key Components
|
||||
|
||||
- `src/main.cc` — argument parsing and Boost.DI composition root.
|
||||
- `JsonLoader` — validates curated location input.
|
||||
- `WikipediaService` — queries Wikipedia extracts, caches results, returns empty
|
||||
context on failure.
|
||||
- `LlamaGenerator` — formats prompts for Gemma 4, validates JSON output, retries
|
||||
malformed responses up to three times. If output looks truncated, the retry
|
||||
raises the token budget before trying again.
|
||||
- `MockGenerator` — stable hash-based output so the same city input always
|
||||
produces the same brewery.
|
||||
- `SqliteExportService` — creates a dated SQLite file per run and persists each
|
||||
successful brewery into normalized tables.
|
||||
- Brewery payloads include English and local-language name and description
|
||||
fields.
|
||||
|
||||
### Runtime Behaviour
|
||||
|
||||
`WikipediaService` queries city, country, and beer-related Wikipedia extracts
|
||||
using its configured lookup, then caches the first successful response per query
|
||||
string. The fetched extract text is included in the prompt as context for
|
||||
generation.
|
||||
|
||||
`GetLocationContext()` returns an empty string when the web client is
|
||||
unavailable or when lookup/parsing fails.
|
||||
|
||||
`LlamaGenerator` validates model output as structured JSON. The retry path
|
||||
exists as a safety hatch for cases where the reasoning block consumes available
|
||||
token budget and compresses the JSON output space. All runs to date have
|
||||
produced valid output on the first pass; the path is kept for resilience.
|
||||
|
||||
`MockGenerator` uses stable hashes for repeatable output in demos and Storybook
|
||||
runs.
|
||||
|
||||
### Process Flow - Activity Diagram
|
||||
|
||||

|
||||
|
||||
### Architectural Overview - Class Diagram
|
||||
|
||||

|
||||
|
||||
---
|
||||
|
||||
## Generated Output
|
||||
|
||||
Each successful run stores a `GeneratedBrewery` pair with the source location
|
||||
and a `BreweryResult` payload. The same generated records are also written to a
|
||||
fresh SQLite export file named with the current UTC timestamp.
|
||||
|
||||
| Field | Meaning |
|
||||
| ------------------- | ------------------------------------------ |
|
||||
| `name_en` | Brewery name in English. |
|
||||
| `description_en` | Brewery description in English. |
|
||||
| `name_local` | Brewery name in the local language. |
|
||||
| `description_local` | Brewery description in the local language. |
|
||||
|
||||
The log dump also includes city, country, state or province, ISO subdivision
|
||||
code, latitude, and longitude for each entry.
|
||||
|
||||
### Consumer Data Shape
|
||||
|
||||
| Field | Why it matters |
|
||||
| ----------------------------------- | ------------------------------------------------ |
|
||||
| `city`, `state_province`, `country` | Human-readable location labels and page headings |
|
||||
| `iso3166_1`, `iso3166_2` | Filtering, regional grouping, locale matching |
|
||||
| `latitude`, `longitude` | Map pins and nearby brewery views |
|
||||
| `local_languages` | Locale-aware copy selection |
|
||||
| `name_en`, `description_en` | Default English display content |
|
||||
| `name_local`, `description_local` | Local-language display content |
|
||||
| `region_context` | Richer copy for cards and detail pages |
|
||||
|
||||
---
|
||||
|
||||
## Tech Stack
|
||||
|
||||
- C++20
|
||||
- CMake 3.31+
|
||||
- Boost.JSON, Boost.ProgramOptions, Boost.DI
|
||||
- spdlog
|
||||
- cpp-httplib (with OpenSSL)
|
||||
- SQLite amalgamation fetched and compiled via CMake FetchContent
|
||||
- llama.cpp (auto-detected from system install or fetched via FetchContent)
|
||||
- Docker with NVIDIA CUDA 12.6 base image for GPU container builds
|
||||
- RunPod for cloud GPU inference
|
||||
|
||||
The build fetches Boost.DI, spdlog, and SQLite via CMake. llama.cpp is fetched
|
||||
only when a system installation is not detected. Metal is enabled on Apple
|
||||
Silicon; CUDA or HIP/ROCm is detected on Linux when the toolkit is present.
|
||||
|
||||
> **Code Style:** Modern C++20 throughout — RAII for ownership,
|
||||
> `std::unique_ptr` for injected dependencies, `std::optional` for parse
|
||||
> outcomes, `std::span` for read-only views over generated city data, structured
|
||||
> bindings in pipeline loops. Formatting follows the Google C++ Style Guide via
|
||||
> `.clang-format` with a narrow column limit and two-space indentation.
|
||||
|
||||
---
|
||||
|
||||
## Tested Hardware
|
||||
|
||||
### ARM macOS — M1 Pro
|
||||
|
||||
| | |
|
||||
| --------- | --------------------------------- |
|
||||
| Host | MacBook Pro 14" (2021) |
|
||||
| CPU | Apple M1 Pro (8-core) |
|
||||
| GPU | Apple M1 Pro (14-core integrated) |
|
||||
| Memory | 16 GB |
|
||||
| Model | Gemma 4 E4B |
|
||||
| Inference | llama.cpp with Metal |
|
||||
|
||||
### x86_64 Linux — NVIDIA RTX 2000
|
||||
|
||||
| | |
|
||||
| --------- | ------------------------------ |
|
||||
| Host | ThinkPad P1 Gen 7 (Fedora 43) |
|
||||
| CPU | Intel Core Ultra 7 155H |
|
||||
| GPU | NVIDIA RTX 2000 Ada Generation |
|
||||
| Memory | 32 GB |
|
||||
| Model | Gemma 4 E4B |
|
||||
| Inference | llama.cpp with CUDA 12.x |
|
||||
|
||||
### x86_64 Linux — Docker / RunPod (NVIDIA CUDA)
|
||||
|
||||
| | |
|
||||
| --------- | ------------------------------------------- |
|
||||
| Host | RunPod GPU pod |
|
||||
| Base | nvidia/cuda:12.6.3-devel-ubuntu24.04 |
|
||||
| Model | Gemma 4 E4B Q6_K |
|
||||
| Inference | llama.cpp prebuilt CUDA backends via dlopen |
|
||||
|
||||
---
|
||||
|
||||
## Fixture Strategy
|
||||
|
||||
- `--mocked` for stable fixtures, repeatable screenshots, and Storybook runs.
|
||||
- `--model` when geographically grounded content matters for demos.
|
||||
- Keep `locations.json` structured enough to support discovery and future
|
||||
filtering.
|
||||
- Treat SQLite output as seed material for the app's brewery domain, not
|
||||
production data.
|
||||
|
||||
---
|
||||
|
||||
## Repo Layout
|
||||
|
||||
| Path | Purpose |
|
||||
| ---------------------------- | -------------------------------------------------- |
|
||||
| `includes/` | Public headers and shared models. |
|
||||
| `src/` | Implementation files. |
|
||||
| `locations.json` | Curated city input copied into the build tree. |
|
||||
| `prompts/` | System prompts used by the model-backed path. |
|
||||
| `diagrams/` | Architecture and pipeline diagrams. |
|
||||
| `tooling/pipeline/runpod/` | Dockerfile, launcher, and RunPod pod template. |
|
||||
| `ETHICS-AND-KNOWN-ISSUES.md` | Ethics, bias, hallucination analysis, mitigations. |
|
||||
|
||||
---
|
||||
|
||||
## Code Tour
|
||||
|
||||
- `src/main.cc` — argument parsing and DI composition root.
|
||||
- `src/biergarten_data_generator/` — orchestration, sampling, logging, and
|
||||
export.
|
||||
- `src/services/wikipedia/` — enrichment service and cache.
|
||||
- `src/services/sqlite/` — SQLite export implementation.
|
||||
- `src/data_generation/llama/` — local inference, prompt loading, output
|
||||
validation.
|
||||
- `src/data_generation/mock/` — deterministic fallback.
|
||||
- `tooling/pipeline/runpod/` — container build and runtime launcher.
|
||||
|
||||
---
|
||||
|
||||
## Next Steps
|
||||
|
||||
The pipeline currently produces city-aware brewery records and dated SQLite
|
||||
exports. The next passes add additional fixture types so the app can exercise
|
||||
the full brewery domain without live data.
|
||||
|
||||
### Testing — Very High Priority
|
||||
|
||||
- Unit test JSON validation and retry logic against malformed, truncated, and
|
||||
empty model outputs.
|
||||
- Integration test the enrichment pipeline with missing context, short context,
|
||||
and fake context inputs.
|
||||
- Adversarial context tests: feed plausible but geographically incorrect
|
||||
Wikipedia extracts and verify the model does not silently blend them with
|
||||
training data.
|
||||
- Verify bilingual enrichment behaviour when only an English extract is
|
||||
available versus when both extracts are present.
|
||||
- Confirm the retry path is reachable when the reasoning block consumes
|
||||
available token budget.
|
||||
|
||||
### Beer Generation
|
||||
|
||||
Generate catalog entries with style, ABV, IBU, color, aroma notes, and food
|
||||
pairing hints. Link beers back to breweries and cities. Keep style coverage wide
|
||||
enough to exercise search, sort, and category filters.
|
||||
|
||||
### User Generation
|
||||
|
||||
Generate user profiles with stable names, bios, locale hints, and preference
|
||||
signals. Include stable IDs for downstream fixture joins. Keep output
|
||||
deterministic for screenshots while allowing larger randomized batches.
|
||||
|
||||
### Check-In System
|
||||
|
||||
Produce timestamped check-in events between users and breweries. Use a J-curve
|
||||
activity profile — a small set of users accounts for most check-ins, the rest
|
||||
appear occasionally. Add bursty behaviour around weekends and travel periods.
|
||||
|
||||
### Beer Ratings
|
||||
|
||||
Generate rating events with a strong positive skew and a long tail of lower
|
||||
scores. Avoid uniform distributions. Attach timestamps and user IDs so the app
|
||||
can compute averages, trends, and per-style comparisons.
|
||||
34
docs/pipeline/diagrams/biergarten-weizen-theme.puml
Normal file
34
docs/pipeline/diagrams/biergarten-weizen-theme.puml
Normal file
@@ -0,0 +1,34 @@
|
||||
skinparam shadowing false
|
||||
skinparam backgroundColor #FCFCF7
|
||||
skinparam defaultFontName "DM Sans"
|
||||
skinparam defaultFontColor #14180C
|
||||
skinparam titleFontName "Volkhov"
|
||||
skinparam titleFontColor #14180C
|
||||
skinparam ArrowColor #656F33
|
||||
skinparam NoteBackgroundColor #DBEEDD
|
||||
skinparam NoteFontColor #14180C
|
||||
skinparam NoteBorderColor #4A5837
|
||||
skinparam SwimlaneBorderColor #4A5837
|
||||
skinparam SwimlaneBorderThickness 1
|
||||
skinparam activityStartColor #EBECE3
|
||||
skinparam activityEndColor #4A5837
|
||||
skinparam activityStopColor #4A5837
|
||||
skinparam ActivityBackgroundColor #EBECE3
|
||||
skinparam ActivityBorderColor #4A5837
|
||||
skinparam ActivityDiamondBackgroundColor #CBD2B5
|
||||
skinparam ActivityDiamondBorderColor #4A5837
|
||||
skinparam packageStyle rectangle
|
||||
skinparam packageBackgroundColor #F1F3EA
|
||||
skinparam packageBorderColor #4A5837
|
||||
skinparam packageFontColor #14180C
|
||||
skinparam classBackgroundColor #EBECE3
|
||||
skinparam classBorderColor #4A5837
|
||||
skinparam classFontColor #14180C
|
||||
skinparam classAttributeFontColor #3F4724
|
||||
skinparam classStereotypeFontColor #4A5837
|
||||
skinparam interfaceBackgroundColor #DBEEDD
|
||||
skinparam interfaceBorderColor #4A5837
|
||||
skinparam interfaceFontColor #14180C
|
||||
skinparam enumBackgroundColor #E4E6D8
|
||||
skinparam enumBorderColor #4A5837
|
||||
skinparam enumFontColor #14180C
|
||||
@@ -29,7 +29,7 @@ if (Are arguments valid?) then (no)
|
||||
else (yes)
|
||||
endif
|
||||
|
||||
:Init CurlGlobalState & LlamaBackendState;
|
||||
:Init OpenSSL global state & LlamaBackendState;
|
||||
:di::make_injector(...);
|
||||
:injector.create<std::unique_ptr<BiergartenDataGenerator>>();
|
||||
:BiergartenDataGenerator::Run();
|
||||
@@ -26,6 +26,7 @@ skinparam note {
|
||||
title The Biergarten Data Pipeline - Class Diagram
|
||||
|
||||
class BiergartenDataGenerator {
|
||||
- logger_ : std::shared_ptr<ILogger>
|
||||
- context_service_ : std::unique_ptr<IEnrichmentService>
|
||||
- generator_ : std::unique_ptr<DataGenerator>
|
||||
- exporter_ : std::unique_ptr<IExportService>
|
||||
@@ -36,6 +37,46 @@ class BiergartenDataGenerator {
|
||||
- LogResults() : void
|
||||
}
|
||||
|
||||
class LogLevel <<enumeration>> {
|
||||
Debug
|
||||
Info
|
||||
Warn
|
||||
Error
|
||||
}
|
||||
|
||||
class PipelinePhase <<enumeration>> {
|
||||
Startup
|
||||
UserGeneration
|
||||
BreweryAndBeerGeneration
|
||||
CheckinGeneration
|
||||
RatingGeneration
|
||||
FollowGeneration
|
||||
Teardown
|
||||
}
|
||||
|
||||
struct LogEntry {
|
||||
+ timestamp : std::chrono::system_clock::time_point
|
||||
+ level : LogLevel
|
||||
+ phase : PipelinePhase
|
||||
+ message : std::string
|
||||
+ worker : std::optional<std::string>
|
||||
}
|
||||
|
||||
interface ILogger <<interface>> {
|
||||
+ Log(entry : const LogEntry&) : void
|
||||
}
|
||||
|
||||
class LogProducer {
|
||||
- channel_ : BoundedChannel<LogEntry>&
|
||||
+ Log(entry : const LogEntry&) : void
|
||||
}
|
||||
|
||||
class LogDispatcher {
|
||||
- channel_ : BoundedChannel<LogEntry>&
|
||||
+ Run() : void
|
||||
- ToSpdlogLevel(level) : spdlog::level::level_enum
|
||||
}
|
||||
|
||||
interface IEnrichmentService <<interface>> {
|
||||
+ GetLocationContext(loc : const Location&) : std::string
|
||||
}
|
||||
@@ -52,7 +93,7 @@ interface WebClient <<interface>> {
|
||||
+ UrlEncode(value : const std::string&) : std::string
|
||||
}
|
||||
|
||||
class CURLWebClient {
|
||||
class HttpWebClient {
|
||||
+ Get(url : const std::string&) : std::string
|
||||
+ UrlEncode(value : const std::string&) : std::string
|
||||
}
|
||||
@@ -123,14 +164,21 @@ class SystemDateTimeProvider {
|
||||
}
|
||||
|
||||
' Structural Relationships / Dependency Injection
|
||||
BiergartenDataGenerator *-- ILogger : owns
|
||||
BiergartenDataGenerator *-- IEnrichmentService : owns
|
||||
BiergartenDataGenerator *-- DataGenerator : owns
|
||||
BiergartenDataGenerator *-- IExportService : owns
|
||||
|
||||
LogEntry *-- LogLevel
|
||||
LogEntry *-- PipelinePhase
|
||||
ILogger <|.. LogProducer : implements
|
||||
LogProducer ..> LogEntry : emits
|
||||
LogDispatcher ..> LogEntry : consumes
|
||||
|
||||
IEnrichmentService <|.. WikipediaService : implements
|
||||
WikipediaService *-- WebClient : owns
|
||||
|
||||
WebClient <|.. CURLWebClient : implements
|
||||
WebClient <|.. HttpWebClient : implements
|
||||
|
||||
DataGenerator <|.. MockGenerator : implements
|
||||
DataGenerator <|.. LlamaGenerator : implements
|
||||
1
docs/pipeline/diagrams/current/output/activity.svg
Normal file
1
docs/pipeline/diagrams/current/output/activity.svg
Normal file
File diff suppressed because one or more lines are too long
1
docs/pipeline/diagrams/current/output/class.svg
Normal file
1
docs/pipeline/diagrams/current/output/class.svg
Normal file
File diff suppressed because one or more lines are too long
360
docs/pipeline/diagrams/planned/activity.puml
Normal file
360
docs/pipeline/diagrams/planned/activity.puml
Normal file
@@ -0,0 +1,360 @@
|
||||
@startuml biergarten_activity
|
||||
!include ../biergarten-weizen-theme.puml
|
||||
skinparam defaultFontSize 13
|
||||
skinparam titleFontSize 20
|
||||
|
||||
title The Biergarten Data Pipeline — Activity Diagram
|
||||
|
||||
|Main|
|
||||
start
|
||||
:ParseArguments(argc, argv);
|
||||
if (Invalid args?) then (yes)
|
||||
:spdlog::error;
|
||||
stop
|
||||
else (no)
|
||||
endif
|
||||
:Init OpenSSL global state & LlamaBackendState;
|
||||
:Build DI injector;
|
||||
|
||||
:Initialize SqliteExportService;
|
||||
note right
|
||||
Opens SQLite connection.
|
||||
(Transactions are now managed
|
||||
per-phase via batching).
|
||||
end note
|
||||
|
||||
:Create BoundedChannel<LogEntry> log_ch;
|
||||
:Spawn Log Worker thread;
|
||||
note right
|
||||
Log worker drains log_ch for the
|
||||
entire pipeline lifetime.
|
||||
All workers emit LogEntry structs
|
||||
via PipelineLogger -- never spdlog directly.
|
||||
end note
|
||||
|
||||
:BiergartenPipelineOrchestrator::Run();
|
||||
|BiergartenPipelineOrchestrator::Run()|
|
||||
|
||||
fork
|
||||
:JsonLoader::LoadBeerStyles("beer-styles.json");
|
||||
:EnrichmentService::PreWarmBeerStyleCache(beer_styles);
|
||||
fork again
|
||||
:JsonLoader::LoadLocations("locations.json");
|
||||
:EnrichmentService::PreWarmLocationCache(sampled_locations);
|
||||
end fork
|
||||
fork
|
||||
:JsonLoader::LoadNamesByCountry("names-by-country.json");
|
||||
fork again
|
||||
:JsonLoader::LoadPersonas("personas.json");
|
||||
end fork
|
||||
|
||||
' ═══════════════════════════════════════════
|
||||
' PHASE 0 — USER GENERATION
|
||||
' ═══════════════════════════════════════════
|
||||
|Orchestrator|
|
||||
:RunUserPhase(sampled_locations);
|
||||
:Create BoundedChannels\n(loc_ch, exp_ch);
|
||||
|
||||
fork
|
||||
|Orchestrator|
|
||||
:Loop: Send Locations -> loc_ch;
|
||||
:Close loc_ch;
|
||||
note right
|
||||
Producer closes loc_ch.
|
||||
LLM Worker while loop
|
||||
terminates on empty + closed.
|
||||
end note
|
||||
fork again
|
||||
|LLM Worker|
|
||||
while (loc_ch has items?) is (yes)
|
||||
:Receive Location;
|
||||
|
||||
:GetLocationContextFromCache(location);
|
||||
note right
|
||||
Guaranteed cache hit from startup.
|
||||
end note
|
||||
|
||||
:IPersonaSelectionStrategy::SelectPersona(\n personas_palette_);
|
||||
note right
|
||||
Guaranteed cache hit from startup.
|
||||
Returns a Persona struct carrying
|
||||
style_affinities, abv_range,
|
||||
ibu_preference, checkin_weight.
|
||||
end note
|
||||
|
||||
:NamesByCountry::SampleName(\n location.iso3166_1);
|
||||
note right
|
||||
Deterministic lookup -- no LLM involved.
|
||||
Name selected from pre-keyed table
|
||||
and passed into the generation prompt.
|
||||
end note
|
||||
|
||||
:GenerateUser(enriched_city, persona, sampled_name)\nvia DataGenerator;
|
||||
note right
|
||||
LLM receives: EnrichedCity context + persona
|
||||
description + sampled name. Generates
|
||||
bio and preference signals grounded
|
||||
in locale and persona.
|
||||
end note
|
||||
|
||||
:PipelineLogger::Log(Info, UserGeneration,\n city, user_id, "llm");
|
||||
:Send GeneratedUser -> exp_ch;
|
||||
endwhile (no)
|
||||
:Close exp_ch;
|
||||
note right
|
||||
Producer closes exp_ch.
|
||||
SQLite Worker while loop
|
||||
terminates on empty + closed.
|
||||
end note
|
||||
fork again
|
||||
|SQLite Worker|
|
||||
:BEGIN TRANSACTION;
|
||||
while (exp_ch has items?) is (yes)
|
||||
:Receive GeneratedUser;
|
||||
:ProcessUser(user);
|
||||
:PipelineLogger::Log(Info, UserGeneration,\n city, user_id, "sqlite");
|
||||
:Append -> user_pool_;
|
||||
if (Batch size reached?) then (yes)
|
||||
:COMMIT & BEGIN;
|
||||
else (no)
|
||||
endif
|
||||
endwhile (no)
|
||||
:COMMIT (Final);
|
||||
end fork
|
||||
|
||||
|Orchestrator|
|
||||
:Join LLM Worker, SQLite Worker;
|
||||
|
||||
' ═══════════════════════════════════════════
|
||||
' PHASE 1a — BREWERY GENERATION
|
||||
' ═══════════════════════════════════════════
|
||||
:RunBreweryPhase(sampled_locations);
|
||||
:Create BoundedChannels\n(loc_ch, exp_ch);
|
||||
|
||||
fork
|
||||
|Orchestrator|
|
||||
:Loop: Sample User from user_pool_
|
||||
and pair with Location;
|
||||
:Send BreweryTask(Location, User) -> loc_ch;
|
||||
:Close loc_ch;
|
||||
fork again
|
||||
|LLM Worker|
|
||||
while (loc_ch has items?) is (yes)
|
||||
:Receive BreweryTask(Location, User);
|
||||
|
||||
:GetLocationContextFromCache(task.location);
|
||||
note right
|
||||
Guaranteed cache hit from startup.
|
||||
end note
|
||||
|
||||
:GenerateBrewery(enriched_city, context, task.user)\nvia DataGenerator;
|
||||
note right
|
||||
KV cache stays warm.
|
||||
Brewery is linked to the sampled owner_user_id.
|
||||
end note
|
||||
:PipelineLogger::Log(Info,\n BreweryGeneration,\n city, brewery_id, "llm");
|
||||
:Send GeneratedBrewery -> exp_ch;
|
||||
endwhile (no)
|
||||
:Close exp_ch;
|
||||
fork again
|
||||
|SQLite Worker|
|
||||
:BEGIN TRANSACTION;
|
||||
while (exp_ch has items?) is (yes)
|
||||
:Receive GeneratedBrewery;
|
||||
:ProcessBrewery(brewery);
|
||||
:PipelineLogger::Log(Info,\n BreweryGeneration,\n city, brewery_id, "sqlite");
|
||||
:Append -> brewery_pool_;
|
||||
if (Batch size reached?) then (yes)
|
||||
:COMMIT & BEGIN;
|
||||
else (no)
|
||||
endif
|
||||
endwhile (no)
|
||||
:COMMIT (Final);
|
||||
end fork
|
||||
|
||||
|Orchestrator|
|
||||
:Join LLM Worker, SQLite Worker;
|
||||
note right
|
||||
brewery_pool_ is now fully populated.
|
||||
Phase 1b may begin.
|
||||
end note
|
||||
|
||||
' ═══════════════════════════════════════════
|
||||
' PHASE 1b — BEER GENERATION
|
||||
' ═══════════════════════════════════════════
|
||||
:RunBeerPhase();
|
||||
:Create BoundedChannels\n(brew_ch, exp_ch);
|
||||
|
||||
fork
|
||||
|Orchestrator|
|
||||
:Loop: Send Breweries -> brew_ch;
|
||||
:Close brew_ch;
|
||||
fork again
|
||||
|LLM Worker|
|
||||
while (brew_ch has items?) is (yes)
|
||||
:Receive GeneratedBrewery;
|
||||
:IBeerSelectionStrategy::SelectStyles(\n brewery, beer_style_palette_);
|
||||
|
||||
while (For each selected BeerStyle?) is (remaining)
|
||||
:GetStyleContextFromCache(style);
|
||||
note right
|
||||
Guaranteed cache hit from startup.
|
||||
KV cache stays warm across all
|
||||
beer generations -- system prompt
|
||||
does not change within this phase.
|
||||
end note
|
||||
:GenerateBeer(brewery, style_context)\nvia DataGenerator;
|
||||
:Attach GeneratedBeer to bundle;
|
||||
endwhile (done)
|
||||
|
||||
:PipelineLogger::Log(Info,\n BeerGeneration,\n city, brewery_id, "llm");
|
||||
:Send BeersBundle -> exp_ch;
|
||||
endwhile (no)
|
||||
:Close exp_ch;
|
||||
fork again
|
||||
|SQLite Worker|
|
||||
:BEGIN TRANSACTION;
|
||||
while (exp_ch has items?) is (yes)
|
||||
:Receive BeersBundle;
|
||||
while (For each beer in bundle?) is (remaining)
|
||||
:Set beer.brewery_id from bundle;
|
||||
:ProcessBeer(beer);
|
||||
:Append -> beer_pool_;
|
||||
endwhile (done)
|
||||
:PipelineLogger::Log(Info,\n BeerGeneration,\n city, brewery_id, "sqlite");
|
||||
if (Batch size reached?) then (yes)
|
||||
:COMMIT & BEGIN;
|
||||
else (no)
|
||||
endif
|
||||
endwhile (no)
|
||||
:COMMIT (Final);
|
||||
end fork
|
||||
|
||||
|Orchestrator|
|
||||
:Join LLM Worker, SQLite Worker;
|
||||
note right
|
||||
Both brewery_pool_ and beer_pool_
|
||||
are now completely populated.
|
||||
Checkin and Follow phases may
|
||||
now run in parallel.
|
||||
end note
|
||||
|
||||
' ═══════════════════════════════════════════
|
||||
' PHASE 2 — CHECKIN + FOLLOW GENERATION
|
||||
' (parallel — both depend only on user_pool_
|
||||
' and brewery_pool_ being fully populated)
|
||||
' ═══════════════════════════════════════════
|
||||
fork
|
||||
|Orchestrator|
|
||||
:RunCheckinPhase();
|
||||
:ICheckinDistributionStrategy::\nAssignActivityWeights(user_pool_);
|
||||
note right
|
||||
Weights seeded from each user's
|
||||
persona.checkin_weight. J-curve profile
|
||||
emerges from persona distribution.
|
||||
end note
|
||||
|
||||
:BEGIN TRANSACTION;
|
||||
while (For each GeneratedUser in user_pool_?) is (remaining)
|
||||
:CheckinsForUser(user, brewery_pool_.size());
|
||||
while (For each checkin index?) is (remaining)
|
||||
:TimestampFor(user, index);
|
||||
:Select brewery from brewery_pool_;
|
||||
:GenerateCheckin(user, brewery, timestamp)\nvia DataGenerator;
|
||||
:ProcessCheckin(checkin);
|
||||
:PipelineLogger::Log(Info, CheckinGeneration,\n nullopt, checkin_id, "sqlite");
|
||||
:Append -> checkin_pool_;
|
||||
if (Batch size reached?) then (yes)
|
||||
:COMMIT & BEGIN;
|
||||
else (no)
|
||||
endif
|
||||
endwhile (done)
|
||||
endwhile (done)
|
||||
:COMMIT (Final);
|
||||
|
||||
fork again
|
||||
|Orchestrator|
|
||||
:RunFollowPhase();
|
||||
:IFollowGenerationStrategy::\nAssignFollowWeights(user_pool_);
|
||||
note right
|
||||
For RandomFollowStrategy, weights
|
||||
are uniform. For ActivityWeightedFollowStrategy,
|
||||
weights derived from user.activity_weight
|
||||
so high-activity users attract more followers.
|
||||
end note
|
||||
|
||||
:BEGIN TRANSACTION;
|
||||
:IFollowGenerationStrategy::\nGenerateFollows(user_pool_);
|
||||
note right
|
||||
Self-follow constraint (follower_id != followed_id)
|
||||
enforced here and at the DB schema level.
|
||||
end note
|
||||
while (For each GeneratedFollow?) is (remaining)
|
||||
:ProcessFollow(follow);
|
||||
:PipelineLogger::Log(Info, FollowGeneration,\n nullopt, follower_id, "sqlite");
|
||||
:Append -> follow_pool_;
|
||||
if (Batch size reached?) then (yes)
|
||||
:COMMIT & BEGIN;
|
||||
else (no)
|
||||
endif
|
||||
endwhile (done)
|
||||
:COMMIT (Final);
|
||||
|
||||
end fork
|
||||
|
||||
|Orchestrator|
|
||||
:Join CheckinPhase, FollowPhase;
|
||||
note right
|
||||
checkin_pool_ and follow_pool_
|
||||
are now fully populated.
|
||||
Rating phase may begin.
|
||||
end note
|
||||
|
||||
' ═══════════════════════════════════════════
|
||||
' PHASE 3 — RATING GENERATION
|
||||
' ═══════════════════════════════════════════
|
||||
:RunRatingPhase();
|
||||
note right
|
||||
Beer selection biased by
|
||||
user.persona.style_affinities and abv_range.
|
||||
Rating skew modulated per persona.
|
||||
end note
|
||||
|
||||
:BEGIN TRANSACTION;
|
||||
while (For each GeneratedCheckin in checkin_pool_?) is (remaining)
|
||||
:Match brewery_id, select beer from beer_pool_\n(same brewery_id, biased by persona affinities);
|
||||
if (Beer exists for brewery?) then (yes)
|
||||
:GenerateRating(user, beer, checkin_id)\nvia DataGenerator;
|
||||
:ProcessRating(rating);
|
||||
:PipelineLogger::Log(Info, RatingGeneration,\n nullopt, rating_id, "sqlite");
|
||||
if (Batch size reached?) then (yes)
|
||||
:COMMIT & BEGIN;
|
||||
else (no)
|
||||
endif
|
||||
else (no)
|
||||
:PipelineLogger::Log(Warn, RatingGeneration,\n nullopt, brewery_id, "sqlite");
|
||||
:Skip -- brewery has no beers;
|
||||
endif
|
||||
endwhile (done)
|
||||
:COMMIT (Final);
|
||||
|
||||
' ═══════════════════════════════════════════
|
||||
' TEARDOWN
|
||||
' ═══════════════════════════════════════════
|
||||
|Orchestrator|
|
||||
:Finalize SqliteExportService;
|
||||
note right
|
||||
Safely closes the DB connection.
|
||||
end note
|
||||
:Close log_ch;
|
||||
|
||||
|Main|
|
||||
:spdlog::info "Pipeline complete in X ms";
|
||||
:Join Log Worker;
|
||||
note right
|
||||
Drain guarantees no LogEntry is
|
||||
dropped at shutdown.
|
||||
end note
|
||||
stop
|
||||
|
||||
@enduml
|
||||
@@ -1,51 +1,16 @@
|
||||
@startuml future_possible_architecture
|
||||
@startuml class_diagram
|
||||
|
||||
' ==========================================
|
||||
' CONFIGURATION & STYLING
|
||||
' ==========================================
|
||||
left to right direction
|
||||
skinparam linetype ortho
|
||||
!include ../biergarten-weizen-theme.puml
|
||||
skinparam classAttributeFontSize 9
|
||||
skinparam defaultFontSize 25
|
||||
skinparam titleFontSize 30
|
||||
|
||||
' --- Typography ---
|
||||
skinparam defaultFontName "DM Sans"
|
||||
skinparam defaultFontSize 14
|
||||
skinparam titleFontName "Volkhov"
|
||||
skinparam titleFontSize 20
|
||||
title Biergarten Data Pipeline — Class Diagram
|
||||
|
||||
' --- Global Colors ---
|
||||
skinparam backgroundColor #FCFCF7
|
||||
skinparam defaultFontColor #14180C
|
||||
skinparam titleFontColor #14180C
|
||||
skinparam ArrowColor #656F33
|
||||
|
||||
skinparam class {
|
||||
BackgroundColor #EBECE3
|
||||
HeaderBackgroundColor #CBD2B5
|
||||
BorderColor #4A5837
|
||||
ArrowColor #656F33
|
||||
FontColor #14180C
|
||||
}
|
||||
|
||||
skinparam package {
|
||||
BackgroundColor #DBEEDD
|
||||
BorderColor #4A5837
|
||||
FontColor #14180C
|
||||
}
|
||||
|
||||
skinparam note {
|
||||
BackgroundColor #DBEEDD
|
||||
BorderColor #4A5837
|
||||
FontColor #14180C
|
||||
}
|
||||
|
||||
skinparam monochrome reverse
|
||||
|
||||
title The Biergarten Data Pipeline — Planned Architecture
|
||||
|
||||
' ==========================================
|
||||
' DOMAIN MODELS
|
||||
' ==========================================
|
||||
package "Domain Models" {
|
||||
package "Domain: Models" {
|
||||
|
||||
class Location {
|
||||
+ city : std::string
|
||||
@@ -62,8 +27,9 @@ package "Domain Models" {
|
||||
+ text : std::string
|
||||
+ completeness : Completeness
|
||||
+ char_count : size_t
|
||||
--
|
||||
<<enum>> Completeness
|
||||
}
|
||||
|
||||
enum Completeness {
|
||||
Full
|
||||
Partial
|
||||
Absent
|
||||
@@ -116,138 +82,99 @@ package "Domain Models" {
|
||||
+ note : std::string
|
||||
}
|
||||
|
||||
class GenerationMetadata {
|
||||
+ generation_id : uint64_t
|
||||
+ generated_time : std::string
|
||||
+ context_provided : bool
|
||||
+ generated_with : std::string
|
||||
}
|
||||
|
||||
class GeneratedBrewery {
|
||||
+ brewery_id : sqlite3_int64
|
||||
+ brewery_id : uint64_t
|
||||
+ location : Location
|
||||
+ brewery : BreweryResult
|
||||
+ context_completeness : LocationContext::Completeness
|
||||
+ generated_at : std::string
|
||||
+ metadata : GenerationMetadata
|
||||
}
|
||||
|
||||
class GeneratedBeer {
|
||||
+ beer_id : sqlite3_int64
|
||||
+ brewery_id : sqlite3_int64
|
||||
+ beer_id : uint64_t
|
||||
+ brewery_id : uint64_t
|
||||
+ location : Location
|
||||
+ style : BeerStyle
|
||||
+ beer : BeerResult
|
||||
+ generated_at : std::string
|
||||
+ metadata : GenerationMetadata
|
||||
}
|
||||
|
||||
class GeneratedUser {
|
||||
+ user_id : sqlite3_int64
|
||||
+ user_id : uint64_t
|
||||
+ location : Location
|
||||
+ user : UserResult
|
||||
+ generated_at : std::string
|
||||
+ metadata : GenerationMetadata
|
||||
}
|
||||
|
||||
class GeneratedCheckin {
|
||||
+ checkin_id : sqlite3_int64
|
||||
+ user_id : sqlite3_int64
|
||||
+ brewery_id : sqlite3_int64
|
||||
+ checkin_id : uint64_t
|
||||
+ user_id : uint64_t
|
||||
+ brewery_id : uint64_t
|
||||
+ checkin : CheckinResult
|
||||
+ generated_at : std::string
|
||||
+ metadata : GenerationMetadata
|
||||
}
|
||||
|
||||
class GeneratedRating {
|
||||
+ user_id : sqlite3_int64
|
||||
+ beer_id : sqlite3_int64
|
||||
+ checkin_id : sqlite3_int64
|
||||
+ user_id : uint64_t
|
||||
+ beer_id : uint64_t
|
||||
+ checkin_id : uint64_t
|
||||
+ rating : RatingResult
|
||||
+ generated_at : std::string
|
||||
+ metadata : GenerationMetadata
|
||||
}
|
||||
|
||||
class SamplingOptions {
|
||||
+ temperature : float = 1.0F
|
||||
+ top_p : float = 0.95F
|
||||
+ top_k : uint32_t = 64
|
||||
+ n_ctx : uint32_t = 8192
|
||||
+ seed : int = -1
|
||||
class GeneratedFollow {
|
||||
+ follower_id : uint64_t
|
||||
+ followed_id : uint64_t
|
||||
+ metadata : GenerationMetadata
|
||||
}
|
||||
|
||||
class GeneratorOptions {
|
||||
+ model_path : std::filesystem::path
|
||||
+ use_mocked : bool = false
|
||||
+ sampling : SamplingOptions
|
||||
class UserPersona {
|
||||
+ name: std::string
|
||||
+ description: std::string
|
||||
+ style_affinities: std::vector<std::string>
|
||||
}
|
||||
|
||||
class PipelineOptions {
|
||||
+ output_path : std::filesystem::path
|
||||
+ log_path : std::filesystem::path
|
||||
}
|
||||
|
||||
class ApplicationOptions {
|
||||
+ generator : GeneratorOptions
|
||||
+ pipeline : PipelineOptions
|
||||
}
|
||||
|
||||
' --- Domain Model Relationships ---
|
||||
ApplicationOptions *-- GeneratorOptions
|
||||
ApplicationOptions *-- PipelineOptions
|
||||
GeneratorOptions *-- SamplingOptions
|
||||
LocationContext *-- Completeness
|
||||
}
|
||||
|
||||
|
||||
' ==========================================
|
||||
' LOGGING
|
||||
' ==========================================
|
||||
package "Logging" {
|
||||
|
||||
enum LogLevel {
|
||||
Debug
|
||||
Info
|
||||
Warn
|
||||
Error
|
||||
package "Domain: Application Configuration" {
|
||||
class SamplingOptions {
|
||||
+ temperature: float = 1.0F
|
||||
+ top_p: float = 0.95F
|
||||
+ top_k: uint32_t = 64
|
||||
+ n_ctx: uint32_t = 8192
|
||||
+ seed: int = -1
|
||||
}
|
||||
|
||||
enum PipelinePhase {
|
||||
Startup
|
||||
UserGeneration
|
||||
BreweryAndBeerGeneration
|
||||
CheckinGeneration
|
||||
RatingGeneration
|
||||
Teardown
|
||||
class GeneratorOptions {
|
||||
+ model_path: std::filesystem::path
|
||||
+ use_mocked: bool = false
|
||||
+ sampling: std::optional<SamplingOptions>
|
||||
}
|
||||
|
||||
class LogEntry {
|
||||
+ timestamp : std::chrono::system_clock::time_point
|
||||
+ level : LogLevel
|
||||
+ phase : PipelinePhase
|
||||
+ message : std::string
|
||||
+ city : std::optional<std::string>
|
||||
+ entity_id : std::optional<std::string>
|
||||
+ worker : std::optional<std::string>
|
||||
class PipelineOptions {
|
||||
+ output_path: std::filesystem::path
|
||||
+ log_path: std::filesystem::path
|
||||
}
|
||||
|
||||
interface Logger <<interface>> {
|
||||
+ Log(level, phase, message,\n city, entity_id, worker) : void
|
||||
class ApplicationOptions {
|
||||
+ generator: GeneratorOptions
|
||||
+ pipeline: PipelineOptions
|
||||
}
|
||||
|
||||
class PipelineLogger {
|
||||
- log_ch_ : BoundedChannel<LogEntry>&
|
||||
+ Log(level, phase, message,\n city, entity_id, worker) : void
|
||||
}
|
||||
|
||||
class LogWorker {
|
||||
- log_ch_ : BoundedChannel<LogEntry>&
|
||||
+ Run() : void
|
||||
- FormatTimestamp(tp) : std::string
|
||||
- ToSpdlogLevel(level) : spdlog::level::level_enum
|
||||
- ToString(phase) : std::string
|
||||
}
|
||||
|
||||
' --- Logging Relationships ---
|
||||
LogEntry *-- LogLevel
|
||||
LogEntry *-- PipelinePhase
|
||||
PipelineLogger ..> LogEntry : emits
|
||||
LogWorker ..> LogEntry : consumes
|
||||
ApplicationOptions *-- GeneratorOptions
|
||||
ApplicationOptions *-- PipelineOptions
|
||||
GeneratorOptions o-- SamplingOptions
|
||||
}
|
||||
|
||||
|
||||
' ==========================================
|
||||
' DOMAIN POLICY
|
||||
' ==========================================
|
||||
package "Domain Policy" {
|
||||
package "Domain: Policy" {
|
||||
|
||||
interface ContextStrategy <<interface>> {
|
||||
+ QueriesFor(loc : const Location&) : std::vector<std::string>
|
||||
@@ -297,13 +224,99 @@ package "Domain Policy" {
|
||||
+ TimestampFor(user : const GeneratedUser&,\n index : size_t) : std::string
|
||||
}
|
||||
|
||||
class RandomCheckinStrategy {
|
||||
- rng_ : std::mt19937
|
||||
- min_checkins_ : size_t
|
||||
- max_checkins_ : size_t
|
||||
+ AssignActivityWeights(users : std::vector<GeneratedUser>&) : void
|
||||
+ CheckinsForUser(user : const GeneratedUser&,\n brewery_count : size_t) : size_t
|
||||
+ TimestampFor(user : const GeneratedUser&,\n index : size_t) : std::string
|
||||
}
|
||||
|
||||
interface FollowGenerationStrategy <<interface>> {
|
||||
+ GenerateFollows(users : const std::vector<GeneratedUser>&) : std::vector<GeneratedFollow>
|
||||
}
|
||||
|
||||
class RandomFollowStrategy {
|
||||
- rng_ : std::mt19937
|
||||
- min_follows_ : size_t
|
||||
- max_follows_ : size_t
|
||||
+ GenerateFollows(users : const std::vector<GeneratedUser>&) : std::vector<GeneratedFollow>
|
||||
}
|
||||
|
||||
class ActivityWeightedFollowStrategy {
|
||||
- rng_ : std::mt19937
|
||||
- min_follows_ : size_t
|
||||
- max_follows_ : size_t
|
||||
+ GenerateFollows(users : const std::vector<GeneratedUser>&) : std::vector<GeneratedFollow>
|
||||
}
|
||||
}
|
||||
|
||||
package "Infrastructure: Logging" {
|
||||
enum LogLevel {
|
||||
Debug
|
||||
Info
|
||||
Warn
|
||||
Error
|
||||
}
|
||||
|
||||
' ==========================================
|
||||
' ORCHESTRATION
|
||||
' ==========================================
|
||||
package "Orchestration" {
|
||||
enum PipelinePhase {
|
||||
Startup
|
||||
UserGeneration
|
||||
BreweryAndBeerGeneration
|
||||
CheckinGeneration
|
||||
RatingGeneration
|
||||
FollowGeneration
|
||||
Teardown
|
||||
}
|
||||
|
||||
class LogEntry {
|
||||
+ timestamp : std::chrono::system_clock::time_point
|
||||
+ level : LogLevel
|
||||
+ phase : PipelinePhase
|
||||
+ message : std::string
|
||||
+ worker : std::optional<std::string>
|
||||
}
|
||||
|
||||
interface ILogger <<interface>> {
|
||||
+ Log(entry : const LogEntry&) : void
|
||||
}
|
||||
|
||||
class LogProducer {
|
||||
- channel_ : BoundedChannel<LogEntry>&
|
||||
+ Log(entry : const LogEntry&) : void
|
||||
}
|
||||
|
||||
class LogDispatcher {
|
||||
- channel_ : BoundedChannel<LogEntry>&
|
||||
+ Run() : void
|
||||
- ToSpdlogLevel(level) : spdlog::level::level_enum
|
||||
}
|
||||
|
||||
LogEntry *-- LogLevel
|
||||
LogEntry *-- PipelinePhase
|
||||
ILogger <|.. LogProducer
|
||||
LogProducer ..> LogEntry : emits
|
||||
LogDispatcher ..> LogEntry : consumes
|
||||
}
|
||||
|
||||
package "Infrastructure: Pipeline Channel" {
|
||||
|
||||
class "BoundedChannel<T>" as BoundedChannel {
|
||||
- queue_ : std::queue<T>
|
||||
- mutex_ : std::mutex
|
||||
- not_full_ : std::condition_variable
|
||||
- not_empty_ : std::condition_variable
|
||||
- capacity_ : size_t
|
||||
- closed_ : bool
|
||||
+ Send(item : T) : void
|
||||
+ Receive() : std::optional<T>
|
||||
+ Close() : void
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
package "Infrastructure: Data Preloading" {
|
||||
|
||||
interface DataPreloader <<interface>> {
|
||||
+ LoadLocations(filepath : const std::filesystem::path&) : std::vector<Location>
|
||||
@@ -312,38 +325,6 @@ package "Orchestration" {
|
||||
+ LoadNamesByCountry(filepath : const std::filesystem::path&) : NamesByCountry
|
||||
}
|
||||
|
||||
class BiergartenPipelineOrchestrator {
|
||||
- preloader_ : std::unique_ptr<DataPreloader>
|
||||
- enrichment_service_ : std::unique_ptr<EnrichmentService>
|
||||
- generator_ : std::unique_ptr<DataGenerator>
|
||||
- logger_ : std::unique_ptr<Logger>
|
||||
- exporter_ : std::unique_ptr<ExportService>
|
||||
- brewery_context_strategy_ : std::unique_ptr<ContextStrategy>
|
||||
- sampling_strategy_ : std::unique_ptr<SamplingStrategy>
|
||||
- beer_selection_strategy_ : std::unique_ptr<BeerSelectionStrategy>
|
||||
- checkin_strategy_ : std::unique_ptr<CheckinDistributionStrategy>
|
||||
- beer_style_palette_ : std::vector<BeerStyle>
|
||||
- options_ : ApplicationOptions
|
||||
--
|
||||
- user_pool_ : std::vector<GeneratedUser>
|
||||
- brewery_pool_ : std::vector<GeneratedBrewery>
|
||||
- beer_pool_ : std::vector<GeneratedBeer>
|
||||
- checkin_pool_ : std::vector<GeneratedCheckin>
|
||||
--
|
||||
+ Run() : bool
|
||||
- RunUserPhase(locations : const std::vector<Location>&) : void
|
||||
- RunBreweryAndBeerPhase(locations : const std::vector<Location>&) : void
|
||||
- RunCheckinPhase() : void
|
||||
- RunRatingPhase() : void
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
' ==========================================
|
||||
' INFRASTRUCTURE: PRELOADING
|
||||
' ==========================================
|
||||
package "Infrastructure: Preloading" {
|
||||
|
||||
class JsonLoader {
|
||||
+ LoadLocations(filepath : const std::filesystem::path&) : std::vector<Location>
|
||||
+ LoadBeerStyles(filepath : const std::filesystem::path&) : std::vector<BeerStyle>
|
||||
@@ -353,10 +334,6 @@ package "Infrastructure: Preloading" {
|
||||
|
||||
}
|
||||
|
||||
|
||||
' ==========================================
|
||||
' INFRASTRUCTURE: ENRICHMENT
|
||||
' ==========================================
|
||||
package "Infrastructure: Enrichment" {
|
||||
|
||||
interface EnrichmentService <<interface>> {
|
||||
@@ -375,25 +352,37 @@ package "Infrastructure: Enrichment" {
|
||||
+ UrlEncode(value : const std::string&) : std::string
|
||||
}
|
||||
|
||||
class CURLWebClient {
|
||||
class HttpWebClient {
|
||||
+ Get(url : const std::string&) : std::string
|
||||
+ UrlEncode(value : const std::string&) : std::string
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
package "Infrastructure: Prompting" {
|
||||
|
||||
' ==========================================
|
||||
' INFRASTRUCTURE: GENERATION
|
||||
' ==========================================
|
||||
package "Infrastructure: Generation" {
|
||||
interface IPromptDirectory <<interface>> {
|
||||
+ Load(key : std::string_view) : std::string
|
||||
}
|
||||
|
||||
class PromptDirectory {
|
||||
- prompt_dir_ : std::filesystem::path
|
||||
- cache_ : std::unordered_map<std::string, std::string>
|
||||
+ PromptDirectory(prompt_dir : const std::filesystem::path&)
|
||||
+ Load(key : std::string_view) : std::string
|
||||
}
|
||||
|
||||
IPromptDirectory <|.. PromptDirectory
|
||||
}
|
||||
|
||||
package "Infrastructure: Data Generation" {
|
||||
|
||||
interface DataGenerator <<interface>> {
|
||||
+ GenerateBrewery(location : const Location&,\n context : const LocationContext&) : BreweryResult
|
||||
+ GenerateBeer(brewery_id : sqlite3_int64,\n location : const Location&,\n context : const LocationContext&,\n style : const BeerStyle&) : BeerResult
|
||||
+ GenerateBeer(brewery_id : uint64_t,\n location : const Location&,\n context : const LocationContext&,\n style : const BeerStyle&) : BeerResult
|
||||
+ GenerateUser(location : const Location&) : UserResult
|
||||
+ GenerateCheckin(user : const GeneratedUser&,\n brewery : const GeneratedBrewery&,\n timestamp : const std::string&) : CheckinResult
|
||||
+ GenerateRating(user : const GeneratedUser&,\n beer : const GeneratedBeer&,\n checkin_id : sqlite3_int64) : RatingResult
|
||||
+ GenerateRating(user : const GeneratedUser&,\n beer : const GeneratedBeer&,\n checkin_id : uint64_t) : RatingResult
|
||||
}
|
||||
|
||||
class MockGenerator {
|
||||
@@ -409,6 +398,7 @@ package "Infrastructure: Generation" {
|
||||
- model_ : ModelHandle
|
||||
- context_ : ContextHandle
|
||||
- prompt_formatter_ : std::unique_ptr<PromptFormatter>
|
||||
- prompt_directory_ : std::unique_ptr<IPromptDirectory>
|
||||
- rng_ : std::mt19937
|
||||
+ GenerateBrewery(...) : BreweryResult
|
||||
+ GenerateBeer(...) : BeerResult
|
||||
@@ -432,39 +422,16 @@ package "Infrastructure: Generation" {
|
||||
|
||||
}
|
||||
|
||||
|
||||
' ==========================================
|
||||
' INFRASTRUCTURE: PIPELINE CHANNEL
|
||||
' ==========================================
|
||||
package "Infrastructure: Pipeline Channel" {
|
||||
|
||||
class "BoundedChannel<T>" as BoundedChannel {
|
||||
- queue_ : std::queue<T>
|
||||
- mutex_ : std::mutex
|
||||
- not_full_ : std::condition_variable
|
||||
- not_empty_ : std::condition_variable
|
||||
- capacity_ : size_t
|
||||
- closed_ : bool
|
||||
+ Send(item : T) : void
|
||||
+ Receive() : std::optional<T>
|
||||
+ Close() : void
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
||||
' ==========================================
|
||||
' INFRASTRUCTURE: EXPORT
|
||||
' ==========================================
|
||||
package "Infrastructure: Export" {
|
||||
package "Infrastructure: Data Export" {
|
||||
|
||||
interface ExportService <<interface>> {
|
||||
+ Initialize() : void
|
||||
+ ProcessBrewery(brewery : const GeneratedBrewery&) : sqlite3_int64
|
||||
+ ProcessBeer(beer : const GeneratedBeer&) : sqlite3_int64
|
||||
+ ProcessUser(user : const GeneratedUser&) : sqlite3_int64
|
||||
+ ProcessCheckin(checkin : const GeneratedCheckin&) : sqlite3_int64
|
||||
+ ProcessBrewery(brewery : const GeneratedBrewery&) : uint64_t
|
||||
+ ProcessBeer(beer : const GeneratedBeer&) : uint64_t
|
||||
+ ProcessUser(user : const GeneratedUser&) : uint64_t
|
||||
+ ProcessCheckin(checkin : const GeneratedCheckin&) : uint64_t
|
||||
+ ProcessRating(rating : const GeneratedRating&) : void
|
||||
+ ProcessFollow(follow : const GeneratedFollow&) : void
|
||||
+ Finalize() : void
|
||||
}
|
||||
|
||||
@@ -477,15 +444,17 @@ package "Infrastructure: Export" {
|
||||
- insert_user_stmt_ : SqliteStatementHandle
|
||||
- insert_checkin_stmt_ : SqliteStatementHandle
|
||||
- insert_rating_stmt_ : SqliteStatementHandle
|
||||
- insert_follow_stmt_ : SqliteStatementHandle
|
||||
- transaction_open_ : bool
|
||||
- location_cache_ : std::unordered_map<std::string, sqlite3_int64>
|
||||
- brewery_cache_ : std::unordered_map<std::string, sqlite3_int64>
|
||||
- location_cache_ : std::unordered_map<std::string, uint64_t>
|
||||
- brewery_cache_ : std::unordered_map<std::string, uint64_t>
|
||||
+ Initialize() : void
|
||||
+ ProcessBrewery(brewery : const GeneratedBrewery&) : sqlite3_int64
|
||||
+ ProcessBeer(beer : const GeneratedBeer&) : sqlite3_int64
|
||||
+ ProcessUser(user : const GeneratedUser&) : sqlite3_int64
|
||||
+ ProcessCheckin(checkin : const GeneratedCheckin&) : sqlite3_int64
|
||||
+ ProcessRating(rating : const GeneratedRating&) : void
|
||||
+ ProcessRecord(brewery : const GeneratedBrewery&) : uint64_t
|
||||
+ ProcessRecord(beer : const GeneratedBeer&) : uint64_t
|
||||
+ ProcessRecord(user : const GeneratedUser&) : uint64_t
|
||||
+ ProcessRecord(checkin : const GeneratedCheckin&) : uint64_t
|
||||
+ ProcessRecord(rating : const GeneratedRating&) : void
|
||||
+ ProcessRecord(follow : const GeneratedFollow&) : void
|
||||
+ Finalize() : void
|
||||
- InitializeSchema() : void
|
||||
- PrepareStatements() : void
|
||||
@@ -503,10 +472,33 @@ package "Infrastructure: Export" {
|
||||
|
||||
}
|
||||
|
||||
|
||||
' ==========================================
|
||||
' GLOBAL RELATIONSHIPS
|
||||
' ==========================================
|
||||
class BiergartenPipelineOrchestrator {
|
||||
- preloader_ : std::unique_ptr<DataPreloader>
|
||||
- enrichment_service_ : std::unique_ptr<EnrichmentService>
|
||||
- generator_ : std::unique_ptr<DataGenerator>
|
||||
- logger_ : std::unique_ptr<Logger>
|
||||
- exporter_ : std::unique_ptr<ExportService>
|
||||
- brewery_context_strategy_ : std::unique_ptr<ContextStrategy>
|
||||
- sampling_strategy_ : std::unique_ptr<SamplingStrategy>
|
||||
- beer_selection_strategy_ : std::unique_ptr<BeerSelectionStrategy>
|
||||
- checkin_strategy_ : std::unique_ptr<CheckinDistributionStrategy>
|
||||
- follow_strategy_ : std::unique_ptr<FollowGenerationStrategy>
|
||||
- beer_style_palette_ : std::vector<BeerStyle>
|
||||
- options_ : ApplicationOptions
|
||||
--
|
||||
- user_pool_ : std::vector<GeneratedUser>
|
||||
- brewery_pool_ : std::vector<GeneratedBrewery>
|
||||
- beer_pool_ : std::vector<GeneratedBeer>
|
||||
- checkin_pool_ : std::vector<GeneratedCheckin>
|
||||
- follow_pool_ : std::vector<GeneratedFollow>
|
||||
--
|
||||
+ Run() : bool
|
||||
- RunUserPhase(locations : const std::vector<Location>&) : void
|
||||
- RunBreweryAndBeerPhase(locations : const std::vector<Location>&) : void
|
||||
- RunCheckinPhase() : void
|
||||
- RunRatingPhase() : void
|
||||
- RunFollowPhase() : void
|
||||
}
|
||||
|
||||
' --- Orchestration Aggregations (Services & Strategies) ---
|
||||
BiergartenPipelineOrchestrator *-- DataPreloader
|
||||
@@ -514,6 +506,7 @@ BiergartenPipelineOrchestrator *-- EnrichmentService
|
||||
BiergartenPipelineOrchestrator *-- DataGenerator
|
||||
BiergartenPipelineOrchestrator *-- ExportService
|
||||
BiergartenPipelineOrchestrator *-- CheckinDistributionStrategy
|
||||
BiergartenPipelineOrchestrator *-- FollowGenerationStrategy
|
||||
BiergartenPipelineOrchestrator *-- SamplingStrategy
|
||||
BiergartenPipelineOrchestrator *-- BeerSelectionStrategy
|
||||
BiergartenPipelineOrchestrator *-- ApplicationOptions
|
||||
@@ -524,6 +517,7 @@ BiergartenPipelineOrchestrator *-- "0..*" GeneratedUser : user_pool_
|
||||
BiergartenPipelineOrchestrator *-- "0..*" GeneratedBrewery : brewery_pool_
|
||||
BiergartenPipelineOrchestrator *-- "0..*" GeneratedBeer : beer_pool_
|
||||
BiergartenPipelineOrchestrator *-- "0..*" GeneratedCheckin : checkin_pool_
|
||||
BiergartenPipelineOrchestrator *-- "0..*" GeneratedFollow : follow_pool_
|
||||
|
||||
' --- Interfaces & Implementations ---
|
||||
DataPreloader <|.. JsonLoader
|
||||
@@ -533,8 +527,11 @@ ContextStrategy <|.. BeerContextStrategy
|
||||
SamplingStrategy <|.. UniformSamplingStrategy
|
||||
BeerSelectionStrategy <|.. RandomBeerSelectionStrategy
|
||||
CheckinDistributionStrategy <|.. JCurveCheckinStrategy
|
||||
CheckinDistributionStrategy <|.. RandomCheckinStrategy
|
||||
FollowGenerationStrategy <|.. RandomFollowStrategy
|
||||
FollowGenerationStrategy <|.. ActivityWeightedFollowStrategy
|
||||
EnrichmentService <|.. WikipediaService
|
||||
WebClient <|.. CURLWebClient
|
||||
WebClient <|.. HttpWebClient
|
||||
DataGenerator <|.. MockGenerator
|
||||
DataGenerator <|.. LlamaGenerator
|
||||
PromptFormatter <|.. Gemma4JinjaPromptFormatter
|
||||
@@ -545,6 +542,7 @@ DateTimeProvider <|.. SystemDateTimeProvider
|
||||
WikipediaService *-- WebClient
|
||||
WikipediaService ..> ContextStrategy
|
||||
LlamaGenerator *-- PromptFormatter
|
||||
LlamaGenerator *-- IPromptDirectory
|
||||
LlamaGenerator ..> GeneratorOptions
|
||||
SqliteExportService *-- DateTimeProvider
|
||||
|
||||
@@ -557,12 +555,18 @@ EnrichedCity *-- Location
|
||||
EnrichedCity *-- LocationContext
|
||||
GeneratedBrewery *-- Location
|
||||
GeneratedBrewery *-- BreweryResult
|
||||
GeneratedBrewery *-- GenerationMetadata
|
||||
GeneratedBeer *-- Location
|
||||
GeneratedBeer *-- BeerStyle
|
||||
GeneratedBeer *-- BeerResult
|
||||
GeneratedBeer *-- GenerationMetadata
|
||||
GeneratedUser *-- Location
|
||||
GeneratedUser *-- UserResult
|
||||
GeneratedUser *-- GenerationMetadata
|
||||
GeneratedCheckin *-- CheckinResult
|
||||
GeneratedCheckin *-- GenerationMetadata
|
||||
GeneratedRating *-- RatingResult
|
||||
GeneratedRating *-- GenerationMetadata
|
||||
GeneratedFollow *-- GenerationMetadata
|
||||
|
||||
@enduml
|
||||
File diff suppressed because one or more lines are too long
1
docs/pipeline/diagrams/planned/output/class.svg
Normal file
1
docs/pipeline/diagrams/planned/output/class.svg
Normal file
File diff suppressed because one or more lines are too long
@@ -1,7 +1,7 @@
|
||||
# Docker Guide
|
||||
|
||||
This document covers Docker deployment, configuration, and troubleshooting for The
|
||||
Biergarten App.
|
||||
This document covers Docker deployment, configuration, and troubleshooting for
|
||||
The Biergarten App.
|
||||
|
||||
## Overview
|
||||
|
||||
@@ -13,7 +13,8 @@ The project uses Docker Compose to orchestrate multiple services:
|
||||
- .NET API
|
||||
- Test runners
|
||||
|
||||
See the [deployment diagram](diagrams/pdf/deployment.pdf) for visual representation.
|
||||
See the [deployment diagram](diagrams/pdf/deployment.pdf) for visual
|
||||
representation.
|
||||
|
||||
## Docker Compose Environments
|
||||
|
||||
@@ -144,7 +145,11 @@ api.core / tests (start when ready)
|
||||
|
||||
```yaml
|
||||
healthcheck:
|
||||
test: ['CMD-SHELL', "sqlcmd -S localhost -U sa -P '${DB_PASSWORD}' -C -Q 'SELECT 1'"]
|
||||
test:
|
||||
[
|
||||
"CMD-SHELL",
|
||||
"sqlcmd -S localhost -U sa -P '${DB_PASSWORD}' -C -Q 'SELECT 1'",
|
||||
]
|
||||
interval: 10s
|
||||
timeout: 5s
|
||||
retries: 12
|
||||
@@ -209,16 +214,16 @@ Each environment uses isolated bridge networks:
|
||||
All containers are configured via environment variables from `.env` files:
|
||||
|
||||
```yaml
|
||||
env_file: '.env.dev' # or .env.test, .env.prod
|
||||
env_file: ".env.dev" # or .env.test, .env.prod
|
||||
|
||||
environment:
|
||||
ASPNETCORE_ENVIRONMENT: 'Development'
|
||||
DOTNET_RUNNING_IN_CONTAINER: 'true'
|
||||
DB_SERVER: '${DB_SERVER}'
|
||||
DB_NAME: '${DB_NAME}'
|
||||
DB_USER: '${DB_USER}'
|
||||
DB_PASSWORD: '${DB_PASSWORD}'
|
||||
JWT_SECRET: '${JWT_SECRET}'
|
||||
ASPNETCORE_ENVIRONMENT: "Development"
|
||||
DOTNET_RUNNING_IN_CONTAINER: "true"
|
||||
DB_SERVER: "${DB_SERVER}"
|
||||
DB_NAME: "${DB_NAME}"
|
||||
DB_USER: "${DB_USER}"
|
||||
DB_PASSWORD: "${DB_PASSWORD}"
|
||||
JWT_SECRET: "${JWT_SECRET}"
|
||||
```
|
||||
|
||||
For complete list, see [Environment Variables](environment-variables.md).
|
||||
@@ -1,7 +1,7 @@
|
||||
# Environment Variables
|
||||
|
||||
This document covers the active environment variables used by the current Biergarten
|
||||
stack.
|
||||
This document covers the active environment variables used by the current
|
||||
Biergarten stack.
|
||||
|
||||
## Overview
|
||||
|
||||
@@ -19,8 +19,8 @@ Direct environment variable access via `Environment.GetEnvironmentVariable()`.
|
||||
|
||||
### Frontend (`src/Website`)
|
||||
|
||||
The active website reads runtime values from the server environment for its auth and API
|
||||
integration.
|
||||
The active website reads runtime values from the server environment for its auth
|
||||
and API integration.
|
||||
|
||||
### Docker
|
||||
|
||||
@@ -54,14 +54,15 @@ Provide complete connection string:
|
||||
DB_CONNECTION_STRING="Server=localhost,1433;Database=Biergarten;User Id=sa;Password=YourStrong!Passw0rd;TrustServerCertificate=True;"
|
||||
```
|
||||
|
||||
**Priority**: `DB_CONNECTION_STRING` is checked first. If not found, connection string is
|
||||
built from components.
|
||||
**Priority**: `DB_CONNECTION_STRING` is checked first. If not found, connection
|
||||
string is built from components.
|
||||
|
||||
**Implementation**: See `DefaultSqlConnectionFactory.cs`
|
||||
|
||||
### JWT Authentication Secrets (Backend)
|
||||
|
||||
The backend uses separate secrets for different token types to enable independent key rotation and validation isolation.
|
||||
The backend uses separate secrets for different token types to enable
|
||||
independent key rotation and validation isolation.
|
||||
|
||||
```bash
|
||||
# Access token secret (1-hour tokens)
|
||||
@@ -131,8 +132,8 @@ DOTNET_RUNNING_IN_CONTAINER=true # Flag for container execution
|
||||
|
||||
## Frontend Variables (`src/Website`)
|
||||
|
||||
The active website does not use the old Next.js/Prisma environment model. Its core runtime
|
||||
variables are:
|
||||
The active website does not use the old Next.js/Prisma environment model. Its
|
||||
core runtime variables are:
|
||||
|
||||
```bash
|
||||
API_BASE_URL=http://localhost:8080 # Base URL for the .NET API
|
||||
@@ -208,9 +209,10 @@ cp .env.example .env.dev
|
||||
|
||||
## Legacy Frontend Variables
|
||||
|
||||
Variables for the archived Next.js frontend (`src/Website-v1`) have been removed from this
|
||||
active reference. See [archive/legacy-website-v1.md](archive/legacy-website-v1.md) if you
|
||||
need the legacy Prisma, Cloudinary, Mapbox, or SparkPost notes.
|
||||
Variables for the archived Next.js frontend (`src/Website-v1`) have been removed
|
||||
from this active reference. See
|
||||
[archive/legacy-website-v1.md](archive/legacy-website-v1.md) if you need the
|
||||
legacy Prisma, Cloudinary, Mapbox, or SparkPost notes.
|
||||
|
||||
**Docker Compose Mapping**:
|
||||
|
||||
@@ -243,8 +245,8 @@ need the legacy Prisma, Cloudinary, Mapbox, or SparkPost notes.
|
||||
| `MSSQL_PID` | | | ✓ | No | SQL Server edition |
|
||||
| `DOTNET_RUNNING_IN_CONTAINER` | ✓ | | ✓ | No | Container flag |
|
||||
|
||||
\* Either `DB_CONNECTION_STRING` OR the component variables (`DB_SERVER`, `DB_NAME`,
|
||||
`DB_USER`, `DB_PASSWORD`) must be provided.
|
||||
\* Either `DB_CONNECTION_STRING` OR the component variables (`DB_SERVER`,
|
||||
`DB_NAME`, `DB_USER`, `DB_PASSWORD`) must be provided.
|
||||
|
||||
## Validation
|
||||
|
||||
@@ -258,8 +260,8 @@ Variables are validated at startup:
|
||||
|
||||
### Frontend Validation
|
||||
|
||||
The active website relies on runtime defaults for local development and the surrounding
|
||||
server environment in deployed environments.
|
||||
The active website relies on runtime defaults for local development and the
|
||||
surrounding server environment in deployed environments.
|
||||
|
||||
- `API_BASE_URL` defaults to `http://localhost:8080`
|
||||
- `SESSION_SECRET` falls back to a development-only local secret
|
||||
@@ -1,7 +1,7 @@
|
||||
# Getting Started
|
||||
|
||||
This guide covers local setup for the current Biergarten stack: the .NET backend in
|
||||
`src/Core` and the active React Router frontend in `src/Website`.
|
||||
This guide covers local setup for the current Biergarten stack: the .NET backend
|
||||
in `src/Core` and the active React Router frontend in `src/Website`.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
@@ -128,8 +128,9 @@ dotnet run --project API/API.Core/API.Core.csproj
|
||||
|
||||
## Legacy Frontend Note
|
||||
|
||||
The previous Next.js frontend now lives in `src/Website-v1` and is not the active website.
|
||||
Legacy setup details have been moved to [docs/archive/legacy-website-v1.md](archive/legacy-website-v1.md).
|
||||
The previous Next.js frontend now lives in `src/Website-v1` and is not the
|
||||
active website. Legacy setup details have been moved to
|
||||
[docs/archive/legacy-website-v1.md](archive/legacy-website-v1.md).
|
||||
|
||||
## Next Steps
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
# Testing
|
||||
|
||||
This document describes the testing strategy and how to run tests for The Biergarten App.
|
||||
This document describes the testing strategy and how to run tests for The
|
||||
Biergarten App.
|
||||
|
||||
## Overview
|
||||
|
||||
@@ -9,13 +10,15 @@ The project uses a multi-layered testing approach across backend and frontend:
|
||||
- **API.Specs** - BDD integration tests using Reqnroll (Gherkin)
|
||||
- **Infrastructure.Repository.Tests** - Unit tests for data access layer
|
||||
- **Service.Auth.Tests** - Unit tests for authentication business logic
|
||||
- **Storybook Vitest project** - Browser-based interaction tests for shared website stories
|
||||
- **Storybook Playwright suite** - Browser checks against Storybook-rendered components
|
||||
- **Storybook Vitest project** - Browser-based interaction tests for shared
|
||||
website stories
|
||||
- **Storybook Playwright suite** - Browser checks against Storybook-rendered
|
||||
components
|
||||
|
||||
## Running Tests with Docker (Recommended)
|
||||
|
||||
The easiest way to run all tests is using Docker Compose, which sets up an isolated test
|
||||
environment:
|
||||
The easiest way to run all tests is using Docker Compose, which sets up an
|
||||
isolated test environment:
|
||||
|
||||
```bash
|
||||
docker compose -f docker-compose.test.yaml up --abort-on-container-exit
|
||||
@@ -98,7 +101,8 @@ npm run test:storybook
|
||||
|
||||
**Purpose**:
|
||||
|
||||
- Verifies shared stories such as form fields, submit buttons, navbar states, toasts, and the theme gallery
|
||||
- Verifies shared stories such as form fields, submit buttons, navbar states,
|
||||
toasts, and the theme gallery
|
||||
- Runs in browser mode via Vitest and Storybook integration
|
||||
|
||||
### Frontend Playwright Storybook Tests
|
||||
@@ -113,7 +117,8 @@ npm run test:storybook:playwright
|
||||
|
||||
- Storybook dependencies installed
|
||||
- Playwright browser dependencies installed
|
||||
- The command will start or reuse the Storybook server defined in `playwright.storybook.config.ts`
|
||||
- The command will start or reuse the Storybook server defined in
|
||||
`playwright.storybook.config.ts`
|
||||
|
||||
## Test Coverage
|
||||
|
||||
@@ -278,7 +283,8 @@ Scenario: User login with valid credentials
|
||||
|
||||
## Continuous Integration
|
||||
|
||||
Tests run automatically in CI/CD pipelines using the test Docker Compose configuration:
|
||||
Tests run automatically in CI/CD pipelines using the test Docker Compose
|
||||
configuration:
|
||||
|
||||
```bash
|
||||
# CI/CD command
|
||||
@@ -292,7 +298,8 @@ Exit codes:
|
||||
- `0` - All tests passed
|
||||
- Non-zero - Test failures occurred
|
||||
|
||||
Frontend UI checks should also be included in CI for the active website workspace:
|
||||
Frontend UI checks should also be included in CI for the active website
|
||||
workspace:
|
||||
|
||||
```bash
|
||||
cd src/Website
|
||||
@@ -2,11 +2,14 @@
|
||||
|
||||
## Overview
|
||||
|
||||
The Core project implements comprehensive JWT token validation across three token types:
|
||||
The Core project implements comprehensive JWT token validation across three
|
||||
token types:
|
||||
|
||||
- **Access Tokens**: Short-lived (1 hour) tokens for API authentication
|
||||
- **Refresh Tokens**: Long-lived (21 days) tokens for obtaining new access tokens
|
||||
- **Confirmation Tokens**: Short-lived (30 minutes) tokens for email confirmation
|
||||
- **Refresh Tokens**: Long-lived (21 days) tokens for obtaining new access
|
||||
tokens
|
||||
- **Confirmation Tokens**: Short-lived (30 minutes) tokens for email
|
||||
confirmation
|
||||
|
||||
## Components
|
||||
|
||||
@@ -17,10 +20,13 @@ The Core project implements comprehensive JWT token validation across three toke
|
||||
Low-level JWT operations.
|
||||
|
||||
**Methods:**
|
||||
|
||||
- `GenerateJwt()` - Creates signed JWT tokens
|
||||
- `ValidateJwtAsync()` - Validates token signature, expiration, and format
|
||||
|
||||
**Implementation:** [JwtInfrastructure.cs](Infrastructure.Jwt/JwtInfrastructure.cs)
|
||||
**Implementation:**
|
||||
[JwtInfrastructure.cs](Infrastructure.Jwt/JwtInfrastructure.cs)
|
||||
|
||||
- Uses Microsoft.IdentityModel.JsonWebTokens.JsonWebTokenHandler
|
||||
- Algorithm: HS256 (HMAC-SHA256)
|
||||
- Validates token lifetime, signature, and well-formedness
|
||||
@@ -32,16 +38,20 @@ Low-level JWT operations.
|
||||
High-level token validation with context (token type, user extraction).
|
||||
|
||||
**Methods:**
|
||||
|
||||
- `ValidateAccessTokenAsync(string token)` - Validates access tokens
|
||||
- `ValidateRefreshTokenAsync(string token)` - Validates refresh tokens
|
||||
- `ValidateConfirmationTokenAsync(string token)` - Validates confirmation tokens
|
||||
|
||||
**Returns:** `ValidatedToken` record containing:
|
||||
|
||||
- `UserId` (Guid)
|
||||
- `Username` (string)
|
||||
- `Principal` (ClaimsPrincipal) - Full JWT claims
|
||||
|
||||
**Implementation:** [TokenValidationService.cs](Service.Auth/TokenValidationService.cs)
|
||||
**Implementation:**
|
||||
[TokenValidationService.cs](Service.Auth/TokenValidationService.cs)
|
||||
|
||||
- Reads token secrets from environment variables
|
||||
- Extracts and validates claims (Sub, UniqueName)
|
||||
- Throws `UnauthorizedException` on validation failure
|
||||
@@ -51,15 +61,18 @@ High-level token validation with context (token type, user extraction).
|
||||
Token generation (existing service extended).
|
||||
|
||||
**Methods:**
|
||||
|
||||
- `GenerateAccessToken(UserAccount)` - Creates 1-hour access token
|
||||
- `GenerateRefreshToken(UserAccount)` - Creates 21-day refresh token
|
||||
- `GenerateConfirmationToken(UserAccount)` - Creates 30-minute confirmation token
|
||||
- `GenerateConfirmationToken(UserAccount)` - Creates 30-minute confirmation
|
||||
token
|
||||
|
||||
### Integration Points
|
||||
|
||||
#### [ConfirmationService](Service.Auth/IConfirmationService.cs)
|
||||
|
||||
**Flow:**
|
||||
|
||||
1. Receives confirmation token from user
|
||||
2. Calls `TokenValidationService.ValidateConfirmationTokenAsync()`
|
||||
3. Extracts user ID from validated token
|
||||
@@ -69,6 +82,7 @@ Token generation (existing service extended).
|
||||
#### [RefreshTokenService](Service.Auth/RefreshTokenService.cs)
|
||||
|
||||
**Flow:**
|
||||
|
||||
1. Receives refresh token from user
|
||||
2. Calls `TokenValidationService.ValidateRefreshTokenAsync()`
|
||||
3. Retrieves user account via `AuthRepository.GetUserByIdAsync()`
|
||||
@@ -78,6 +92,7 @@ Token generation (existing service extended).
|
||||
#### [AuthController](API.Core/Controllers/AuthController.cs)
|
||||
|
||||
**Endpoints:**
|
||||
|
||||
- `POST /api/auth/register` - Register new user
|
||||
- `POST /api/auth/login` - Authenticate user
|
||||
- `POST /api/auth/confirm?token=...` - Confirm email
|
||||
@@ -88,11 +103,13 @@ Token generation (existing service extended).
|
||||
### Token Secrets
|
||||
|
||||
Three independent secrets enable:
|
||||
|
||||
- **Key rotation** - Rotate each secret type independently
|
||||
- **Isolation** - Compromise of one secret doesn't affect others
|
||||
- **Different expiration** - Different token types can expire at different rates
|
||||
|
||||
**Environment Variables:**
|
||||
|
||||
```bash
|
||||
ACCESS_TOKEN_SECRET=... # Signs 1-hour access tokens
|
||||
REFRESH_TOKEN_SECRET=... # Signs 21-day refresh tokens
|
||||
@@ -111,6 +128,7 @@ Each token is validated for:
|
||||
### Error Handling
|
||||
|
||||
Validation failures return HTTP 401 Unauthorized:
|
||||
|
||||
- Invalid signature → "Invalid token"
|
||||
- Expired token → "Invalid token" (message doesn't reveal reason for security)
|
||||
- Missing claims → "Invalid token"
|
||||
@@ -149,16 +167,19 @@ Validation failures return HTTP 401 Unauthorized:
|
||||
### Unit Tests
|
||||
|
||||
**TokenValidationService.test.cs**
|
||||
|
||||
- Happy path: Valid token extraction
|
||||
- Error cases: Invalid, expired, malformed tokens
|
||||
- Missing/invalid claims scenarios
|
||||
|
||||
**RefreshTokenService.test.cs**
|
||||
|
||||
- Successful refresh with valid token
|
||||
- Invalid/expired refresh token rejection
|
||||
- Non-existent user handling
|
||||
|
||||
**ConfirmationService.test.cs**
|
||||
|
||||
- Successful confirmation with valid token
|
||||
- Token validation failures
|
||||
- User not found scenarios
|
||||
@@ -166,16 +187,19 @@ Validation failures return HTTP 401 Unauthorized:
|
||||
### BDD Tests (Reqnroll)
|
||||
|
||||
**TokenRefresh.feature**
|
||||
|
||||
- Successful token refresh
|
||||
- Invalid/expired token rejection
|
||||
- Missing token validation
|
||||
|
||||
**Confirmation.feature**
|
||||
|
||||
- Successful email confirmation
|
||||
- Expired/tampered token rejection
|
||||
- Missing token validation
|
||||
|
||||
**AccessTokenValidation.feature**
|
||||
|
||||
- Protected endpoint access token validation
|
||||
- Invalid/expired access token rejection
|
||||
- Token type mismatch (refresh used as access token)
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,559 +0,0 @@
|
||||
,name,city,state
|
||||
0,NorthGate Brewing ,Minneapolis, MN
|
||||
1,Against the Grain Brewery,Louisville, KY
|
||||
2,Jack's Abby Craft Lagers,Framingham, MA
|
||||
3,Mike Hess Brewing Company,San Diego, CA
|
||||
4,Fort Point Beer Company,San Francisco, CA
|
||||
5,COAST Brewing Company,Charleston, SC
|
||||
6,Great Divide Brewing Company,Denver, CO
|
||||
7,Tapistry Brewing,Bridgman, MI
|
||||
8,Big Lake Brewing,Holland, MI
|
||||
9,The Mitten Brewing Company,Grand Rapids, MI
|
||||
10,Brewery Vivant,Grand Rapids, MI
|
||||
11,Petoskey Brewing,Petoskey, MI
|
||||
12,Blackrocks Brewery,Marquette, MI
|
||||
13,Perrin Brewing Company,Comstock Park, MI
|
||||
14,Witch's Hat Brewing Company,South Lyon, MI
|
||||
15,Founders Brewing Company,Grand Rapids, MI
|
||||
16,Flat 12 Bierwerks,Indianapolis, IN
|
||||
17,Tin Man Brewing Company,Evansville, IN
|
||||
18,Black Acre Brewing Co.,Indianapolis, IN
|
||||
19,Brew Link Brewing,Plainfield, IN
|
||||
20,Bare Hands Brewery,Granger, IN
|
||||
21,Three Pints Brewing,Martinsville, IN
|
||||
22,Four Fathers Brewing ,Valparaiso, IN
|
||||
23,Indiana City Brewing,Indianapolis, IN
|
||||
24,Burn 'Em Brewing,Michigan City, IN
|
||||
25,Sun King Brewing Company,Indianapolis, IN
|
||||
26,Evil Czech Brewery,Mishawaka, IN
|
||||
27,450 North Brewing Company,Columbus, IN
|
||||
28,Taxman Brewing Company,Bargersville, IN
|
||||
29,Cedar Creek Brewery,Seven Points, TX
|
||||
30,SanTan Brewing Company,Chandler, AZ
|
||||
31,Boulevard Brewing Company,Kansas City, MO
|
||||
32,James Page Brewing Company,Stevens Point, WI
|
||||
33,The Dudes' Brewing Company,Torrance, CA
|
||||
34,Ballast Point Brewing Company,San Diego, CA
|
||||
35,Anchor Brewing Company,San Francisco, CA
|
||||
36,Figueroa Mountain Brewing Company,Buellton, CA
|
||||
37,Avery Brewing Company,Boulder, CO
|
||||
38,Twisted X Brewing Company,Dripping Springs, TX
|
||||
39,Gonzo's BiggDogg Brewing,Kalamazoo, MI
|
||||
40,Big Muddy Brewing,Murphysboro, IL
|
||||
41,Lost Nation Brewing,East Fairfield, VT
|
||||
42,Rising Tide Brewing Company,Portland, ME
|
||||
43,Rivertowne Brewing Company,Export, PA
|
||||
44,Revolution Brewing Company,Chicago, IL
|
||||
45,Tallgrass Brewing Company,Manhattan, KS
|
||||
46,Sixpoint Craft Ales,Brooklyn, NY
|
||||
47,White Birch Brewing,Hooksett, NH
|
||||
48,Firestone Walker Brewing Company,Paso Robles, CA
|
||||
49,SweetWater Brewing Company,Atlanta, GA
|
||||
50,Flying Mouse Brewery,Troutville, VA
|
||||
51,Upslope Brewing Company,Boulder, CO
|
||||
52,Pipeworks Brewing Company,Chicago, IL
|
||||
53,Bent Brewstillery,Roseville, MN
|
||||
54,Flesk Brewing Company,Lombard, IL
|
||||
55,Pollyanna Brewing Company,Lemont, IL
|
||||
56,BuckleDown Brewing,Lyons, IL
|
||||
57,Destihl Brewery,Bloomington, IL
|
||||
58,Summit Brewing Company,St. Paul, MN
|
||||
59,Latitude 42 Brewing Company,Portage, MI
|
||||
60,4 Hands Brewing Company,Saint Louis, MO
|
||||
61,Surly Brewing Company,Brooklyn Center, MN
|
||||
62,Against The Grain Brewery,Louisville, KY
|
||||
63,Crazy Mountain Brewing Company,Edwards, CO
|
||||
64,SlapShot Brewing Company,Chicago, IL
|
||||
65,Mikerphone Brewing,Chicago, IL
|
||||
66,Freetail Brewing Company,San Antonio, TX
|
||||
67,3 Daughters Brewing,St Petersburg, FL
|
||||
68,Red Shedman Farm Brewery and Hop...,Mt. Airy, MD
|
||||
69,Appalachian Mountain Brewery,Boone, NC
|
||||
70,Birdsong Brewing Company,Charlotte, NC
|
||||
71,Union Craft Brewing,Baltimore, MD
|
||||
72,Atwater Brewery,Detroit, MI
|
||||
73,Ale Asylum,Madison, WI
|
||||
74,Two Brothers Brewing Company,Warrenville, IL
|
||||
75,Bent Paddle Brewing Company,Duluth, MN
|
||||
76,Bell's Brewery,Kalamazoo, MI
|
||||
77,Blue Owl Brewing,Austin, TX
|
||||
78,Speakasy Ales & Lagers,San Francisco, CA
|
||||
79,Black Tooth Brewing Company,Sheridan, WY
|
||||
80,Hopworks Urban Brewery,Portland, OR
|
||||
81,Epic Brewing,Denver, CO
|
||||
82,New Belgium Brewing Company,Fort Collins, CO
|
||||
83,Sierra Nevada Brewing Company,Chico, CA
|
||||
84,Keweenaw Brewing Company,Houghton, MI
|
||||
85,Brewery Terra Firma,Traverse City, MI
|
||||
86,Grey Sail Brewing Company,Westerly, RI
|
||||
87,Kirkwood Station Brewing Company,Kirkwood, MO
|
||||
88,Goose Island Brewing Company,Chicago, IL
|
||||
89,Broad Brook Brewing LLC,East Windsor, CT
|
||||
90,The Lion Brewery,Wilkes-Barre, PA
|
||||
91,Madtree Brewing Company,Cincinnati, OH
|
||||
92,Jackie O's Pub & Brewery,Athens, OH
|
||||
93,Rhinegeist Brewery,Cincinnati, OH
|
||||
94,Warped Wing Brewing Company,Dayton, OH
|
||||
95,Blackrocks Brewery,Marquette, MA
|
||||
96,Catawba Valley Brewing Company,Morganton, NC
|
||||
97,Tröegs Brewing Company,Hershey, PA
|
||||
98,Mission Brewery,San Diego, CA
|
||||
99,Christian Moerlein Brewing Company,Cincinnati, OH
|
||||
100,West Sixth Brewing,Lexington, KY
|
||||
101,Coastal Extreme Brewing Company,Newport, RI
|
||||
102,King Street Brewing Company,Anchorage, AK
|
||||
103,Beer Works Brewery,Lowell, MA
|
||||
104,Lone Tree Brewing Company,Lone Tree, CO
|
||||
105,Four String Brewing Company,Columbus, OH
|
||||
106,Glabrous Brewing Company,Pineland, ME
|
||||
107,Bonfire Brewing Company,Eagle, CO
|
||||
108,Thomas Hooker Brewing Company,Bloomfield, CT
|
||||
109,"Woodstock Inn, Station & Brewery",North Woodstock, NH
|
||||
110,Renegade Brewing Company,Denver, CO
|
||||
111,Mother Earth Brew Company,Vista, CA
|
||||
112,Black Market Brewing Company,Temecula, CA
|
||||
113,Vault Brewing Company,Yardley, PA
|
||||
114,Jailbreak Brewing Company,Laurel, MD
|
||||
115,Smartmouth Brewing Company,Norfolk, VA
|
||||
116,Base Camp Brewing Co.,Portland, OR
|
||||
117,Alameda Brewing,Portland, OR
|
||||
118,Southern Star Brewing Company,Conroe, TX
|
||||
119,Steamworks Brewing Company,Durango, CO
|
||||
120,Horny Goat Brew Pub,Milwaukee, WI
|
||||
121,Cheboygan Brewing Company,Cheboygan, MI
|
||||
122,Center of the Universe Brewing C...,Ashland, VA
|
||||
123,Ipswich Ale Brewery,Ipswich, MA
|
||||
124,Griffin Claw Brewing Company,Birmingham, MI
|
||||
125,Karbach Brewing Company,Houston, TX
|
||||
126,Uncle Billy's Brewery and Smokeh...,Austin, TX
|
||||
127,Deep Ellum Brewing Company,Dallas, TX
|
||||
128,Real Ale Brewing Company,Blanco, TX
|
||||
129,Straub Brewery,St Mary's, PA
|
||||
130,Shebeen Brewing Company,Wolcott, CT
|
||||
131,Stevens Point Brewery,Stevens Point, WI
|
||||
132,Weston Brewing Company,Weston, MO
|
||||
133,Southern Prohibition Brewing Com...,Hattiesburg, MS
|
||||
134,Minhas Craft Brewery,Monroe, WI
|
||||
135,Pug Ryan's Brewery,Dillon, CO
|
||||
136,Hops & Grains Brewing Company,Austin, TX
|
||||
137,Sietsema Orchards and Cider Mill,Ada, MI
|
||||
138,Summit Brewing Company,St Paul, MN
|
||||
139,Core Brewing & Distilling Company,Springdale, AR
|
||||
140,Independence Brewing Company,Austin, TX
|
||||
141,Cigar City Brewing Company,Tampa, FL
|
||||
142,Third Street Brewhouse,Cold Spring, MN
|
||||
143,Narragansett Brewing Company,Providence, RI
|
||||
144,Grimm Brothers Brewhouse,Loveland, CO
|
||||
145,Cisco Brewers,Nantucket, MA
|
||||
146,Angry Minnow,Hayward, WI
|
||||
147,Platform Beer Company,Cleveland, OH
|
||||
148,Odyssey Beerwerks,Arvada, CO
|
||||
149,Lonerider Brewing Company,Raleigh, NC
|
||||
150,Oakshire Brewing,Eugene, OR
|
||||
151,Fort Pitt Brewing Company,Latrobe, PA
|
||||
152,Tin Roof Brewing Company,Baton Rouge, LA
|
||||
153,Three Creeks Brewing,Sisters, OR
|
||||
154,2 Towns Ciderhouse,Corvallis, OR
|
||||
155,Caldera Brewing Company,Ashland, OR
|
||||
156,Greenbrier Valley Brewing Company,Lewisburg, WV
|
||||
157,Phoenix Ale Brewery,Phoenix, AZ
|
||||
158,Lumberyard Brewing Company,Flagstaff, AZ
|
||||
159,Uinta Brewing Company,Salt Lake City, UT
|
||||
160,Four Peaks Brewing Company,Tempe, AZ
|
||||
161,Martin House Brewing Company,Fort Worth, TX
|
||||
162,Right Brain Brewery,Traverse City, MI
|
||||
163,Sly Fox Brewing Company,Phoenixville, PA
|
||||
164,Round Guys Brewing,Lansdale, PA
|
||||
165,Great Crescent Brewery,Aurora, IN
|
||||
166,Oskar Blues Brewery,Longmont, CO
|
||||
167,Boxcar Brewing Company,West Chester, PA
|
||||
168,High Hops Brewery,Windsor, CO
|
||||
169,Crooked Fence Brewing Company,Garden City, ID
|
||||
170,Everybody's Brewing,White Salmon, WA
|
||||
171,Anderson Valley Brewing Company,Boonville, CA
|
||||
172,Fiddlehead Brewing Company,Shelburne, VT
|
||||
173,Evil Twin Brewing,Brooklyn, NY
|
||||
174,New Orleans Lager & Ale Brewing ...,New Orleans, LA
|
||||
175,Spiteful Brewing Company,Chicago, IL
|
||||
176,Rahr & Sons Brewing Company,Fort Worth, TX
|
||||
177,18th Street Brewery,Gary, IN
|
||||
178,Cambridge Brewing Company,Cambridge, MA
|
||||
179,Carolina Brewery,Pittsboro, NC
|
||||
180,Frog Level Brewing Company,Waynesville, NC
|
||||
181,Wild Wolf Brewing Company,Nellysford, VA
|
||||
182,COOP Ale Works,Oklahoma City, OK
|
||||
183,Seventh Son Brewing Company,Columbus, OH
|
||||
184,Oasis Texas Brewing Company,Austin, TX
|
||||
185,Vander Mill Ciders,Spring Lake, MI
|
||||
186,St. Julian Winery,Paw Paw, MI
|
||||
187,Pedernales Brewing Company,Fredericksburg, TX
|
||||
188,Mother's Brewing,Springfield, MO
|
||||
189,Modern Monks Brewery,Lincoln, NE
|
||||
190,Two Beers Brewing Company,Seattle, WA
|
||||
191,Snake River Brewing Company,Jackson, WY
|
||||
192,Capital Brewery,Middleton, WI
|
||||
193,Anthem Brewing Company,Oklahoma City, OK
|
||||
194,Goodlife Brewing Co.,Bend, OR
|
||||
195,Breakside Brewery,Portland, OR
|
||||
196,Goose Island Brewery Company,Chicago, IL
|
||||
197,Burnside Brewing Co.,Portland, OR
|
||||
198,Hop Valley Brewing Company,Springfield, OR
|
||||
199,Worthy Brewing Company,Bend, OR
|
||||
200,Occidental Brewing Company,Portland, OR
|
||||
201,Fearless Brewing Company,Estacada, OR
|
||||
202,Upland Brewing Company,Bloomington, IN
|
||||
203,Mehana Brewing Co.,Hilo, HI
|
||||
204,Hawai'i Nui Brewing Co.,Hilo, HI
|
||||
205,People's Brewing Company,Lafayette, IN
|
||||
206,Fort George Brewery,Astoria, OR
|
||||
207,Branchline Brewing Company,San Antonio, TX
|
||||
208,Kalona Brewing Company,Kalona, IA
|
||||
209,Modern Times Beer,San Diego, CA
|
||||
210,Temperance Beer Company,Evanston, IL
|
||||
211,Wisconsin Brewing Company,Verona, WI
|
||||
212,Crow Peak Brewing Company,Spearfish, SD
|
||||
213,Grapevine Craft Brewery,Farmers Branch, TX
|
||||
214,Buffalo Bayou Brewing Company,Houston, TX
|
||||
215,Texian Brewing Co.,Richmond, TX
|
||||
216,Orpheus Brewing,Atlanta, GA
|
||||
217,Forgotten Boardwalk,Cherry Hill, NJ
|
||||
218,Laughing Dog Brewing Company,Ponderay, ID
|
||||
219,Bozeman Brewing Company,Bozeman, MT
|
||||
220,Big Choice Brewing,Broomfield, CO
|
||||
221,Big Storm Brewing Company,Odessa, FL
|
||||
222,Carton Brewing Company,Atlantic Highlands, NJ
|
||||
223,Midnight Sun Brewing Company,Anchorage, AK
|
||||
224,Fat Head's Brewery,Middleburg Heights, OH
|
||||
225,Refuge Brewery,Temecula, CA
|
||||
226,Chatham Brewing,Chatham, NY
|
||||
227,DC Brau Brewing Company,Washington, DC
|
||||
228,Geneva Lake Brewing Company,Lake Geneva, WI
|
||||
229,Rochester Mills Brewing Company,Rochester, MI
|
||||
230,Cape Ann Brewing Company,Gloucester, MA
|
||||
231,Borderlands Brewing Company,Tucson, AZ
|
||||
232,College Street Brewhouse and Pub,Lake Havasu City, AZ
|
||||
233,Joseph James Brewing Company,Henderson, NV
|
||||
234,Harpoon Brewery,Boston, MA
|
||||
235,Back East Brewing Company,Bloomfield, CT
|
||||
236,Champion Brewing Company,Charlottesville, VA
|
||||
237,Devil's Backbone Brewing Company,Lexington, VA
|
||||
238,Newburgh Brewing Company,Newburgh, NY
|
||||
239,Wiseacre Brewing Company,Memphis, TN
|
||||
240,Golden Road Brewing,Los Angeles, CA
|
||||
241,New Republic Brewing Company,College Station, TX
|
||||
242,Infamous Brewing Company,Austin, TX
|
||||
243,Two Henrys Brewing Company,Plant City, FL
|
||||
244,Lift Bridge Brewing Company,Stillwater, MN
|
||||
245,Lucky Town Brewing Company,Jackson, MS
|
||||
246,Quest Brewing Company,Greenville, SC
|
||||
247,Creature Comforts,Athens, GA
|
||||
248,Half Full Brewery,Stamford, CT
|
||||
249,Southampton Publick House,Southampton, NY
|
||||
250,Chapman's Brewing,Angola, IN
|
||||
251,Barrio Brewing Company,Tucson, AZ
|
||||
252,Santa Cruz Mountain Brewing,Santa Cruz, CA
|
||||
253,Frankenmuth Brewery,Frankenmuth, MI
|
||||
254,Meckley's Cidery,Somerset Center, MI
|
||||
255,Stillwater Artisanal Ales,Baltimore, MD
|
||||
256,Finch's Beer Company,Chicago, IL
|
||||
257,South Austin Brewery,South Austin, TX
|
||||
258,Bauhaus Brew Labs,Minneapolis, MN
|
||||
259,Ozark Beer Company,Rogers, AR
|
||||
260,Mountain Town Brewing Company ,Mount Pleasant, MI
|
||||
261,Otter Creek Brewing,Waterbury, VT
|
||||
262,The Brewer's Art,Baltimore, MD
|
||||
263,Denver Beer Company,Denver, CO
|
||||
264,Ska Brewing Company,Durango, CO
|
||||
265,Tractor Brewing Company,Albuquerque, NM
|
||||
266,Peak Organic Brewing Company,Portland, ME
|
||||
267,Cape Cod Beer,Hyannis, MA
|
||||
268,Long Trail Brewing Company,Bridgewater Corners, VT
|
||||
269,Great Raft Brewing Company,Shreveport, LA
|
||||
270,Alaskan Brewing Company,Juneau, AK
|
||||
271,Notch Brewing Company,Ipswich, MA
|
||||
272,The Alchemist,Waterbury, VT
|
||||
273,Three Notch'd Brewing Company,Charlottesville, VA
|
||||
274,Portside Brewery,Cleveland, OH
|
||||
275,Otter Creek Brewing,Middlebury, VT
|
||||
276,Montauk Brewing Company,Montauk, NY
|
||||
277,Indeed Brewing Company,Minneapolis, MN
|
||||
278,Berkshire Brewing Company,South Deerfield, MA
|
||||
279,Foolproof Brewing Company,Pawtucket, RI
|
||||
280,Headlands Brewing Company,Mill Valley, CA
|
||||
281,Bolero Snort Brewery,Ridgefield Park, NJ
|
||||
282,Thunderhead Brewing Company,Kearney, NE
|
||||
283,Defiance Brewing Company,Hays, KS
|
||||
284,Milwaukee Brewing Company,Milwaukee, WI
|
||||
285,Catawba Island Brewing,Port Clinton, OH
|
||||
286,Back Forty Beer Company,Gadsden, AL
|
||||
287,Four Corners Brewing Company,Dallas, TX
|
||||
288,Saint Archer Brewery,San Diego, CA
|
||||
289,Rogue Ales,Newport, OR
|
||||
290,Hale's Ales,Seattle, WA
|
||||
291,Tommyknocker Brewery,Idaho Springs, CO
|
||||
292,Baxter Brewing Company,Lewiston, ME
|
||||
293,Northampton Brewery,Northamtpon, MA
|
||||
294,Black Shirt Brewing Company,Denver, CO
|
||||
295,Wachusett Brewing Company,Westminster, MA
|
||||
296,Widmer Brothers Brewing Company,Portland, OR
|
||||
297,Hop Farm Brewing Company,Pittsburgh, PA
|
||||
298,Liquid Hero Brewery,York, PA
|
||||
299,Matt Brewing Company,Utica, NY
|
||||
300,Boston Beer Company,Boston, MA
|
||||
301,Old Forge Brewing Company,Danville, PA
|
||||
302,Utah Brewers Cooperative,Salt Lake City, UT
|
||||
303,Magic Hat Brewing Company,South Burlington, VT
|
||||
304,Blue Hills Brewery,Canton, MA
|
||||
305,Night Shift Brewing,Everett, MA
|
||||
306,Beach Brewing Company,Virginia Beach, VA
|
||||
307,Payette Brewing Company,Garden City, ID
|
||||
308,Brew Bus Brewing,Tampa, FL
|
||||
309,Sockeye Brewing Company,Boise, ID
|
||||
310,Pine Street Brewery,San Francisco, CA
|
||||
311,Dirty Bucket Brewing Company,Woodinville, WA
|
||||
312,Jackalope Brewing Company,Nashville, TN
|
||||
313,Slanted Rock Brewing Company,Meridian, ID
|
||||
314,Piney River Brewing Company,Bucryus, MO
|
||||
315,Cutters Brewing Company,Avon, IN
|
||||
316,Iron Hill Brewery & Restaurant,Wilmington, DE
|
||||
317,Marshall Wharf Brewing Company,Belfast, ME
|
||||
318,Banner Beer Company,Williamsburg, MA
|
||||
319,Dick's Brewing Company,Centralia, WA
|
||||
320,Claremont Craft Ales,Claremont, CA
|
||||
321,Rivertown Brewing Company,Lockland, OH
|
||||
322,Voodoo Brewery,Meadville, PA
|
||||
323,D.L. Geary Brewing Company,Portland, ME
|
||||
324,Pisgah Brewing Company,Black Mountain, NC
|
||||
325,Neshaminy Creek Brewing Company,Croydon, PA
|
||||
326,Morgan Street Brewery,Saint Louis, MO
|
||||
327,Half Acre Beer Company,Chicago, IL
|
||||
328,The Just Beer Project,Burlington, VT
|
||||
329,The Bronx Brewery,Bronx, NY
|
||||
330,Dead Armadillo Craft Brewing,Tulsa, OK
|
||||
331,Catawba Brewing Company,Morganton, NC
|
||||
332,La Cumbre Brewing Company,Albuquerque, NM
|
||||
333,David's Ale Works,Diamond Springs, CA
|
||||
334,The Traveler Beer Company,Burlington, VT
|
||||
335,Fargo Brewing Company,Fargo, ND
|
||||
336,Big Sky Brewing Company,Missoula, MT
|
||||
337,Nebraska Brewing Company,Papillion, NE
|
||||
338,Uncle John's Fruit House Winery,St. John's, MI
|
||||
339,Wormtown Brewery,Worcester, MA
|
||||
340,Due South Brewing Company,Boynton Beach, FL
|
||||
341,Palisade Brewing Company,Palisade, CO
|
||||
342,KelSo Beer Company,Brooklyn, NY
|
||||
343,Hardywood Park Craft Brewery,Richmond, VA
|
||||
344,Wolf Hills Brewing Company,Abingdon, VA
|
||||
345,Lavery Brewing Company,Erie, PA
|
||||
346,Manzanita Brewing Company,Santee, CA
|
||||
347,Fullsteam Brewery,Durham, NC
|
||||
348,Four Horsemen Brewing Company,South Bend, IN
|
||||
349,Hinterland Brewery,Green Bay, WI
|
||||
350,Central Coast Brewing Company,San Luis Obispo, CA
|
||||
351,Westfield River Brewing Company,Westfield, MA
|
||||
352,Elevator Brewing Company,Columbus, OH
|
||||
353,Aslan Brewing Company,Bellingham, WA
|
||||
354,Kulshan Brewery,Bellingham, WA
|
||||
355,Pikes Peak Brewing Company,Monument, CO
|
||||
356,Manayunk Brewing Company,Philadelphia, PA
|
||||
357,Buckeye Brewing,Cleveland, OH
|
||||
358,Daredevil Brewing Company,Shelbyville, IN
|
||||
359,NoDa Brewing Company,Charlotte, NC
|
||||
360,Aviator Brewing Company,Fuquay-Varina, NC
|
||||
361,Wild Onion Brewing Company,Lake Barrington, IL
|
||||
362,Hilliard's Beer,Seattle, WA
|
||||
363,Mikkeller,Pottstown, PA
|
||||
364,Bohemian Brewery,Midvale, UT
|
||||
365,Great River Brewery,Davenport, IA
|
||||
366,Mustang Brewing Company,Mustang, OK
|
||||
367,Airways Brewing Company,Kent, WA
|
||||
368,21st Amendment Brewery,San Francisco, CA
|
||||
369,Eddyline Brewery & Restaurant,Buena Vista, CO
|
||||
370,Pizza Port Brewing Company,Carlsbad, CA
|
||||
371,Sly Fox Brewing Company,Pottstown, PA
|
||||
372,Spring House Brewing Company,Conestoga, PA
|
||||
373,7venth Sun,Dunedin, FL
|
||||
374,Astoria Brewing Company,Astoria, OR
|
||||
375,Maui Brewing Company,Lahaina, HI
|
||||
376,RoughTail Brewing Company,Midwest City, OK
|
||||
377,Lucette Brewing Company,Menominee, WI
|
||||
378,Bold City Brewery,Jacksonville, FL
|
||||
379,Grey Sail Brewing of Rhode Island,Westerly, RI
|
||||
380,Blue Blood Brewing Company,Lincoln, NE
|
||||
381,Swashbuckler Brewing Company,Manheim, PA
|
||||
382,Blue Mountain Brewery,Afton, VA
|
||||
383,Starr Hill Brewery,Crozet, VA
|
||||
384,Westbrook Brewing Company,Mt. Pleasant, SC
|
||||
385,Shipyard Brewing Company,Portland, ME
|
||||
386,Revolution Brewing,Paonia, CO
|
||||
387,Natian Brewery,Portland, OR
|
||||
388,Alltech's Lexington Brewing Company,Lexington, KY
|
||||
389,Oskar Blues Brewery (North Carol...,Brevard, NC
|
||||
390,Orlison Brewing Company,Airway Heights, WA
|
||||
391,Breckenridge Brewery,Denver, CO
|
||||
392,Santa Fe Brewing Company,Santa Fe, NM
|
||||
393,Miami Brewing Company,Miami, FL
|
||||
394,Schilling & Company,Seattle, WA
|
||||
395,Hops & Grain Brewery,Austin, TX
|
||||
396,White Flame Brewing Company,Hudsonville, MI
|
||||
397,Ruhstaller Beer Company,Sacramento, CA
|
||||
398,Saugatuck Brewing Company,Douglas, MI
|
||||
399,Moab Brewery,Moab, UT
|
||||
400,Macon Beer Company,Macon, GA
|
||||
401,Amnesia Brewing Company,Washougal, WA
|
||||
402,Wolverine State Brewing Company,Ann Arbor, MI
|
||||
403,Red Tank Cider Company,Bend, OR
|
||||
404,Cascadia Ciderworks United,Portland, OR
|
||||
405,Fate Brewing Company,Boulder, CO
|
||||
406,Lazy Monk Brewing,Eau Claire, WI
|
||||
407,Bitter Root Brewing,Hamilton, MT
|
||||
408,10 Barrel Brewing Company,Bend, OR
|
||||
409,Tamarack Brewing Company,Lakeside, MT
|
||||
410,New England Brewing Company,Woodbridge, CT
|
||||
411,Seattle Cider Company,Seattle, WA
|
||||
412,Straight to Ale,Huntsville, AL
|
||||
413,Austin Beerworks,Austin, TX
|
||||
414,Blue Mountain Brewery,Arrington, VA
|
||||
415,Coastal Empire Beer Company,Savannah, GA
|
||||
416,Jack's Hard Cider (Hauser Estate...,Biglerville, PA
|
||||
417,Boulder Beer Company,Boulder, CO
|
||||
418,Coalition Brewing Company,Portland, OR
|
||||
419,Sanitas Brewing Company,Boulder, CO
|
||||
420,Gore Range Brewery,Edwards, CO
|
||||
421,Redstone Meadery,Boulder, CO
|
||||
422,Blue Dog Mead,Eugene, OR
|
||||
423,Hess Brewing Company,San Diego, CA
|
||||
424,Wynkoop Brewing Company,Denver, CO
|
||||
425,Ciderboys,Stevens Point, WI
|
||||
426,Armadillo Ale Works,Denton, TX
|
||||
427,Roanoke Railhouse Brewery,Roanoke, VA
|
||||
428,Schlafly Brewing Company,Saint Louis, MO
|
||||
429,Asher Brewing Company,Boulder, CO
|
||||
430,Lost Rhino Brewing Company,Ashburn, VA
|
||||
431,North Country Brewing Company,Slippery Rock, PA
|
||||
432,Seabright Brewery,Santa Cruz, CA
|
||||
433,French Broad Brewery,Asheville, NC
|
||||
434,Angry Orchard Cider Company,Cincinnati, OH
|
||||
435,Two Roads Brewing Company,Stratford, CT
|
||||
436,Southern Oregon Brewing Company,Medford, OR
|
||||
437,Brooklyn Brewery,Brooklyn, NY
|
||||
438,The Right Brain Brewery,Traverse City, MI
|
||||
439,Kona Brewing Company,Kona, HI
|
||||
440,MillKing It Productions,Royal Oak, MI
|
||||
441,Pateros Creek Brewing Company,Fort Collins, CO
|
||||
442,O'Fallon Brewery,O'Fallon, MO
|
||||
443,Marble Brewery,Albuquerque, NM
|
||||
444,Big Wood Brewery,Vadnais Heights, MN
|
||||
445,Howard Brewing Company,Lenoir, NC
|
||||
446,Downeast Cider House,Leominster, MA
|
||||
447,Swamp Head Brewery,Gainesville, FL
|
||||
448,Mavericks Beer Company,Half Moon Bay, CA
|
||||
449,TailGate Beer,San Diego, CA
|
||||
450,Northwest Brewing Company,Pacific, WA
|
||||
451,Dad & Dude's Breweria,Aurora, CO
|
||||
452,Centennial Beer Company,Edwards, CO
|
||||
453,Denali Brewing Company,Talkeetna, AK
|
||||
454,Deschutes Brewery,Bend, OR
|
||||
455,Sunken City Brewing Company,Hardy, VA
|
||||
456,Lucette Brewing Company,Menominie, WI
|
||||
457,The Black Tooth Brewing Company,Sheridan, WY
|
||||
458,Kenai River Brewing Company,Soldotna, AK
|
||||
459,River North Brewery,Denver, CO
|
||||
460,Fremont Brewing Company,Seattle, WA
|
||||
461,Armstrong Brewing Company,South San Francisco, CA
|
||||
462,AC Golden Brewing Company,Golden, CO
|
||||
463,Big Bend Brewing Company,Alpine, TX
|
||||
464,Good Life Brewing Company,Bend, OR
|
||||
465,Engine 15 Brewing,Jacksonville Beach, FL
|
||||
466,Green Room Brewing,Jacksonville, FL
|
||||
467,Brindle Dog Brewing Company,Tampa Bay, FL
|
||||
468,Peace Tree Brewing Company,Knoxville, IA
|
||||
469,Terrapin Brewing Company,Athens, GA
|
||||
470,Pete's Brewing Company,San Antonio, TX
|
||||
471,Okoboji Brewing Company,Spirit Lake, IA
|
||||
472,Crystal Springs Brewing Company,Boulder, CO
|
||||
473,Engine House 9,Tacoma, WA
|
||||
474,Tonka Beer Company,Minnetonka, MN
|
||||
475,Red Hare Brewing Company,Marietta, GA
|
||||
476,Hangar 24 Craft Brewery,Redlands, CA
|
||||
477,Big Elm Brewing,Sheffield, MA
|
||||
478,Good People Brewing Company,Birmingham, AL
|
||||
479,Heavy Seas Beer,Halethorpe, MD
|
||||
480,Telluride Brewing Company,Telluride, CO
|
||||
481,7 Seas Brewing Company,Gig Harbor, WA
|
||||
482,Confluence Brewing Company,Des Moines, IA
|
||||
483,Bale Breaker Brewing Company,Yakima, WA
|
||||
484,The Manhattan Brewing Company,New York, NY
|
||||
485,MacTarnahans Brewing Company,Portland, OR
|
||||
486,Stillmank Beer Company,Green Bay, WI
|
||||
487,Redhook Brewery,Woodinville, WA
|
||||
488,Dock Street Brewery,Philadelphia, PA
|
||||
489,Blue Point Brewing Company,Patchogue, NY
|
||||
490,Tampa Bay Brewing Company,Tampa, FL
|
||||
491,Devil's Canyon Brewery,Belmont, CA
|
||||
492,Stone Coast Brewing Company,Portland, ME
|
||||
493,Broken Tooth Brewing Company,Anchorage, AK
|
||||
494,Seven Brides Brewery,Silverton, OR
|
||||
495,Newburyport Brewing Company,Newburyport, MA
|
||||
496,Dry Dock Brewing Company,Aurora, CO
|
||||
497,Cans Bar and Canteen,Charlotte, NC
|
||||
498,Sprecher Brewing Company,Glendale, WI
|
||||
499,Wildwood Brewing Company,Stevensville, MT
|
||||
500,High Noon Saloon And Brewery,Leavenworth, KS
|
||||
501,Woodchuck Hard Cider,Middlebury, VT
|
||||
502,Sea Dog Brewing Company,Portland, ME
|
||||
503,Oskar Blues Brewery,Lyons, CO
|
||||
504,Carolina Beer & Beverage,Mooresville, NC
|
||||
505,Krebs Brewing Company (Pete's Pl...,Krebs, OK
|
||||
506,Warbird Brewing Company,Fort Wayne, IN
|
||||
507,Mudshark Brewing Company,Lake Havasu City, AZ
|
||||
508,Spilker Ales,Cortland, NE
|
||||
509,Wingman Brewers,Tacoma, WA
|
||||
510,Kettle House Brewing Company,Missoula, MT
|
||||
511,Sherwood Forest Brewers,Marlborough, MA
|
||||
512,Cottrell Brewing,Pawcatuck, CT
|
||||
513,Arctic Craft Brewery,Colorado Springs, CO
|
||||
514,Monkey Paw Pub & Brewery,San Diego, CA
|
||||
515,Crabtree Brewing Company,Greeley, CO
|
||||
516,Emerald City Beer Company,Seattle, WA
|
||||
517,Butcher's Brewing,Carlsbad, CA
|
||||
518,New South Brewing Company,Myrtle Beach, SC
|
||||
519,Big River Brewing Company,Chattanooga, TN
|
||||
520,Twisted Pine Brewing Company,Boulder, CO
|
||||
521,Flying Dog Brewery,Frederick, MD
|
||||
522,Uncommon Brewers,Santa Cruz, CA
|
||||
523,Aspen Brewing Company,Aspen, CO
|
||||
524,Triangle Brewing Company,Durham, NC
|
||||
525,Bomb Beer Company,New York, NY
|
||||
526,Churchkey Can Company,Seattle, WA
|
||||
527,Intuition Ale Works,Jacksonville, FL
|
||||
528,Asheville Brewing Company,Asheville, NC
|
||||
529,Northwoods Brewpub,Eau Claire, WI
|
||||
530,Buckbean Brewing Company,Reno, NV
|
||||
531,Dolores River Brewery,Dolores, CO
|
||||
532,Flat Rock Brewing Company,Smithton, PA
|
||||
533,Abita Brewing Company,Abita Springs, LA
|
||||
534,Mammoth Brewing Company,Mammoth Lakes, CA
|
||||
535,Harvest Moon Brewing Company,Belt, MT
|
||||
536,Grand Canyon Brewing Company,Williams, AZ
|
||||
537,Lewis and Clark Brewing Company,Helena, MT
|
||||
538,Dundee Brewing Company,Rochester, NY
|
||||
539,Twin Lakes Brewing Company,Greenville, DE
|
||||
540,Mother Earth Brewing Company,Kinston, NC
|
||||
541,Arcadia Brewing Company,Battle Creek, MI
|
||||
542,Angry Minnow Brewing Company,Hayward, WI
|
||||
543,Great Northern Brewing Company,Whitefish, MT
|
||||
544,Pyramid Breweries,Seattle, WA
|
||||
545,Lancaster Brewing Company,Lancaster, PA
|
||||
546,Upstate Brewing Company,Elmira, NY
|
||||
547,Moat Mountain Smoke House & Brew...,North Conway, NH
|
||||
548,Prescott Brewing Company,Prescott, AZ
|
||||
549,Mogollon Brewing Company,Flagstaff, AZ
|
||||
550,Wind River Brewing Company,Pinedale, WY
|
||||
551,Silverton Brewery,Silverton, CO
|
||||
552,Mickey Finn's Brewery,Libertyville, IL
|
||||
553,Covington Brewhouse,Covington, LA
|
||||
554,Dave's Brewfarm,Wilson, WI
|
||||
555,Ukiah Brewing Company,Ukiah, CA
|
||||
556,Butternuts Beer and Ale,Garrattsville, NY
|
||||
557,Sleeping Lady Brewing Company,Anchorage, AK
|
||||
|
162686
misc/raw-data/breweries.json
162686
misc/raw-data/breweries.json
File diff suppressed because it is too large
Load Diff
@@ -1,578 +0,0 @@
|
||||
[
|
||||
{
|
||||
"text": "100 Acre Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/100-acre-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "All My Friends Beer Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/all-my-friends-beer-co/"
|
||||
},
|
||||
{
|
||||
"text": "All or Nothing Brewhouse",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/all-or-nothing-brewhouse/"
|
||||
},
|
||||
{
|
||||
"text": "Anderson Craft Ales",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/anderson-craft-ales/"
|
||||
},
|
||||
{
|
||||
"text": "Badlands Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/badlands-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Bancroft Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/bancroft-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Banded Goose Brewing Comany",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/banded-goose-brewing-comany/"
|
||||
},
|
||||
{
|
||||
"text": "Beau’s Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/beaus-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "BeerLab! London",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/beerlab-london/"
|
||||
},
|
||||
{
|
||||
"text": "Bellwoods Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/bellwoods-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Bench Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/bench-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Beyond The Pale Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/beyond-the-pale-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Bicycle Craft Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/bicycle-craft-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Big Rig Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/big-rig-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Big Rock Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/big-rock-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Black Gold Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/black-gold-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Black Oak Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/black-oak-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Block 3 Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/block-3-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Blood Brothers Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/blood-brothers-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Bobcaygeon Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/bobcaygeon-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Boshkung Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/boshkung-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Brauwerk Hoffman – Rockland",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/brauwerk-hoffman-rockland/"
|
||||
},
|
||||
{
|
||||
"text": "Bridge Masters Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/bridge-masters-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Broadhead Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/broadhead-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Broken Rail Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/broken-rail-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Burdock Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/burdock-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "C’est What Durham Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/cest-what-durham-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Calabogie Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/calabogie-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Cameron’s Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/camerons-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Canvas Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/canvas-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Caps Off Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/caps-off-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Century Barn Brewing & Beverage Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/century-barn-brewing-and-beverage-company/"
|
||||
},
|
||||
{
|
||||
"text": "Chronicle Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/chronicle-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Clifford Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/clifford-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Cold Bear Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/cold-bear-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Collective Arts Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/collective-arts-brewing-ltd/"
|
||||
},
|
||||
{
|
||||
"text": "Common Good Beer Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/common-good-beer-co/"
|
||||
},
|
||||
{
|
||||
"text": "Couchiching Craft Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/couchiching-craft-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Cowbell Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/cowbell-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Cured Craft Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/cured-craft-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Daft Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/daft-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Dog House Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/dog-house-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Dominion City Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/dominion-city-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Eastbound Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/eastbound-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Equals Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/equals-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Fairweather Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/fairweather-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Farm League Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/farm-league-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Fixed Gear Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/fixed-gear-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Flying Monkeys Craft Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/flying-monkeys-craft-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Focal Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/focal-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Foundry Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/foundry-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Four Fathers Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/four-fathers-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Frank Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/frank-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Freddy’s",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/freddys/"
|
||||
},
|
||||
{
|
||||
"text": "Full Beard Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/1068-2/"
|
||||
},
|
||||
{
|
||||
"text": "Furnace Room Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/furnace-room-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Gateway City Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/gateway-city-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Glasstown Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/glasstown-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Godspeed Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/godspeed-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Goldenfield Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/goldenfield-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Grand River Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/grand-river-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Granite Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/granite-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Great Lakes Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/great-lakes-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Haliburton Highlands Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/haliburton-highlands-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Imperial City Brew House",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/imperial-city-brew-house/"
|
||||
},
|
||||
{
|
||||
"text": "Indie Ale House",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/indie-ale-house/"
|
||||
},
|
||||
{
|
||||
"text": "Jobsite Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/jobsite-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Kichesippi Beer Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/kichesippi-beer-co/"
|
||||
},
|
||||
{
|
||||
"text": "Kick and Push Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/kick-and-push-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Lake of Bays Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/lake-of-bays-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Lake Of The Woods Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/lake-of-the-woods-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Left Field Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/left-field-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Lightcaster Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/lightcaster-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "MacKinnon Brothers Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/mackinnon-brothers-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Maclean’s Ales Inc.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/macleans-ales-inc/"
|
||||
},
|
||||
{
|
||||
"text": "Magnotta Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/magnotta-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Market Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/market-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Mascot Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/mascot-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Matron Fine Beer",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/matron-fine-beer/"
|
||||
},
|
||||
{
|
||||
"text": "Meyers Creek Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/meyers-creek-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Midtown Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/midtown-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Miski Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/miski-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Muddy York Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/muddy-york-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Muskoka Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/muskoka-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Natterjack Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/natterjack-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Newark Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/newark-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Niagara Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/niagara-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Niagara College Teaching Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/niagara-college-teaching-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Niagara Oast House Brewers",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/niagara-oast-house-brewers/"
|
||||
},
|
||||
{
|
||||
"text": "Nickel Brook Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/nickel-brook-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Northern Superior Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/northern-superior-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Old Credit Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/old-credit-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Old Flame Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/1239-2/"
|
||||
},
|
||||
{
|
||||
"text": "Orléans Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/orleans-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Overflow Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/overflow-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Parsons Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/parsons-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Perth Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/perth-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Prince Eddy’s Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/prince-eddys-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Quayle’s Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/quayles-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Quetico Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/quetico-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Railway City Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/railway-city-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Ramblin’ Road Brewery Farm",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/ramblin-road-brewery-farm/"
|
||||
},
|
||||
{
|
||||
"text": "Red Barn Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/red-barn-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Refined Fool Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/refined-fool-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Rouge River Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/rouge-river-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Royal City Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/royal-city-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Sassy Britches Brewing Co Ltd",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/sassy-britches-brewing-co-ltd/"
|
||||
},
|
||||
{
|
||||
"text": "Sawdust City Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/sawdust-city-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Shawn & Ed Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/shawn-ed-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Silversmith Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/silversmith-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Slake Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/slake-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Sleeping Giant Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/sleeping-giant-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Something in the Water Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/something-in-the-water-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Sonnen Hill Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/sonnen-hill-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Sons of Kent Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/sons-of-kent-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Spark Beer",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/spark-beer/"
|
||||
},
|
||||
{
|
||||
"text": "Split Rail Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/split-rail-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Stack Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/stack-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Steam Whistle Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/steam-whistle-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Steel Wheel Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/steel-wheel-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Stonehooker Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/stonehooker-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Stonepicker Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/stonepicker-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Stray Dog Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/stray-dog-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "The Exchange Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/the-exchange-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "The Grove Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/the-grove-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "The Second Wedge Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/the-second-wedge-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Thornbury Village Craft Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/thornbury-village-craft-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Three Sheets Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/three-sheets-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Tooth and Nail Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/tooth-and-nail-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Torched Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/torched-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Town Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/town-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Trestle Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/trestle-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "True History Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/true-history-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Upper Thames Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/upper-thames-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Vimy Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/vimy-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Walkerville Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/walkerville-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Wave Maker Craft Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/wave-maker-craft-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Wellington Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/wellington-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Whiprsnapr Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/whiprsnapr-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Whiskeyjack Beer Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/whiskeyjack-beer-company/"
|
||||
},
|
||||
{
|
||||
"text": "Whitewater Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/whitewater-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Willibald Farm Distillery & Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/willibald-farm-distillery-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Windmill Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/windmill-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Wishbone Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/wishbone-brewing/"
|
||||
}
|
||||
]
|
||||
@@ -1,181 +0,0 @@
|
||||
cmake_minimum_required(VERSION 3.24)
|
||||
project(biergarten-pipeline)
|
||||
|
||||
set(CMAKE_POLICY_VERSION_MINIMUM 3.5 CACHE STRING "" FORCE)
|
||||
|
||||
# =============================================================================
|
||||
# 1. Platform & GPU Detection
|
||||
# =============================================================================
|
||||
if(WIN32)
|
||||
message(FATAL_ERROR "[biergarten] Windows is currently not supported. Please use Linux (Fedora 43) or macOS (M1 Pro).")
|
||||
endif()
|
||||
|
||||
if(APPLE)
|
||||
if(CMAKE_SYSTEM_PROCESSOR MATCHES "arm64")
|
||||
message(STATUS "[biergarten] Apple Silicon detected — enabling Metal acceleration.")
|
||||
set(GGML_METAL ON CACHE BOOL "Enable Metal for Apple Silicon" FORCE)
|
||||
else()
|
||||
message(STATUS "[biergarten] Intel Mac detected — using CPU / Accelerate framework.")
|
||||
set(GGML_METAL OFF CACHE BOOL "Disable Metal for Intel Macs" FORCE)
|
||||
endif()
|
||||
elseif(UNIX AND NOT APPLE)
|
||||
find_package(CUDAToolkit QUIET)
|
||||
find_package(HIP QUIET)
|
||||
|
||||
if(CUDAToolkit_FOUND)
|
||||
message(STATUS "[biergarten] NVIDIA GPU detected — enabling CUDA acceleration.")
|
||||
set(GGML_CUDA ON CACHE BOOL "Enable CUDA for NVIDIA GPUs" FORCE)
|
||||
set(CMAKE_CUDA_ARCHITECTURES native)
|
||||
elseif(HIP_FOUND OR EXISTS "/opt/rocm")
|
||||
message(STATUS "[biergarten] AMD GPU detected — enabling HIP/ROCm acceleration.")
|
||||
set(GGML_HIPBLAS ON CACHE BOOL "Enable HIP for AMD GPUs" FORCE)
|
||||
else()
|
||||
message(STATUS "[biergarten] No NVIDIA or AMD GPU found — falling back to CPU.")
|
||||
endif()
|
||||
endif()
|
||||
|
||||
# =============================================================================
|
||||
# 2. Project-wide Settings (Standard & Optimization)
|
||||
# =============================================================================
|
||||
|
||||
set(CMAKE_CXX_STANDARD 20)
|
||||
set(CMAKE_CXX_STANDARD_REQUIRED ON)
|
||||
set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
|
||||
|
||||
# Release Build Optimization: Aggressive (-O3), Arch-specific, and LTO
|
||||
set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -O3 -march=native -flto")
|
||||
|
||||
set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -Og -g")
|
||||
|
||||
# =============================================================================
|
||||
# 3. Dependencies
|
||||
# =============================================================================
|
||||
include(FetchContent)
|
||||
|
||||
find_package(CURL QUIET)
|
||||
if(NOT CURL_FOUND)
|
||||
message(FATAL_ERROR "[biergarten] libcurl not found. Install it (e.g. 'sudo dnf install libcurl-devel').")
|
||||
endif()
|
||||
|
||||
# Require system Boost for JSON and Program Options to speed up build times
|
||||
find_package(Boost REQUIRED COMPONENTS json program_options)
|
||||
|
||||
FetchContent_Declare(
|
||||
sqlite_amalgamation
|
||||
URL https://www.sqlite.org/2026/sqlite-amalgamation-3530000.zip
|
||||
URL_HASH SHA3_256=c2325c53b3b41761469f91cfb078e96882ac5d85bac10c11b0bd8f253b031e5b
|
||||
)
|
||||
FetchContent_GetProperties(sqlite_amalgamation)
|
||||
if(NOT sqlite_amalgamation_POPULATED)
|
||||
FetchContent_Populate(sqlite_amalgamation)
|
||||
endif()
|
||||
|
||||
if(NOT TARGET sqlite3)
|
||||
add_library(sqlite3 STATIC
|
||||
${sqlite_amalgamation_SOURCE_DIR}/sqlite3.c
|
||||
)
|
||||
target_include_directories(sqlite3 PUBLIC
|
||||
${sqlite_amalgamation_SOURCE_DIR}
|
||||
)
|
||||
target_compile_definitions(sqlite3 PUBLIC
|
||||
SQLITE_THREADSAFE=1
|
||||
)
|
||||
endif()
|
||||
|
||||
FetchContent_Declare(
|
||||
llama-cpp
|
||||
GIT_REPOSITORY https://github.com/ggml-org/llama.cpp.git
|
||||
GIT_TAG b8742
|
||||
)
|
||||
FetchContent_MakeAvailable(llama-cpp)
|
||||
|
||||
FetchContent_Declare(
|
||||
boost-di
|
||||
GIT_REPOSITORY https://github.com/boost-ext/di.git
|
||||
GIT_TAG v1.3.0
|
||||
)
|
||||
FetchContent_MakeAvailable(boost-di)
|
||||
if(TARGET Boost.DI AND NOT TARGET boost::di)
|
||||
add_library(boost::di ALIAS Boost.DI)
|
||||
endif()
|
||||
|
||||
FetchContent_Declare(
|
||||
spdlog
|
||||
GIT_REPOSITORY https://github.com/gabime/spdlog.git
|
||||
GIT_TAG v1.15.3
|
||||
)
|
||||
FetchContent_MakeAvailable(spdlog)
|
||||
|
||||
# =============================================================================
|
||||
# 4. Sources
|
||||
# =============================================================================
|
||||
set(SOURCES
|
||||
src/main.cc
|
||||
src/biergarten_data_generator/biergarten_data_generator.cc
|
||||
src/biergarten_data_generator/run.cc
|
||||
src/biergarten_data_generator/query_cities_with_countries.cc
|
||||
src/biergarten_data_generator/generate_breweries.cc
|
||||
src/biergarten_data_generator/log_results.cc
|
||||
src/services/wikipedia/wikipedia_service.cc
|
||||
src/services/wikipedia/get_summary.cc
|
||||
src/services/wikipedia/fetch_extract.cc
|
||||
src/services/sqlite/sqlite_export_service.cc
|
||||
src/services/sqlite/build_database_path.cc
|
||||
src/services/sqlite/build_location_key.cc
|
||||
src/services/sqlite/initialize_schema.cc
|
||||
src/services/sqlite/prepare_statements.cc
|
||||
src/services/sqlite/initialize.cc
|
||||
src/services/sqlite/process_record.cc
|
||||
src/services/sqlite/finalize_statements.cc
|
||||
src/services/sqlite/rollback_and_close_no_throw.cc
|
||||
src/services/sqlite/finalize.cc
|
||||
src/web_client/curl_global_state.cc
|
||||
src/web_client/curl_web_client_get.cc
|
||||
src/web_client/curl_web_client_url_encode.cc
|
||||
src/data_generation/llama/llama_generator.cc
|
||||
src/data_generation/llama/generate_brewery.cc
|
||||
src/data_generation/llama/generate_user.cc
|
||||
src/data_generation/llama/helpers.cc
|
||||
src/data_generation/llama/infer.cc
|
||||
src/data_generation/llama/load.cc
|
||||
src/data_generation/llama/load_brewery_prompt.cc
|
||||
src/data_generation/prompt_formatting/gemma4_jinja_prompt_formatter.cc
|
||||
src/data_generation/mock/deterministic_hash.cc
|
||||
src/data_generation/mock/generate_brewery.cc
|
||||
src/data_generation/mock/generate_user.cc
|
||||
src/json_handling/json_loader.cc
|
||||
)
|
||||
|
||||
# =============================================================================
|
||||
# 5. Target
|
||||
# =============================================================================
|
||||
add_executable(${PROJECT_NAME} ${SOURCES})
|
||||
target_include_directories(${PROJECT_NAME} PRIVATE
|
||||
includes
|
||||
${llama-cpp_SOURCE_DIR}/include
|
||||
${llama-cpp_SOURCE_DIR}/common
|
||||
)
|
||||
target_link_libraries(${PROJECT_NAME} PRIVATE
|
||||
llama
|
||||
boost::di
|
||||
Boost::json
|
||||
Boost::program_options
|
||||
spdlog::spdlog
|
||||
sqlite3
|
||||
CURL::libcurl
|
||||
)
|
||||
|
||||
# =============================================================================
|
||||
# 6. Runtime Assets
|
||||
# =============================================================================
|
||||
configure_file(
|
||||
${CMAKE_SOURCE_DIR}/locations.json
|
||||
${CMAKE_BINARY_DIR}/locations.json
|
||||
COPYONLY
|
||||
)
|
||||
|
||||
add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD
|
||||
COMMAND ${CMAKE_COMMAND} -E copy_directory
|
||||
${CMAKE_SOURCE_DIR}/prompts
|
||||
${CMAKE_BINARY_DIR}/prompts
|
||||
)
|
||||
@@ -1,344 +0,0 @@
|
||||
# Biergarten Pipeline
|
||||
|
||||
A C++20 command-line pipeline that samples city records from local JSON, enriches each with Wikipedia context, and generates bilingual brewery names and descriptions via a local GGUF model or a deterministic mock.
|
||||
|
||||
---
|
||||
|
||||
## Table of Contents
|
||||
|
||||
- [How It Fits The Main App](#how-it-fits-the-main-app)
|
||||
- [Tech Stack](#tech-stack)
|
||||
- [Build](#build)
|
||||
- [Model](#model)
|
||||
- [Run](#run)
|
||||
- [Architecture](#architecture)
|
||||
- [Pipeline Stages](#pipeline-stages)
|
||||
- [Key Components](#key-components)
|
||||
- [Runtime Behaviour](#runtime-behaviour)
|
||||
- [Generated Output](#generated-output)
|
||||
- [Language Generation Quality](#language-generation-quality)
|
||||
- [Known Issues](#known-issues)
|
||||
- [Tested Hardware](#tested-hardware)
|
||||
- [Repo Layout](#repo-layout)
|
||||
- [Code Tour](#code-tour)
|
||||
- [Fixture Strategy](#fixture-strategy)
|
||||
- [Next Steps](#next-steps)
|
||||
|
||||
---
|
||||
|
||||
## How It Fits The Main App
|
||||
|
||||
The pipeline is a data ingestion layer. It sits outside the web app runtime and produces seed records the app imports at startup or during a dedicated seed step.
|
||||
|
||||
| Planned app area | Pipeline contribution |
|
||||
| -------------------------------- | ------------------------------------------------------------------ |
|
||||
| Brewery discovery and management | Sampled city records, localized names, long-form descriptions |
|
||||
| Beer reviews and ratings | Stable brewery fixtures with enough context to anchor review pages |
|
||||
| Social follow relationships | Repeatable brewery entities for feeds, follows, and saved lists |
|
||||
| Geospatial brewery experiences | Latitude, longitude, and country-level metadata |
|
||||
|
||||
---
|
||||
|
||||
## Tech Stack
|
||||
|
||||
- C++20
|
||||
- CMake 3.24+
|
||||
- Boost.JSON, Boost.ProgramOptions, Boost.DI
|
||||
- spdlog
|
||||
- libcurl
|
||||
- SQLite amalgamation fetched and compiled via CMake FetchContent
|
||||
- llama.cpp
|
||||
|
||||
The build fetches Boost.DI, spdlog, llama.cpp, and SQLite via CMake. Metal is enabled on Apple Silicon; CUDA or HIP/ROCm is detected on Linux when the toolkit is present.
|
||||
|
||||
> **Code Style:** Modern C++20 throughout - RAII for ownership, `std::unique_ptr` for injected dependencies, `std::optional` for parse outcomes, `std::span` for read-only views over generated city data, structured bindings in pipeline loops. Formatting follows the Google C++ Style Guide via `.clang-format` with a narrow column limit and two-space indentation.
|
||||
|
||||
---
|
||||
|
||||
## Build
|
||||
|
||||
Requirements: C++20 compiler, CMake 3.24+, libcurl, Boost (JSON and ProgramOptions).
|
||||
SQLite is fetched from the upstream amalgamation, so no system SQLite package is required.
|
||||
|
||||
```bash
|
||||
cmake -S . -B build
|
||||
cmake --build build
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Model
|
||||
|
||||
> Skip this step if you only need `--mocked`.
|
||||
|
||||
```bash
|
||||
mkdir -p models
|
||||
curl -L \
|
||||
-o models/google_gemma-4-E4B-it-Q6_K.gguf \
|
||||
https://huggingface.co/bartowski/google_gemma-4-E4B-it-GGUF/resolve/main/google_gemma-4-E4B-it-Q6_K.gguf?download=true
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Run
|
||||
|
||||
Run from `build/` so the copied `locations.json` and `prompts/` are available. Each run also writes a fresh dated SQLite file such as `biergarten_seed_2026-04-19T15-30-45.123456Z.sqlite` into the working directory.
|
||||
|
||||
```bash
|
||||
./biergarten-pipeline --mocked
|
||||
./biergarten-pipeline --model models/google_gemma-4-E4B-it-Q6_K.gguf --temperature 1.0 --top-p 0.95 --top-k 64 --n-ctx 8192 --seed -1
|
||||
```
|
||||
|
||||
### CLI Flags
|
||||
|
||||
| Flag | Purpose |
|
||||
| --------------- | ------------------------------------------------------- |
|
||||
| `--mocked` | Deterministic mock generator, no model required. |
|
||||
| `--model, -m` | Path to a GGUF file. Required unless `--mocked` is set. |
|
||||
| `--temperature` | Sampling temperature. Default: `1.0`. |
|
||||
| `--top-p` | Nucleus sampling. Default: `0.95`. |
|
||||
| `--top-k` | Top-k sampling. Default: `64`. |
|
||||
| `--n-ctx` | Context window size. Default: `8192`. |
|
||||
| `--seed` | Random seed. Default: `-1` (random at runtime). |
|
||||
| `--help, -h` | Print usage and exit. |
|
||||
|
||||
`--mocked` and `--model` are mutually exclusive. Omitting both exits with an error before the pipeline starts. Sampling flags are ignored when `--mocked` is set.
|
||||
|
||||
The post-build step copies `prompts/` into `build/prompts/`. Rebuild after editing `prompts/system.md`.
|
||||
|
||||
---
|
||||
|
||||
## Architecture
|
||||
|
||||
### Pipeline Stages
|
||||
|
||||
| Stage | Implementation |
|
||||
| -------- | --------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| Load | `JsonLoader::LoadLocations()` reads `locations.json` into typed `Location` records. |
|
||||
| Sample | `BiergartenDataGenerator::QueryCitiesWithCountries()` samples up to 50 locations per run. |
|
||||
| Enrich | `WikipediaService` fetches city and beer context. Keeps going when a lookup fails. |
|
||||
| Generate | `MockGenerator` or `LlamaGenerator` produces brewery names and descriptions in English and the local language. |
|
||||
| Store | `SqliteExportService` writes each successful brewery into a fresh dated `.sqlite` database with normalized location and brewery tables. |
|
||||
| Log | `spdlog` writes results and warnings to the console. |
|
||||
|
||||
If enrichment or generation fails for a city, that city is skipped and the pipeline continues.
|
||||
|
||||
### Key Components
|
||||
|
||||
- `src/main.cc` - argument parsing and Boost.DI composition root.
|
||||
- `JsonLoader` - validates curated location input.
|
||||
- `WikipediaService` - queries Wikipedia extracts, caches results, returns empty context on failure.
|
||||
- `LlamaGenerator` - formats prompts for Gemma 4, validates JSON output, retries malformed responses up to three times. If output looks truncated, the retry raises the token budget before trying again.
|
||||
- `MockGenerator` - stable hash-based output so the same city input always produces the same brewery.
|
||||
- `SqliteExportService` - creates a dated SQLite file per run and persists each successful brewery into normalized tables.
|
||||
- Brewery payloads include English and local-language name and description fields.
|
||||
|
||||
### Runtime Behaviour
|
||||
|
||||
`WikipediaService` queries city, country, and beer-related Wikipedia extracts using its configured lookup, then caches the first successful response per query string. The fetched extract text is included in the prompt as context for generation.
|
||||
|
||||
`GetLocationContext()` returns an empty string when the web client is unavailable or when lookup/parsing fails.
|
||||
|
||||
`LlamaGenerator` validates model output as structured JSON. The retry path exists as a safety hatch for cases where the reasoning block consumes available token budget and compresses the JSON output space. All runs to date have produced valid output on the first pass; the path is kept for resilience.
|
||||
|
||||
`MockGenerator` uses stable hashes for repeatable output in demos and Storybook runs.
|
||||
|
||||
### Process Flow - Activity Diagram
|
||||
|
||||

|
||||
|
||||
### Architectural Overview - Class Diagram
|
||||
|
||||

|
||||
|
||||
---
|
||||
|
||||
## Generated Output
|
||||
|
||||
Each successful run stores a `GeneratedBrewery` pair with the source location and a `BreweryResult` payload. The same generated records are also written to a fresh SQLite export file named with the current UTC timestamp.
|
||||
|
||||
| Field | Meaning |
|
||||
| ------------------- | ------------------------------------------ |
|
||||
| `name_en` | Brewery name in English. |
|
||||
| `description_en` | Brewery description in English. |
|
||||
| `name_local` | Brewery name in the local language. |
|
||||
| `description_local` | Brewery description in the local language. |
|
||||
|
||||
The log dump also includes city, country, state or province, ISO subdivision code, latitude, and longitude for each entry.
|
||||
|
||||
### Consumer Data Shape
|
||||
|
||||
| Field | Why it matters |
|
||||
| ----------------------------------- | ------------------------------------------------ |
|
||||
| `city`, `state_province`, `country` | Human-readable location labels and page headings |
|
||||
| `iso3166_1`, `iso3166_2` | Filtering, regional grouping, locale matching |
|
||||
| `latitude`, `longitude` | Map pins and nearby brewery views |
|
||||
| `local_languages` | Locale-aware copy selection |
|
||||
| `name_en`, `description_en` | Default English display content |
|
||||
| `name_local`, `description_local` | Local-language display content |
|
||||
| `region_context` | Richer copy for cards and detail pages |
|
||||
|
||||
---
|
||||
|
||||
## Language Generation Quality
|
||||
|
||||
The generation pipeline passes local language codes to the model to retrieve a translated `description_local`.
|
||||
|
||||
Output quality is reliable for high-resource languages such as French, though it may struggle with regional variants and idiomatic phrasing. This can be seen with these data points:
|
||||
|
||||
```json
|
||||
[
|
||||
{
|
||||
"city": "Kinshasa",
|
||||
"state_province": "Kinshasa",
|
||||
"iso3166_2": "CD-KN",
|
||||
"country": "Democratic Republic of the Congo",
|
||||
"iso3166_1": "CD",
|
||||
"latitude": -4.4419,
|
||||
"longitude": 15.2663,
|
||||
"local_languages": ["fr-CD", "ln"]
|
||||
},
|
||||
{
|
||||
"city": "Paris",
|
||||
"state_province": "Île-de-France",
|
||||
"iso3166_2": "FR-IDF",
|
||||
"country": "France",
|
||||
"iso3166_1": "FR",
|
||||
"latitude": 48.8566,
|
||||
"longitude": 2.3522,
|
||||
"local_languages": ["fr-FR"]
|
||||
},
|
||||
{
|
||||
"city": "Abidjan",
|
||||
"state_province": "Abidjan",
|
||||
"iso3166_2": "CI-AB",
|
||||
"country": "Ivory Coast",
|
||||
"iso3166_1": "CI",
|
||||
"latitude": 5.36,
|
||||
"longitude": -4.0083,
|
||||
"local_languages": ["fr-CI"]
|
||||
},
|
||||
{
|
||||
"city": "Montreal",
|
||||
"state_province": "Quebec",
|
||||
"iso3166_2": "CA-QC",
|
||||
"country": "Canada",
|
||||
"iso3166_1": "CA",
|
||||
"latitude": 45.5017,
|
||||
"longitude": -73.5673,
|
||||
"local_languages": ["fr-CA"]
|
||||
},
|
||||
{
|
||||
"city": "Brussels",
|
||||
"state_province": "Brussels-Capital Region",
|
||||
"iso3166_2": "BE-BRU",
|
||||
"country": "Belgium",
|
||||
"iso3166_1": "BE",
|
||||
"latitude": 50.8503,
|
||||
"longitude": 4.3517,
|
||||
"local_languages": ["fr-BE", "nl-BE"]
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
Output sample: [./out-sample/french-cities.example](out-sample/french-cities.example)
|
||||
|
||||
### Known Issues
|
||||
|
||||
#### Low-Resource Language Hallucination
|
||||
|
||||
For languages such as Welsh (Wales), Maori (Aotearoa/New Zealand), or Sicilian (Sicily, Italy), the model can generate text that looks syntactically plausible but is semantically incoherent. This comes from limited training-data coverage rather than prompt engineering.
|
||||
|
||||
#### Proposed Mitigations
|
||||
|
||||
- **Prevention via allowlist:** introduce a high-resource language allowlist. If a location's code is unlisted, skip `description_local` generation and fall back to English.
|
||||
- **Upstream sanitization:** strip known low-resource language codes from the `locations.json` payload before generation.
|
||||
- **Downstream flagging:** add a `description_local_confidence` column to the SQLite schema so downstream applications can filter or flag potentially hallucinated text by language tier.
|
||||
|
||||
---
|
||||
|
||||
## Tested Hardware
|
||||
|
||||
### ARM macOS - M1 Pro
|
||||
|
||||
| | |
|
||||
| --------- | --------------------------------- |
|
||||
| Host | MacBook Pro 14" (2021) |
|
||||
| CPU | Apple M1 Pro (8-core) |
|
||||
| GPU | Apple M1 Pro (14-core integrated) |
|
||||
| Memory | 16 GB |
|
||||
| Model | Gemma 4 E4B |
|
||||
| Inference | llama.cpp with Metal |
|
||||
|
||||
### x86_64 Linux - NVIDIA RTX 2000
|
||||
|
||||
| | |
|
||||
| --------- | ------------------------------ |
|
||||
| Host | ThinkPad P1 Gen 7 (Fedora 43) |
|
||||
| CPU | Intel Core Ultra 7 155H |
|
||||
| GPU | NVIDIA RTX 2000 Ada Generation |
|
||||
| Memory | 32 GB |
|
||||
| Model | Gemma 4 E4B |
|
||||
| Inference | llama.cpp with CUDA 12.x |
|
||||
|
||||
---
|
||||
|
||||
## Repo Layout
|
||||
|
||||
| Path | Purpose |
|
||||
| ---------------- | ---------------------------------------------- |
|
||||
| `includes/` | Public headers and shared models. |
|
||||
| `src/` | Implementation files. |
|
||||
| `locations.json` | Curated city input copied into the build tree. |
|
||||
| `prompts/` | System prompt used by the model-backed path. |
|
||||
| `diagrams/` | Architecture and pipeline diagrams. |
|
||||
|
||||
---
|
||||
|
||||
## Code Tour
|
||||
|
||||
- `src/main.cc` - argument parsing and DI composition root.
|
||||
- `src/biergarten_data_generator/` - orchestration, sampling, logging, and export.
|
||||
- `src/services/wikipedia/` - enrichment service and cache.
|
||||
- `src/services/sqlite/` - SQLite export implementation.
|
||||
- `src/data_generation/llama/` - local inference, prompt loading, output validation.
|
||||
- `src/data_generation/mock/` - deterministic fallback.
|
||||
|
||||
---
|
||||
|
||||
## Fixture Strategy
|
||||
|
||||
- `--mocked` for stable fixtures, repeatable screenshots, and Storybook runs.
|
||||
- `--model` when geographically grounded content matters for demos.
|
||||
- Keep `locations.json` structured enough to support discovery and future filtering.
|
||||
- Treat SQLite output as seed material for the app's brewery domain, not production data.
|
||||
|
||||
---
|
||||
|
||||
## Next Steps
|
||||
|
||||
The pipeline currently produces city-aware brewery records and dated SQLite exports. The next passes add additional fixture types so the app can exercise the full brewery domain without live data.
|
||||
|
||||
### Testing _(Very High Importance)_
|
||||
|
||||
- Unit test JSON validation and retry logic against malformed, truncated, and empty model outputs.
|
||||
- Integration test the enrichment pipeline with missing context, short context, and fake context inputs.
|
||||
- Adversarial context tests: feed plausible but geographically incorrect Wikipedia extracts and verify the model does not silently blend them with training data.
|
||||
- Verify bilingual enrichment behaviour when only an English extract is available versus when both extracts are present.
|
||||
- Confirm the retry path is reachable when the reasoning block consumes available token budget.
|
||||
|
||||
### Beer Generation
|
||||
|
||||
Generate catalog entries with style, ABV, IBU, color, aroma notes, and food pairing hints. Link beers back to breweries and cities. Keep style coverage wide enough to exercise search, sort, and category filters.
|
||||
|
||||
### User Generation
|
||||
|
||||
Generate user profiles with stable names, bios, locale hints, and preference signals. Include stable IDs for downstream fixture joins. Keep output deterministic for screenshots while allowing larger randomized batches.
|
||||
|
||||
### Check-In System
|
||||
|
||||
Produce timestamped check-in events between users and breweries. Use a J-curve activity profile - a small set of users accounts for most check-ins, the rest appear occasionally. Add bursty behaviour around weekends and travel periods.
|
||||
|
||||
### Beer Ratings
|
||||
|
||||
Generate rating events with a strong positive skew and a long tail of lower scores. Avoid uniform distributions. Attach timestamps and user IDs so the app can compute averages, trends, and per-style comparisons.
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -1,262 +0,0 @@
|
||||
@startuml biergarten_activity
|
||||
skinparam defaultFontName "DM Sans"
|
||||
skinparam defaultFontSize 13
|
||||
skinparam titleFontName "Volkhov"
|
||||
skinparam titleFontSize 20
|
||||
skinparam backgroundColor #FCFCF7
|
||||
skinparam defaultFontColor #14180C
|
||||
skinparam titleFontColor #14180C
|
||||
skinparam ArrowColor #656F33
|
||||
skinparam activityStartColor #EBECE3
|
||||
skinparam activityEndColor #4A5837
|
||||
skinparam activityStopColor #4A5837
|
||||
skinparam ActivityBackgroundColor #EBECE3
|
||||
skinparam ActivityBorderColor #4A5837
|
||||
skinparam ActivityDiamondBackgroundColor #CBD2B5
|
||||
skinparam ActivityDiamondBorderColor #4A5837
|
||||
skinparam NoteBackgroundColor #DBEEDD
|
||||
skinparam NoteFontColor #14180C
|
||||
skinparam NoteBorderColor #4A5837
|
||||
skinparam SwimlaneBorderColor #4A5837
|
||||
skinparam SwimlaneBorderThickness 1
|
||||
skinparam monochrome reverse
|
||||
|
||||
|
||||
title The Biergarten Data Pipeline — Activity Diagram
|
||||
|
||||
|Main|
|
||||
start
|
||||
:ParseArguments(argc, argv);
|
||||
if (Invalid args?) then (yes)
|
||||
:spdlog::error;
|
||||
stop
|
||||
else (no)
|
||||
endif
|
||||
:Init CurlGlobalState & LlamaBackendState;
|
||||
:Build DI injector;
|
||||
|
||||
|
||||
:Initialize SqliteExportService;
|
||||
note right
|
||||
Opens SQLite connection.
|
||||
Begins a single transaction
|
||||
covering all five fixture types.
|
||||
end note
|
||||
|
||||
:Create BoundedChannel<LogEntry> log_ch;
|
||||
:Spawn Log Worker thread;
|
||||
note right
|
||||
Log worker drains log_ch for the
|
||||
entire pipeline lifetime.
|
||||
All workers emit LogEntry structs
|
||||
via PipelineLogger — never spdlog directly.
|
||||
end note
|
||||
|
||||
:BiergartenPipelineOrchestrator::Run();
|
||||
|BiergartenPipelineOrchestrator::Run()|
|
||||
:JsonLoader::LoadLocations("locations.json");
|
||||
:JsonLoader::LoadBeerStyles("beer-styles.json");
|
||||
:JsonLoader::LoadPersonas("personas.json");
|
||||
:JsonLoader::LoadNamesByCountry("names-by-country.json");
|
||||
|
||||
:EnrichmentService::PreWarmBeerStyleCache(beer_styles);
|
||||
note right
|
||||
Beer styles do not need location context.
|
||||
Wikipedia summaries for the entire palette are
|
||||
fetched and cached globally at startup.
|
||||
end note
|
||||
|
||||
:EnrichmentService::PreWarmPersonaCache(personas);
|
||||
note right
|
||||
Persona descriptions do not need location context.
|
||||
All persona lookups are resolved and cached
|
||||
globally at startup.
|
||||
end note
|
||||
|
||||
|
||||
' ═══════════════════════════════════════════
|
||||
' PHASE 0 — USER GENERATION
|
||||
' ═══════════════════════════════════════════
|
||||
|Orchestrator|
|
||||
:RunUserPhase(sampled_locations);
|
||||
:Create BoundedChannels\n(loc_ch, llm_ch, exp_ch);
|
||||
|
||||
fork
|
||||
|Orchestrator|
|
||||
:Loop: Send Locations → loc_ch;
|
||||
:Close loc_ch;
|
||||
fork again
|
||||
|LLM Worker|
|
||||
while (loc_ch has items?) is (yes)
|
||||
:Receive Location;
|
||||
|
||||
:IPersonaSelectionStrategy::SelectPersona(\n personas_palette_);
|
||||
note right
|
||||
Guaranteed cache hit from startup.
|
||||
Returns a Persona struct carrying
|
||||
style_affinities, abv_range,
|
||||
ibu_preference, checkin_weight.
|
||||
end note
|
||||
|
||||
:NamesByCountry::SampleName(\n location.iso3166_1);
|
||||
note right
|
||||
Deterministic lookup — no LLM involved.
|
||||
Name selected from pre-keyed table
|
||||
and passed into the generation prompt.
|
||||
end note
|
||||
|
||||
:GenerateUser(location, persona, sampled_name)\nvia DataGenerator;
|
||||
note right
|
||||
LLM receives: Location fields + persona
|
||||
description + sampled name. Generates
|
||||
bio and preference signals grounded
|
||||
in locale and persona.
|
||||
end note
|
||||
|
||||
:PipelineLogger::Log(Info, UserGeneration,\n city, user_id, "llm");
|
||||
:Send GeneratedUser → llm_ch;
|
||||
endwhile (no)
|
||||
:Close llm_ch;
|
||||
fork again
|
||||
|SQLite Worker|
|
||||
while (llm_ch has items?) is (yes)
|
||||
:Receive GeneratedUser;
|
||||
:ProcessUser(user) → sqlite3_int64;
|
||||
:PipelineLogger::Log(Info, UserGeneration,\n city, user_id, "sqlite");
|
||||
:Append → user_pool_;
|
||||
endwhile (no)
|
||||
end fork
|
||||
|
||||
|Orchestrator|
|
||||
:Join LLM Worker, SQLite Worker;
|
||||
|
||||
' ═══════════════════════════════════════════
|
||||
' PHASE 1 — BREWERY & BEER GENERATION
|
||||
' ═══════════════════════════════════════════
|
||||
:RunBreweryAndBeerPhase(sampled_locations);
|
||||
:Create BoundedChannels\n(loc_ch, llm_ch, exp_ch);
|
||||
|
||||
fork
|
||||
|Orchestrator|
|
||||
:Loop: Send Locations → loc_ch;
|
||||
:Close loc_ch;
|
||||
fork again
|
||||
|Enrichment Workers (xN)|
|
||||
while (loc_ch has items?) is (yes)
|
||||
:Receive Location;
|
||||
:GetLocationContext(location,\nBreweryContextStrategy);
|
||||
:PipelineLogger::Log(Info,\n BreweryAndBeerGeneration,\n city, nullopt, "enrichment");
|
||||
:Send EnrichedCity → llm_ch;
|
||||
endwhile (no)
|
||||
|Orchestrator|
|
||||
:Join Enrichment Workers;
|
||||
:Close llm_ch;
|
||||
fork again
|
||||
|LLM Worker|
|
||||
while (llm_ch has items?) is (yes)
|
||||
:Receive EnrichedCity;
|
||||
|
||||
:GenerateBrewery(location, context)\nvia DataGenerator;
|
||||
|
||||
:IBeerSelectionStrategy::SelectStyles(\n brewery, beer_style_palette_);
|
||||
|
||||
while (For each selected BeerStyle?) is (remaining)
|
||||
:GetStyleContextFromCache(style);
|
||||
note right
|
||||
Guaranteed cache hit from startup.
|
||||
end note
|
||||
:GenerateBeer(brewery, style_context)\nvia DataGenerator;
|
||||
:Attach GeneratedBeer to Brewery bundle;
|
||||
endwhile (done)
|
||||
|
||||
:PipelineLogger::Log(Info,\n BreweryAndBeerGeneration,\n city, brewery_id, "llm");
|
||||
:Send BreweryWithBeers Bundle → exp_ch;
|
||||
endwhile (no)
|
||||
:Close exp_ch;
|
||||
fork again
|
||||
|SQLite Worker|
|
||||
while (exp_ch has items?) is (yes)
|
||||
:Receive BreweryWithBeers Bundle;
|
||||
:ProcessBrewery(brewery) → brewery_id;
|
||||
:Append → brewery_pool_;
|
||||
|
||||
while (For each beer in bundle?) is (remaining)
|
||||
:Set beer.brewery_id = brewery_id;
|
||||
:ProcessBeer(beer) → sqlite3_int64;
|
||||
:Append → beer_pool_;
|
||||
endwhile (done)
|
||||
|
||||
:PipelineLogger::Log(Info,\n BreweryAndBeerGeneration,\n city, brewery_id, "sqlite");
|
||||
endwhile (no)
|
||||
end fork
|
||||
|
||||
|Orchestrator|
|
||||
:Join LLM Worker, SQLite Worker;
|
||||
note right
|
||||
Both brewery_pool_ and beer_pool_
|
||||
are now completely populated.
|
||||
end note
|
||||
|
||||
' ═══════════════════════════════════════════
|
||||
' PHASE 2 — CHECKIN GENERATION
|
||||
' ═══════════════════════════════════════════
|
||||
:RunCheckinPhase();
|
||||
:ICheckinDistributionStrategy::\nAssignActivityWeights(user_pool_);
|
||||
note right
|
||||
Weights seeded from each user's
|
||||
persona.checkin_weight. J-curve profile
|
||||
emerges from persona distribution.
|
||||
end note
|
||||
|
||||
while (For each GeneratedUser in user_pool_?) is (remaining)
|
||||
:CheckinsForUser(user, brewery_pool_.size());
|
||||
while (For each checkin index?) is (remaining)
|
||||
:TimestampFor(user, index);
|
||||
:Select brewery from brewery_pool_;
|
||||
:GenerateCheckin(user, brewery, timestamp)\nvia DataGenerator;
|
||||
:ProcessCheckin(checkin) → sqlite3_int64;
|
||||
:PipelineLogger::Log(Info, CheckinGeneration,\n nullopt, checkin_id, "sqlite");
|
||||
:Append → checkin_pool_;
|
||||
endwhile (done)
|
||||
endwhile (done)
|
||||
|
||||
' ═══════════════════════════════════════════
|
||||
' PHASE 3 — RATING GENERATION
|
||||
' ═══════════════════════════════════════════
|
||||
:RunRatingPhase();
|
||||
note right
|
||||
Beer selection biased by
|
||||
user.persona.style_affinities and abv_range.
|
||||
Rating skew modulated per persona.
|
||||
end note
|
||||
|
||||
while (For each GeneratedCheckin in checkin_pool_?) is (remaining)
|
||||
:Match brewery_id → select beer from beer_pool_\n(same brewery_id, biased by persona affinities);
|
||||
if (Beer exists for brewery?) then (yes)
|
||||
:GenerateRating(user, beer, checkin_id)\nvia DataGenerator;
|
||||
:ProcessRating(rating);
|
||||
:PipelineLogger::Log(Info, RatingGeneration,\n nullopt, rating_id, "sqlite");
|
||||
else (no)
|
||||
:PipelineLogger::Log(Warn, RatingGeneration,\n nullopt, brewery_id, "sqlite");
|
||||
:Skip — brewery has no beers;
|
||||
endif
|
||||
endwhile (done)
|
||||
|
||||
' ═══════════════════════════════════════════
|
||||
' TEARDOWN
|
||||
' ═══════════════════════════════════════════
|
||||
|Main|
|
||||
:Finalize SqliteExportService;
|
||||
note right
|
||||
COMMIT covers all five fixture types.
|
||||
end note
|
||||
:Close log_ch;
|
||||
:Join Log Worker;
|
||||
note right
|
||||
Drain guarantees no LogEntry is
|
||||
dropped at shutdown.
|
||||
end note
|
||||
:spdlog::info "Pipeline complete in X ms";
|
||||
stop
|
||||
|
||||
@enduml
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -1,83 +0,0 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
|
||||
|
||||
/**
|
||||
* @file biergarten_data_generator.h
|
||||
* @brief Core orchestration class for pipeline data generation.
|
||||
*/
|
||||
|
||||
#include <memory>
|
||||
#include <span>
|
||||
#include <vector>
|
||||
|
||||
#include "data_generation/data_generator.h"
|
||||
#include "data_model/enriched_city.h"
|
||||
#include "data_model/generated_brewery.h"
|
||||
#include "data_model/location.h"
|
||||
#include "services/enrichment_service.h"
|
||||
#include "services/export_service.h"
|
||||
|
||||
/**
|
||||
* @brief Main data generator class for the Biergarten pipeline.
|
||||
*
|
||||
* This class encapsulates the core logic for generating brewery data.
|
||||
* It handles location loading, city enrichment, and brewery generation.
|
||||
*/
|
||||
class BiergartenDataGenerator {
|
||||
public:
|
||||
/**
|
||||
* @brief Construct a BiergartenDataGenerator with injected dependencies.
|
||||
*
|
||||
* @param context_service Context provider for sampled locations.
|
||||
* @param generator Brewery and user data generator.
|
||||
* @param exporter Storage backend for generated brewery data.
|
||||
*/
|
||||
BiergartenDataGenerator(std::unique_ptr<IEnrichmentService> context_service,
|
||||
std::unique_ptr<DataGenerator> generator,
|
||||
std::unique_ptr<IExportService> exporter);
|
||||
|
||||
/**
|
||||
* @brief Run the data generation pipeline.
|
||||
*
|
||||
* Performs the following steps:
|
||||
* 1. Load curated locations from JSON
|
||||
* 2. Resolve context for each city using the injected context service
|
||||
* 3. Generate brewery data for sampled cities
|
||||
*
|
||||
* @return true if successful, false if not
|
||||
*/
|
||||
bool Run();
|
||||
|
||||
private:
|
||||
/// @brief Owning context provider dependency.
|
||||
std::unique_ptr<IEnrichmentService> context_service_;
|
||||
|
||||
/// @brief Generator dependency selected in the composition root.
|
||||
std::unique_ptr<DataGenerator> generator_;
|
||||
|
||||
/// @brief Storage backend for generated brewery records.
|
||||
std::unique_ptr<IExportService> exporter_;
|
||||
|
||||
/**
|
||||
* @brief Load locations from JSON and sample cities.
|
||||
*
|
||||
* @return Vector of sampled locations capped at 50 entries.
|
||||
*/
|
||||
static std::vector<Location> QueryCitiesWithCountries();
|
||||
|
||||
/**
|
||||
* @brief Generate breweries for enriched cities.
|
||||
*
|
||||
* @param cities Span of enriched city data.
|
||||
*/
|
||||
void GenerateBreweries(std::span<const EnrichedCity> cities);
|
||||
|
||||
/**
|
||||
* @brief Log the generated brewery results.
|
||||
*/
|
||||
void LogResults() const;
|
||||
|
||||
/// @brief Stores generated brewery data.
|
||||
std::vector<GeneratedBrewery> generated_breweries_;
|
||||
};
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
|
||||
@@ -1,42 +0,0 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_APPLICATION_OPTIONS_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_APPLICATION_OPTIONS_H_
|
||||
|
||||
/**
|
||||
* @file data_model/application_options.h
|
||||
* @brief Program options for the Biergarten pipeline application.
|
||||
*/
|
||||
|
||||
#include <cstdint>
|
||||
#include <string>
|
||||
|
||||
/**
|
||||
* @brief Program options for the Biergarten pipeline application.
|
||||
*/
|
||||
struct ApplicationOptions {
|
||||
/// @brief Path to the LLM model file (gguf format); mutually exclusive with
|
||||
/// use_mocked.
|
||||
std::string model_path;
|
||||
|
||||
/// @brief Use mocked generator instead of LLM; mutually exclusive with
|
||||
/// model_path.
|
||||
bool use_mocked = false;
|
||||
|
||||
/// @brief LLM sampling temperature (0.0 to 1.0, higher = more random).
|
||||
float temperature = 1.0F;
|
||||
|
||||
/// @brief LLM nucleus sampling top-p parameter (0.0 to 1.0, higher = more
|
||||
/// random).
|
||||
float top_p = 0.95F;
|
||||
|
||||
/// @brief LLM top-k sampling parameter.
|
||||
uint32_t top_k = 64;
|
||||
|
||||
/// @brief Context window size (tokens) for LLM inference. Higher values
|
||||
/// support longer prompts but use more memory.
|
||||
uint32_t n_ctx = 8192;
|
||||
|
||||
/// @brief Random seed for sampling (-1 for random, otherwise non-negative).
|
||||
int seed = -1;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_APPLICATION_OPTIONS_H_
|
||||
@@ -1,22 +0,0 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_BREWERY_LOCATION_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_BREWERY_LOCATION_H_
|
||||
|
||||
/**
|
||||
* @file data_model/brewery_location.h
|
||||
* @brief Non-owning brewery location input.
|
||||
*/
|
||||
|
||||
#include <string_view>
|
||||
|
||||
/**
|
||||
* @brief Non-owning brewery location input.
|
||||
*/
|
||||
struct BreweryLocation {
|
||||
/// @brief City name.
|
||||
std::string_view city_name;
|
||||
|
||||
/// @brief Country name.
|
||||
std::string_view country_name;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_BREWERY_LOCATION_H_
|
||||
@@ -1,28 +0,0 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_BREWERY_RESULT_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_BREWERY_RESULT_H_
|
||||
|
||||
/**
|
||||
* @file data_model/brewery_result.h
|
||||
* @brief Generated brewery payload.
|
||||
*/
|
||||
|
||||
#include <string>
|
||||
|
||||
/**
|
||||
* @brief Generated brewery payload.
|
||||
*/
|
||||
struct BreweryResult {
|
||||
/// @brief Brewery display name in English.
|
||||
std::string name_en;
|
||||
|
||||
/// @brief Brewery description text in English.
|
||||
std::string description_en;
|
||||
|
||||
/// @brief Brewery display name in the local language.
|
||||
std::string name_local;
|
||||
|
||||
/// @brief Brewery description text in the local language.
|
||||
std::string description_local;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_BREWERY_RESULT_H_
|
||||
@@ -1,21 +0,0 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_ENRICHED_CITY_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_ENRICHED_CITY_H_
|
||||
|
||||
/**
|
||||
* @file data_model/enriched_city.h
|
||||
* @brief Enriched city data with Wikipedia context.
|
||||
*/
|
||||
|
||||
#include <string>
|
||||
|
||||
#include "data_model/location.h"
|
||||
|
||||
/**
|
||||
* @brief Enriched city data with Wikipedia context.
|
||||
*/
|
||||
struct EnrichedCity {
|
||||
Location location;
|
||||
std::string region_context{};
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_ENRICHED_CITY_H_
|
||||
@@ -1,20 +0,0 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATED_BREWERY_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATED_BREWERY_H_
|
||||
|
||||
/**
|
||||
* @file data_model/generated_brewery.h
|
||||
* @brief Helper struct to store generated brewery data.
|
||||
*/
|
||||
|
||||
#include "data_model/brewery_result.h"
|
||||
#include "data_model/location.h"
|
||||
|
||||
/**
|
||||
* @brief Helper struct to store generated brewery data.
|
||||
*/
|
||||
struct GeneratedBrewery {
|
||||
Location location;
|
||||
BreweryResult brewery;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATED_BREWERY_H_
|
||||
@@ -1,13 +0,0 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATION_MODELS_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATION_MODELS_H_
|
||||
|
||||
/**
|
||||
* @file data_model/generation_models.h
|
||||
* @brief Convenience include for shared generation payload models.
|
||||
*/
|
||||
|
||||
#include "data_model/brewery_location.h"
|
||||
#include "data_model/brewery_result.h"
|
||||
#include "data_model/user_result.h"
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATION_MODELS_H_
|
||||
@@ -1,41 +0,0 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_LOCATION_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_LOCATION_H_
|
||||
|
||||
/**
|
||||
* @file data_model/location.h
|
||||
* @brief Location data model used throughout generation pipeline.
|
||||
*/
|
||||
|
||||
#include <string>
|
||||
#include <vector>
|
||||
|
||||
/**
|
||||
* @brief Canonical location record for city-level generation.
|
||||
*/
|
||||
struct Location {
|
||||
/// @brief City name.
|
||||
std::string city{};
|
||||
|
||||
/// @brief State or province name.
|
||||
std::string state_province{};
|
||||
|
||||
/// @brief ISO 3166-2 subdivision code.
|
||||
std::string iso3166_2{};
|
||||
|
||||
/// @brief Country name.
|
||||
std::string country{};
|
||||
|
||||
/// @brief ISO 3166-1 country code.
|
||||
std::string iso3166_1{};
|
||||
|
||||
/// @brief Local language codes in priority order.
|
||||
std::vector<std::string> local_languages{};
|
||||
|
||||
/// @brief Latitude in decimal degrees.
|
||||
double latitude{};
|
||||
|
||||
/// @brief Longitude in decimal degrees.
|
||||
double longitude{};
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_LOCATION_H_
|
||||
@@ -1,12 +0,0 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_PIPELINE_MODELS_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_PIPELINE_MODELS_H_
|
||||
|
||||
/**
|
||||
* @file data_model/pipeline_models.h
|
||||
* @brief Convenience include for pipeline-specific data models.
|
||||
*/
|
||||
|
||||
#include "data_model/enriched_city.h"
|
||||
#include "data_model/generated_brewery.h"
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_PIPELINE_MODELS_H_
|
||||
@@ -1,22 +0,0 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_USER_RESULT_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_USER_RESULT_H_
|
||||
|
||||
/**
|
||||
* @file data_model/user_result.h
|
||||
* @brief Generated user profile payload.
|
||||
*/
|
||||
|
||||
#include <string>
|
||||
|
||||
/**
|
||||
* @brief Generated user profile payload.
|
||||
*/
|
||||
struct UserResult {
|
||||
/// @brief Username handle.
|
||||
std::string username{};
|
||||
|
||||
/// @brief Short user biography.
|
||||
std::string bio{};
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_USER_RESULT_H_
|
||||
@@ -1,250 +0,0 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_EXPORT_SERVICE_HELPERS_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_EXPORT_SERVICE_HELPERS_H_
|
||||
|
||||
/**
|
||||
* @file services/sqlite_export_service_helpers.h
|
||||
* @brief Internal SQLite export helpers shared across per-method translation
|
||||
* units.
|
||||
*/
|
||||
|
||||
#include <sqlite3.h>
|
||||
|
||||
#include <boost/json.hpp>
|
||||
#include <cstddef>
|
||||
#include <cstring>
|
||||
#include <filesystem>
|
||||
#include <limits>
|
||||
#include <memory>
|
||||
#include <stdexcept>
|
||||
#include <string>
|
||||
#include <string_view>
|
||||
#include <vector>
|
||||
|
||||
namespace sqlite_export_service_internal {
|
||||
|
||||
struct SqliteDatabaseDeleter {
|
||||
void operator()(sqlite3* handle) const noexcept {
|
||||
if (handle != nullptr) {
|
||||
sqlite3_close(handle);
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
struct SqliteStatementDeleter {
|
||||
void operator()(sqlite3_stmt* statement) const noexcept {
|
||||
if (statement != nullptr) {
|
||||
sqlite3_finalize(statement);
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
using SqliteDatabaseHandle = std::unique_ptr<sqlite3, SqliteDatabaseDeleter>;
|
||||
using SqliteStatementHandle =
|
||||
std::unique_ptr<sqlite3_stmt, SqliteStatementDeleter>;
|
||||
|
||||
inline constexpr std::string_view kCreateLocationsTableSql = R"sql(
|
||||
|
||||
CREATE TABLE IF NOT EXISTS locations (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
city TEXT NOT NULL,
|
||||
state_province TEXT NOT NULL,
|
||||
iso3166_2 TEXT NOT NULL,
|
||||
country TEXT NOT NULL,
|
||||
iso3166_1 TEXT NOT NULL,
|
||||
local_languages_json TEXT NOT NULL,
|
||||
latitude REAL NOT NULL,
|
||||
longitude REAL NOT NULL,
|
||||
UNIQUE(city, state_province, iso3166_2, country, latitude, longitude)
|
||||
);
|
||||
|
||||
)sql";
|
||||
|
||||
inline constexpr std::string_view kCreateBreweriesTableSql = R"sql(
|
||||
|
||||
CREATE TABLE IF NOT EXISTS breweries (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
location_id INTEGER NOT NULL,
|
||||
name_en TEXT NOT NULL,
|
||||
description_en TEXT NOT NULL,
|
||||
name_local TEXT NOT NULL,
|
||||
description_local TEXT NOT NULL,
|
||||
FOREIGN KEY(location_id) REFERENCES locations(id) ON DELETE CASCADE
|
||||
);
|
||||
|
||||
CREATE INDEX IF NOT EXISTS idx_breweries_location_id ON breweries(location_id);
|
||||
|
||||
)sql";
|
||||
|
||||
inline constexpr std::string_view kInsertLocationSql = R"sql(
|
||||
INSERT INTO locations (
|
||||
city,
|
||||
state_province,
|
||||
iso3166_2,
|
||||
country,
|
||||
iso3166_1,
|
||||
local_languages_json,
|
||||
latitude,
|
||||
longitude
|
||||
) VALUES (?, ?, ?, ?, ?, ?, ?, ?);
|
||||
)sql";
|
||||
|
||||
inline constexpr std::string_view kInsertBrewerySql = R"sql(
|
||||
INSERT INTO breweries (
|
||||
location_id,
|
||||
name_en,
|
||||
description_en,
|
||||
name_local,
|
||||
description_local
|
||||
) VALUES (?, ?, ?, ?, ?);
|
||||
)sql";
|
||||
|
||||
inline constexpr int kLocationCityBindIndex = 1;
|
||||
inline constexpr int kLocationStateProvinceBindIndex = 2;
|
||||
inline constexpr int kLocationIso31662BindIndex = 3;
|
||||
inline constexpr int kLocationCountryBindIndex = 4;
|
||||
inline constexpr int kLocationIso31661BindIndex = 5;
|
||||
inline constexpr int kLocationLanguagesBindIndex = 6;
|
||||
inline constexpr int kLocationLatitudeBindIndex = 7;
|
||||
inline constexpr int kLocationLongitudeBindIndex = 8;
|
||||
|
||||
inline constexpr int kBreweryLocationIdBindIndex = 1;
|
||||
inline constexpr int kBreweryEnglishNameBindIndex = 2;
|
||||
inline constexpr int kBreweryEnglishDescriptionBindIndex = 3;
|
||||
inline constexpr int kBreweryLocalNameBindIndex = 4;
|
||||
inline constexpr int kBreweryLocalDescriptionBindIndex = 5;
|
||||
|
||||
inline void ThrowSqliteError(sqlite3* db_handle, std::string_view action) {
|
||||
const std::string message =
|
||||
db_handle != nullptr ? sqlite3_errmsg(db_handle) : "unknown SQLite error";
|
||||
throw std::runtime_error(std::string(action) + ": " + message);
|
||||
}
|
||||
|
||||
inline SqliteDatabaseHandle OpenDatabase(const std::filesystem::path& path) {
|
||||
sqlite3* raw_handle = nullptr;
|
||||
const std::string path_string = path.string();
|
||||
const int result = sqlite3_open(path_string.c_str(), &raw_handle);
|
||||
SqliteDatabaseHandle handle(raw_handle);
|
||||
if (result != SQLITE_OK) {
|
||||
const std::string message = raw_handle != nullptr
|
||||
? sqlite3_errmsg(raw_handle)
|
||||
: "unknown SQLite error";
|
||||
throw std::runtime_error("Failed to open SQLite export database: " +
|
||||
message);
|
||||
}
|
||||
|
||||
return handle;
|
||||
}
|
||||
|
||||
inline void ExecSql(const SqliteDatabaseHandle& db_handle, std::string_view sql,
|
||||
const char* action) {
|
||||
char* error_message = nullptr;
|
||||
const std::string sql_text(sql);
|
||||
const int result = sqlite3_exec(db_handle.get(), sql_text.c_str(), nullptr,
|
||||
nullptr, &error_message);
|
||||
if (result != SQLITE_OK) {
|
||||
const std::string message = error_message != nullptr
|
||||
? error_message
|
||||
: sqlite3_errmsg(db_handle.get());
|
||||
sqlite3_free(error_message);
|
||||
throw std::runtime_error(std::string(action) + ": " + message);
|
||||
}
|
||||
}
|
||||
|
||||
inline SqliteStatementHandle PrepareStatement(
|
||||
const SqliteDatabaseHandle& db_handle, std::string_view sql,
|
||||
const char* action) {
|
||||
sqlite3_stmt* raw_statement = nullptr;
|
||||
const std::string sql_text(sql);
|
||||
const int result = sqlite3_prepare_v2(db_handle.get(), sql_text.c_str(), -1,
|
||||
&raw_statement, nullptr);
|
||||
SqliteStatementHandle statement(raw_statement);
|
||||
if (result != SQLITE_OK) {
|
||||
ThrowSqliteError(db_handle.get(), action);
|
||||
}
|
||||
|
||||
return statement;
|
||||
}
|
||||
|
||||
inline void ResetStatement(SqliteStatementHandle& statement) {
|
||||
if (statement != nullptr) {
|
||||
sqlite3_reset(statement.get());
|
||||
sqlite3_clear_bindings(statement.get());
|
||||
}
|
||||
}
|
||||
|
||||
inline void DeleteCharArray(void* data) noexcept {
|
||||
delete[] static_cast<char*>(data);
|
||||
}
|
||||
|
||||
inline void BindText(const SqliteStatementHandle& statement, int index,
|
||||
std::string_view value, const char* action) {
|
||||
const auto byte_count = value.size();
|
||||
if (byte_count > static_cast<std::size_t>(std::numeric_limits<int>::max())) {
|
||||
ThrowSqliteError(sqlite3_db_handle(statement.get()), action);
|
||||
}
|
||||
|
||||
auto buffer = std::make_unique<char[]>(byte_count + 1);
|
||||
std::memcpy(buffer.get(), value.data(), byte_count);
|
||||
buffer[byte_count] = '\0';
|
||||
|
||||
char* raw_buffer = buffer.release();
|
||||
const int result =
|
||||
sqlite3_bind_text(statement.get(), index, raw_buffer,
|
||||
static_cast<int>(byte_count), DeleteCharArray);
|
||||
if (result != SQLITE_OK) {
|
||||
DeleteCharArray(raw_buffer);
|
||||
ThrowSqliteError(sqlite3_db_handle(statement.get()), action);
|
||||
}
|
||||
}
|
||||
|
||||
inline void BindDouble(const SqliteStatementHandle& statement, int index,
|
||||
double value, std::string_view action) {
|
||||
const int result = sqlite3_bind_double(statement.get(), index, value);
|
||||
if (result != SQLITE_OK) {
|
||||
ThrowSqliteError(sqlite3_db_handle(statement.get()), action);
|
||||
}
|
||||
}
|
||||
|
||||
inline void BindInt64(const SqliteStatementHandle& statement, int index,
|
||||
sqlite3_int64 value, std::string_view action) {
|
||||
const int result = sqlite3_bind_int64(statement.get(), index, value);
|
||||
if (result != SQLITE_OK) {
|
||||
ThrowSqliteError(sqlite3_db_handle(statement.get()), action);
|
||||
}
|
||||
}
|
||||
|
||||
inline void StepStatement(const SqliteDatabaseHandle& db_handle,
|
||||
const SqliteStatementHandle& statement,
|
||||
std::string_view action) {
|
||||
const int result = sqlite3_step(statement.get());
|
||||
if (result != SQLITE_DONE) {
|
||||
ThrowSqliteError(db_handle.get(), action);
|
||||
}
|
||||
}
|
||||
|
||||
inline sqlite3_int64 LastInsertRowId(const SqliteDatabaseHandle& db_handle) {
|
||||
return sqlite3_last_insert_rowid(db_handle.get());
|
||||
}
|
||||
|
||||
inline void RollbackTransactionNoThrow(
|
||||
const SqliteDatabaseHandle& db_handle) noexcept {
|
||||
if (!db_handle) {
|
||||
return;
|
||||
}
|
||||
|
||||
sqlite3_exec(db_handle.get(), "ROLLBACK;", nullptr, nullptr, nullptr);
|
||||
}
|
||||
|
||||
inline std::string SerializeLocalLanguages(
|
||||
const std::vector<std::string>& local_languages) {
|
||||
boost::json::array array;
|
||||
array.reserve(local_languages.size());
|
||||
for (const auto& language : local_languages) {
|
||||
array.emplace_back(language);
|
||||
}
|
||||
return boost::json::serialize(array);
|
||||
}
|
||||
|
||||
} // namespace sqlite_export_service_internal
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_EXPORT_SERVICE_HELPERS_H_
|
||||
@@ -1,54 +0,0 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_CURL_WEB_CLIENT_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_CURL_WEB_CLIENT_H_
|
||||
|
||||
/**
|
||||
* @file web_client/curl_web_client.h
|
||||
* @brief libcurl-based WebClient implementation.
|
||||
*/
|
||||
|
||||
#include "web_client/web_client.h"
|
||||
|
||||
/**
|
||||
* @brief RAII wrapper for curl_global_init and curl_global_cleanup.
|
||||
*
|
||||
* Create one instance in application startup before using libcurl and keep it
|
||||
* alive for application lifetime.
|
||||
*/
|
||||
class CurlGlobalState {
|
||||
public:
|
||||
/// @brief Initializes global libcurl state.
|
||||
CurlGlobalState();
|
||||
|
||||
/// @brief Cleans up global libcurl state.
|
||||
~CurlGlobalState();
|
||||
|
||||
/// @brief Non-copyable type.
|
||||
CurlGlobalState(const CurlGlobalState&) = delete;
|
||||
|
||||
/// @brief Non-copyable type.
|
||||
CurlGlobalState& operator=(const CurlGlobalState&) = delete;
|
||||
};
|
||||
|
||||
/**
|
||||
* @brief WebClient implementation backed by libcurl.
|
||||
*/
|
||||
class CURLWebClient : public WebClient {
|
||||
public:
|
||||
/**
|
||||
* @brief Executes an HTTP GET request.
|
||||
*
|
||||
* @param url Request URL.
|
||||
* @return Response body.
|
||||
*/
|
||||
std::string Get(const std::string& url) override;
|
||||
|
||||
/**
|
||||
* @brief URL-encodes a string value.
|
||||
*
|
||||
* @param value Raw value.
|
||||
* @return URL-encoded string.
|
||||
*/
|
||||
std::string UrlEncode(const std::string& value) override;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_CURL_WEB_CLIENT_H_
|
||||
@@ -1,113 +0,0 @@
|
||||
# FULL SYSTEM PROMPT
|
||||
|
||||
You are an expert brewery copywriter, an architectural observer, and a master of zymurgy.
|
||||
|
||||
Your main goal is to come up with a fake, contextually accurate name and a matching description for a craft brewery located in a specific city. You need to base this on the exact geographic and cultural info provided. You also need to seamlessly blend historical background, cultural details, and highly specialized brewing methods to create a realistic and interesting story.
|
||||
|
||||
You will receive the inputs like this:
|
||||
|
||||
## CITY:
|
||||
|
||||
[City Name]
|
||||
|
||||
## COUNTRY:
|
||||
|
||||
[Country Name]
|
||||
|
||||
## LOCAL LANGUAGE CODES:
|
||||
|
||||
[Local language codes in priority order]
|
||||
|
||||
## CONTEXT:
|
||||
|
||||
[Information about local beer culture, history, geography, or language context]
|
||||
|
||||
## CRITICAL OUTPUT FORMAT (READ CAREFULLY):
|
||||
|
||||
ABSOLUTELY NO MARKDOWN FORMATTING. Do NOT wrap your response in json or ``` blocks.
|
||||
|
||||
Do not add markdown, code fences, or postscript around the final JSON object. Do not say "Here is the JSON" or "Enjoy!".
|
||||
|
||||
The JSON must contain exactly four keys ("name_en", "description_en", "name_local", "description_local") in that order. Do not rename or add any other keys.
|
||||
|
||||
ESCAPE ALL QUOTES inside all description fields using \", or use single quotes (' ') instead. This applies equally to description_en and description_local. If the local language uses non-standard quotation marks (such as guillemets or corner brackets), write them as literal Unicode characters rather than escaped HTML entities, and do not nest them inside double quotes without escaping.
|
||||
|
||||
DO NOT use actual line breaks (\n) inside any string. Keep all descriptions as one continuous string each.
|
||||
|
||||
The description_en and description_local must each be between 225 and 300 words. Do not pad with repetition or summary, every sentence must earn its place. Be concise and specific.
|
||||
|
||||
Expected JSON format:
|
||||
|
||||
```json
|
||||
{
|
||||
"name_en": "Fictional Local Brewery Name in English",
|
||||
"description_en": "The English description goes here.",
|
||||
"name_local": "Translated brewery name in the local language",
|
||||
"description_local": "The localised description goes here."
|
||||
}
|
||||
```
|
||||
|
||||
## CONTENT RULES AND CONSTRAINTS:
|
||||
|
||||
### THE HOOK:
|
||||
|
||||
The first sentence must be a sensory environmental hook written as a personal observation, something the owner notices or has always noticed. It should establish the local weather, smell, or soundscape of the city. Do not open with the brewery's name or a generic welcome.
|
||||
|
||||
### GEOGRAPHIC & CULTURAL ANCHOR:
|
||||
|
||||
The story must be deeply tied to the provided geographic and cultural info. Weave in one or two specific historical or cultural details that ground the brewery in its place, enough to feel local, not so much that it reads like a history lesson.
|
||||
|
||||
### TECHNICAL BREWING DETAIL (VARY THIS!):
|
||||
|
||||
You must include one highly specialized technical brewing detail. To avoid sounding repetitive, make sure this varies a lot. Some examples: using local wild yeast (like spontaneous Brettanomyces), adjusting the water profile (like Burtonization), specific mashing techniques, or using local barrels for aging. Don't use basic concepts like generic mash temperatures.
|
||||
|
||||
### ARCHITECTURAL DETAIL (VARY THIS!):
|
||||
|
||||
You must include one specific architectural or environmental detail, highlighting the building's physical wear, structure, or history. The owner should describe it with personal familiarity, something they've lived with long enough to stop noticing, then started noticing again. Avoid overused industry clichés like repurposed dairy equipment or glycol chillers.
|
||||
|
||||
### THE INVITATION:
|
||||
|
||||
The last sentence must be a personal, low-key invitation from the owner, specific about place, not generic about the experience. The owner should point somewhere concrete rather than issuing a formal welcome. Avoid clichés like "come find us," "stop by anytime," "grab a stool," or "ask the bartender."
|
||||
|
||||
### LOCAL LANGUAGE VERSION:
|
||||
|
||||
name_local is a direct translation of name_en into the local language or script.
|
||||
Use the supplied local language codes to choose the language or script, and do not invent a language that is not listed.
|
||||
|
||||
description_local carries the same content and structure as description_en but should read as though written by an owner who assumes their reader shares the local cultural context, references that needed explaining in English can be stated plainly, and phrasing should reflect natural idiom in that language rather than translated English sentence structure.
|
||||
|
||||
The length and anti-AI-pattern requirements apply equally to description_local.
|
||||
|
||||
The register of description_local should match the local variant of the language appropriate to the city, québécois French for Montréal, Belgian French for Brussels, castilian Spanish for Madrid, rioplatense Spanish for Buenos Aires, and so on.
|
||||
|
||||
### THE BLOCKLIST (FORBIDDEN CONCEPTS):
|
||||
|
||||
You absolutely cannot use the following words and phrases. Make sure your final output doesn't have any of these:
|
||||
|
||||
- "hidden gem"
|
||||
- "passion"
|
||||
- "authentic"
|
||||
- "repurposed dairy tank"
|
||||
- "repurposed industrial vat"
|
||||
- "concrete eggs"
|
||||
- "glycol chiller"
|
||||
- "mash temperature"
|
||||
- "grab a stool"
|
||||
- "ask the bartender"
|
||||
- "come find us"
|
||||
- "stop by anytime"
|
||||
|
||||
#### FORBIDDEN WRITING PATTERNS
|
||||
|
||||
The following patterns are common AI writing pitfalls and must not appear in either description:
|
||||
|
||||
- Negative parallelism constructions: "It's not X, it's Y" or "We're not about X, we're about Y"
|
||||
- Inflated significance phrases: "stands as a testament," "plays a vital role," "leaves a lasting impact," "watershed moment," "deeply rooted," "rich cultural heritage," "rich cultural tapestry," "enduring legacy"
|
||||
- Superficial trailing analyses: sentences ending in -ing words that add opinion without content ("ensuring consistency," "reflecting the city's spirit," "highlighting our commitment")
|
||||
- Promotional travel-copy tone: "breathtaking," "must-visit," "stunning," "vibrant"
|
||||
- Overused conjunctive transitions used as sentence openers: "Moreover," "Furthermore," "In addition," "In contrast"
|
||||
- Rule of three: do not consistently organise ideas or examples in triplets
|
||||
|
||||
### VOICE & PERSPECTIVE:
|
||||
|
||||
The description must be written in the first person, from the perspective of the brewery's owner. Favour "we" and "our" over "I" and "my." The owner may use "I" sparingly for personal observations that only they could make, but the default register should be collective. The tone should feel lived-in and a little weathered. Do not use third-person or second-person pronouns.
|
||||
@@ -1,16 +0,0 @@
|
||||
/**
|
||||
* @file biergarten_data_generator/biergarten_data_generator.cc
|
||||
* @brief BiergartenDataGenerator constructor implementation.
|
||||
*/
|
||||
|
||||
#include "biergarten_data_generator.h"
|
||||
|
||||
#include <utility>
|
||||
|
||||
BiergartenDataGenerator::BiergartenDataGenerator(
|
||||
std::unique_ptr<IEnrichmentService> context_service,
|
||||
std::unique_ptr<DataGenerator> generator,
|
||||
std::unique_ptr<IExportService> exporter)
|
||||
: context_service_(std::move(context_service)),
|
||||
generator_(std::move(generator)),
|
||||
exporter_(std::move(exporter)) {}
|
||||
@@ -1,58 +0,0 @@
|
||||
/**
|
||||
* @file biergarten_data_generator/generate_breweries.cc
|
||||
* @brief BiergartenDataGenerator::GenerateBreweries() implementation.
|
||||
*/
|
||||
|
||||
#include <spdlog/spdlog.h>
|
||||
|
||||
#include "biergarten_data_generator.h"
|
||||
|
||||
void BiergartenDataGenerator::GenerateBreweries(
|
||||
std::span<const EnrichedCity> cities) {
|
||||
spdlog::info("\n=== SAMPLE BREWERY GENERATION ===");
|
||||
|
||||
generated_breweries_.clear();
|
||||
size_t skipped_count = 0;
|
||||
size_t export_failed_count = 0;
|
||||
|
||||
for (const auto& [location, region_context] : cities) {
|
||||
try {
|
||||
const BreweryResult brewery =
|
||||
generator_->GenerateBrewery(location, region_context);
|
||||
|
||||
const GeneratedBrewery gen{.location = location, .brewery = brewery};
|
||||
|
||||
generated_breweries_.push_back(gen);
|
||||
|
||||
try {
|
||||
exporter_->ProcessRecord(gen);
|
||||
} catch (const std::exception& export_exception) {
|
||||
++export_failed_count;
|
||||
|
||||
spdlog::warn(
|
||||
"[Pipeline] Generated brewery for '{}' ({}) but SQLite export "
|
||||
"failed: {}",
|
||||
location.city, location.country, export_exception.what());
|
||||
}
|
||||
} catch (const std::exception& e) {
|
||||
++skipped_count;
|
||||
|
||||
spdlog::warn(
|
||||
"[Pipeline] Skipping city '{}' ({}): brewery generation failed: "
|
||||
"{}",
|
||||
location.city, location.country, e.what());
|
||||
}
|
||||
}
|
||||
|
||||
if (skipped_count > 0) {
|
||||
spdlog::warn("[Pipeline] Skipped {} city/cities due to generation errors",
|
||||
skipped_count);
|
||||
}
|
||||
|
||||
if (export_failed_count > 0) {
|
||||
spdlog::warn(
|
||||
"[Pipeline] Failed to export {} generated brewery/breweries to "
|
||||
"SQLite",
|
||||
export_failed_count);
|
||||
}
|
||||
}
|
||||
@@ -1,26 +0,0 @@
|
||||
/**
|
||||
* @file biergarten_data_generator/log_results.cc
|
||||
* @brief BiergartenDataGenerator::LogResults() implementation.
|
||||
*/
|
||||
|
||||
#include <spdlog/spdlog.h>
|
||||
|
||||
#include "biergarten_data_generator.h"
|
||||
|
||||
void BiergartenDataGenerator::LogResults() const {
|
||||
spdlog::info("\n=== GENERATED DATA DUMP ===");
|
||||
size_t index = 1;
|
||||
for (const auto& [location, brewery] : generated_breweries_) {
|
||||
spdlog::info(
|
||||
"{}. city=\"{}\" country=\"{}\" state=\"{}\" "
|
||||
"iso3166_2={} lat={} lon={}",
|
||||
index, location.city, location.country, location.state_province,
|
||||
location.iso3166_2, location.latitude, location.longitude);
|
||||
spdlog::info(" brewery_name_en=\"{}\"", brewery.name_en);
|
||||
spdlog::info(" brewery_description_en=\"{}\"", brewery.description_en);
|
||||
spdlog::info(" brewery_name_local=\"{}\"", brewery.name_local);
|
||||
spdlog::info(" brewery_description_local=\"{}\"",
|
||||
brewery.description_local);
|
||||
++index;
|
||||
}
|
||||
}
|
||||
@@ -1,41 +0,0 @@
|
||||
/**
|
||||
* @file biergarten_data_generator/query_cities_with_countries.cc
|
||||
* @brief BiergartenDataGenerator::QueryCitiesWithCountries() implementation.
|
||||
*/
|
||||
|
||||
#include <spdlog/spdlog.h>
|
||||
|
||||
#include <algorithm>
|
||||
#include <filesystem>
|
||||
#include <iterator>
|
||||
#include <random>
|
||||
|
||||
#include "biergarten_data_generator.h"
|
||||
#include "json_handling/json_loader.h"
|
||||
|
||||
static constexpr size_t kBreweryAmount = 50;
|
||||
|
||||
std::vector<Location> BiergartenDataGenerator::QueryCitiesWithCountries() {
|
||||
spdlog::info("\n=== GEOGRAPHIC DATA OVERVIEW ===");
|
||||
|
||||
const std::filesystem::path locations_path = "locations.json";
|
||||
|
||||
auto all_locations = JsonLoader::LoadLocations(locations_path);
|
||||
spdlog::info(" Locations available: {}", all_locations.size());
|
||||
|
||||
const size_t sample_count = std::min(kBreweryAmount, all_locations.size());
|
||||
|
||||
const auto sample_count_signed =
|
||||
static_cast<std::iter_difference_t<decltype(all_locations.cbegin())>>(
|
||||
sample_count);
|
||||
|
||||
std::vector<Location> sampled_locations;
|
||||
sampled_locations.reserve(sample_count);
|
||||
|
||||
std::random_device random_generator;
|
||||
std::ranges::sample(all_locations, std::back_inserter(sampled_locations),
|
||||
sample_count_signed, random_generator);
|
||||
|
||||
spdlog::info(" Sampled locations: {}", sampled_locations.size());
|
||||
return sampled_locations;
|
||||
}
|
||||
@@ -1,52 +0,0 @@
|
||||
/**
|
||||
* @file biergarten_data_generator/run.cc
|
||||
* @brief BiergartenDataGenerator::Run() implementation.
|
||||
*/
|
||||
|
||||
#include <spdlog/spdlog.h>
|
||||
|
||||
#include <utility>
|
||||
|
||||
#include "biergarten_data_generator.h"
|
||||
|
||||
bool BiergartenDataGenerator::Run() {
|
||||
try {
|
||||
exporter_->Initialize();
|
||||
|
||||
std::vector<Location> cities = QueryCitiesWithCountries();
|
||||
std::vector<EnrichedCity> enriched;
|
||||
enriched.reserve(cities.size());
|
||||
|
||||
size_t skipped_count = 0;
|
||||
for (auto& city : cities) {
|
||||
try {
|
||||
std::string region_context = context_service_->GetLocationContext(city);
|
||||
spdlog::debug("[Pipeline] Context for '{}' ({}) gathered:\n{}",
|
||||
city.city, city.country, region_context);
|
||||
|
||||
enriched.push_back(
|
||||
EnrichedCity{.location = std::move(city),
|
||||
.region_context = std::move(region_context)});
|
||||
} catch (const std::exception& exception) {
|
||||
++skipped_count;
|
||||
spdlog::warn(
|
||||
"[Pipeline] Skipping city '{}' ({}): context lookup failed: {}",
|
||||
city.city, city.country, exception.what());
|
||||
}
|
||||
}
|
||||
|
||||
if (skipped_count > 0) {
|
||||
spdlog::warn(
|
||||
"[Pipeline] Skipped {} city/cities due to context lookup errors",
|
||||
skipped_count);
|
||||
}
|
||||
|
||||
this->GenerateBreweries(enriched);
|
||||
exporter_->Finalize();
|
||||
this->LogResults();
|
||||
return true;
|
||||
} catch (const std::exception& e) {
|
||||
spdlog::error("Pipeline execution failed with error: {}", e.what());
|
||||
return false;
|
||||
}
|
||||
}
|
||||
@@ -1,18 +0,0 @@
|
||||
/**
|
||||
* @file data_generation/llama/generate_user.cc
|
||||
* @brief Generates locale-aware user profiles with strict two-line formatting,
|
||||
* retry handling, and output sanitization for downstream parsing.
|
||||
*/
|
||||
|
||||
#include <spdlog/spdlog.h>
|
||||
|
||||
#include <stdexcept>
|
||||
#include <string>
|
||||
|
||||
#include "data_generation/llama_generator.h"
|
||||
#include "data_generation/llama_generator_helpers.h"
|
||||
|
||||
UserResult LlamaGenerator::GenerateUser(const std::string& locale) {
|
||||
return {.username = "test_user",
|
||||
.bio = "This is a test user profile from " + locale + "."};
|
||||
}
|
||||
@@ -1,55 +0,0 @@
|
||||
/**
|
||||
* @file data_generation/llama/load_brewery_prompt.cc
|
||||
* @brief Resolves brewery system prompt content from cache or a configured
|
||||
* filesystem path and provides a robust inline fallback prompt when absent.
|
||||
*/
|
||||
|
||||
#include <spdlog/spdlog.h>
|
||||
|
||||
#include <filesystem>
|
||||
#include <fstream>
|
||||
#include <stdexcept>
|
||||
|
||||
#include "data_generation/llama_generator.h"
|
||||
|
||||
/**
|
||||
* @brief Loads brewery system prompt from disk or cache.
|
||||
*
|
||||
* @param prompt_file_path Preferred prompt file location.
|
||||
* @return Prompt text loaded from disk.
|
||||
*/
|
||||
std::string LlamaGenerator::LoadBrewerySystemPrompt(
|
||||
const std::filesystem::path& prompt_file_path) {
|
||||
// Return cached version if already loaded
|
||||
if (!brewery_system_prompt_.empty()) {
|
||||
return brewery_system_prompt_;
|
||||
}
|
||||
|
||||
std::ifstream prompt_file(prompt_file_path);
|
||||
if (!prompt_file.is_open()) {
|
||||
spdlog::error(
|
||||
"LlamaGenerator: Failed to open brewery system prompt file '{}'",
|
||||
prompt_file_path.string());
|
||||
throw std::runtime_error(
|
||||
"LlamaGenerator: missing brewery system prompt file: " +
|
||||
prompt_file_path.string());
|
||||
}
|
||||
|
||||
const std::string prompt((std::istreambuf_iterator(prompt_file)),
|
||||
std::istreambuf_iterator<char>());
|
||||
prompt_file.close();
|
||||
|
||||
if (prompt.empty()) {
|
||||
spdlog::error("LlamaGenerator: Brewery system prompt file '{}' is empty",
|
||||
prompt_file_path.string());
|
||||
throw std::runtime_error(
|
||||
"LlamaGenerator: empty brewery system prompt file: " +
|
||||
prompt_file_path.string());
|
||||
}
|
||||
|
||||
spdlog::info(
|
||||
"LlamaGenerator: Loaded brewery system prompt from '{}' ({} chars)",
|
||||
prompt_file_path.string(), prompt.length());
|
||||
brewery_system_prompt_ = prompt;
|
||||
return brewery_system_prompt_;
|
||||
}
|
||||
@@ -1,198 +0,0 @@
|
||||
/**
|
||||
* @file main.cc
|
||||
* @brief Parses command-line options, validates runtime mode selection,
|
||||
* initializes shared infrastructure, and executes the pipeline entry flow.
|
||||
*/
|
||||
|
||||
#include <spdlog/spdlog.h>
|
||||
|
||||
#include <boost/di.hpp>
|
||||
#include <boost/program_options.hpp>
|
||||
#include <chrono>
|
||||
#include <exception>
|
||||
#include <memory>
|
||||
#include <optional>
|
||||
#include <sstream>
|
||||
#include <string>
|
||||
|
||||
#include "biergarten_data_generator.h"
|
||||
#include "data_generation/llama_generator.h"
|
||||
#include "data_generation/mock_generator.h"
|
||||
#include "data_generation/prompt_formatting/gemma4_jinja_prompt_formatter.h"
|
||||
#include "data_model/application_options.h"
|
||||
#include "llama_backend_state.h"
|
||||
#include "services/enrichment_service.h"
|
||||
#include "services/export_service.h"
|
||||
#include "services/sqlite_export_service.h"
|
||||
#include "services/wikipedia_service.h"
|
||||
#include "web_client/curl_web_client.h"
|
||||
|
||||
namespace prog_opts = boost::program_options;
|
||||
namespace di = boost::di;
|
||||
|
||||
/**
|
||||
* @brief Parse command-line arguments into ApplicationOptions.
|
||||
*
|
||||
* @param argc Command-line argument count.
|
||||
* @param argv Command-line arguments.
|
||||
* @return Parsed ApplicationOptions if parsing succeeded, std::nullopt
|
||||
* otherwise.
|
||||
*/
|
||||
std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv) {
|
||||
prog_opts::options_description desc("Pipeline Options");
|
||||
|
||||
auto opt = desc.add_options();
|
||||
|
||||
opt("help,h", "Produce help message");
|
||||
|
||||
opt("mocked", prog_opts::bool_switch(),
|
||||
"Use mocked generator for brewery/user data");
|
||||
|
||||
opt("model,m", prog_opts::value<std::string>()->default_value(""),
|
||||
"Path to LLM model (gguf)");
|
||||
|
||||
opt("temperature", prog_opts::value<float>()->default_value(1.0F),
|
||||
"Sampling temperature (higher = more random)");
|
||||
|
||||
opt("top-p", prog_opts::value<float>()->default_value(0.95F),
|
||||
"Nucleus sampling top-p in (0,1] (higher = more random)");
|
||||
|
||||
opt("top-k", prog_opts::value<uint32_t>()->default_value(64),
|
||||
"Top-k sampling parameter (higher = more candidate tokens)");
|
||||
|
||||
opt("n-ctx", prog_opts::value<uint32_t>()->default_value(8192),
|
||||
"Context window size in tokens (1-32768)");
|
||||
|
||||
opt("seed", prog_opts::value<int>()->default_value(-1),
|
||||
"Sampler seed: -1 for random, otherwise non-negative integer");
|
||||
|
||||
// Handle the "no arguments" or "help" case
|
||||
if (argc == 1) {
|
||||
spdlog::info("Biergarten Pipeline");
|
||||
std::stringstream usage_stream;
|
||||
usage_stream << "\nUsage: biergarten-pipeline [options]\n\n" << desc;
|
||||
spdlog::info(usage_stream.str());
|
||||
return std::nullopt;
|
||||
}
|
||||
|
||||
try {
|
||||
prog_opts::variables_map variables_map;
|
||||
prog_opts::store(prog_opts::parse_command_line(argc, argv, desc),
|
||||
variables_map);
|
||||
prog_opts::notify(variables_map);
|
||||
|
||||
if (variables_map.contains("help")) {
|
||||
std::stringstream help_stream;
|
||||
help_stream << "\n" << desc;
|
||||
spdlog::info(help_stream.str());
|
||||
return std::nullopt;
|
||||
}
|
||||
|
||||
const auto use_mocked = variables_map["mocked"].as<bool>();
|
||||
const auto model_path = variables_map["model"].as<std::string>();
|
||||
|
||||
if (use_mocked && !model_path.empty()) {
|
||||
spdlog::error(
|
||||
"Invalid arguments: --mocked and --model are mutually exclusive");
|
||||
return std::nullopt;
|
||||
}
|
||||
|
||||
if (!use_mocked && model_path.empty()) {
|
||||
spdlog::error(
|
||||
"Invalid arguments: Either --mocked or --model must be specified");
|
||||
return std::nullopt;
|
||||
}
|
||||
|
||||
const bool has_llm_params = !variables_map["temperature"].defaulted() ||
|
||||
!variables_map["top-p"].defaulted() ||
|
||||
!variables_map["top-k"].defaulted() ||
|
||||
!variables_map["seed"].defaulted();
|
||||
|
||||
if (use_mocked && has_llm_params) {
|
||||
spdlog::warn(
|
||||
"Sampling parameters (--temperature, --top-p, --top-k, --seed) are"
|
||||
" ignored when using --mocked");
|
||||
}
|
||||
|
||||
ApplicationOptions options;
|
||||
options.use_mocked = use_mocked;
|
||||
options.model_path = model_path;
|
||||
options.temperature = variables_map["temperature"].as<float>();
|
||||
options.top_p = variables_map["top-p"].as<float>();
|
||||
options.top_k = variables_map["top-k"].as<uint32_t>();
|
||||
options.n_ctx = variables_map["n-ctx"].as<uint32_t>();
|
||||
options.seed = variables_map["seed"].as<int>();
|
||||
|
||||
return options;
|
||||
} catch (const std::exception& exception) {
|
||||
spdlog::error("Failed to parse command-line arguments: {}",
|
||||
exception.what());
|
||||
return std::nullopt;
|
||||
} catch (...) {
|
||||
spdlog::error("Failed to parse command-line arguments: unknown error");
|
||||
return std::nullopt;
|
||||
}
|
||||
}
|
||||
|
||||
struct Timer {
|
||||
std::chrono::steady_clock::time_point start_time =
|
||||
std::chrono::steady_clock::now();
|
||||
[[nodiscard]] int64_t Elapsed() const {
|
||||
return std::chrono::duration_cast<std::chrono::milliseconds>(
|
||||
std::chrono::steady_clock::now() - start_time)
|
||||
.count();
|
||||
}
|
||||
};
|
||||
|
||||
int main(const int argc, char** argv) {
|
||||
try {
|
||||
Timer timer;
|
||||
const CurlGlobalState curl_state;
|
||||
const LlamaBackendState llama_backend_state;
|
||||
spdlog::set_pattern("[%Y-%m-%d %H:%M:%S.%e] [%^%l%$] %v");
|
||||
|
||||
const auto parsed_options = ParseArguments(argc, argv);
|
||||
if (!parsed_options.has_value()) {
|
||||
return 0;
|
||||
}
|
||||
|
||||
const auto options = *parsed_options;
|
||||
|
||||
const auto injector = di::make_injector(
|
||||
di::bind<WebClient>().to<CURLWebClient>(),
|
||||
di::bind<ApplicationOptions>().to(options),
|
||||
di::bind<IEnrichmentService>().to<WikipediaService>(),
|
||||
di::bind<IExportService>().to<SqliteExportService>(),
|
||||
di::bind<IPromptFormatter>().to<Gemma4JinjaPromptFormatter>(),
|
||||
di::bind<std::string>().to(options.model_path),
|
||||
di::bind<DataGenerator>().to(
|
||||
[options](const auto& inj) -> std::unique_ptr<DataGenerator> {
|
||||
if (options.use_mocked) {
|
||||
spdlog::info(
|
||||
"[Generator] Using MockGenerator (no model path provided)");
|
||||
return std::make_unique<MockGenerator>();
|
||||
}
|
||||
|
||||
spdlog::info(
|
||||
"[Generator] Using LlamaGenerator: {} (temperature={}, "
|
||||
"top-p={}, top-k={}, n_ctx={}, seed={})",
|
||||
options.model_path, options.temperature, options.top_p,
|
||||
options.top_k, options.n_ctx, options.seed);
|
||||
return inj.template create<std::unique_ptr<LlamaGenerator>>();
|
||||
}));
|
||||
|
||||
auto generator =
|
||||
injector.create<std::unique_ptr<BiergartenDataGenerator>>();
|
||||
|
||||
if (!generator->Run()) {
|
||||
spdlog::error("Pipeline execution failed");
|
||||
return 1;
|
||||
}
|
||||
|
||||
spdlog::info("Pipeline executed successfully in {} ms", timer.Elapsed());
|
||||
return 0;
|
||||
} catch (const std::exception& exception) {
|
||||
spdlog::critical("Unhandled fatal error in main: {}", exception.what());
|
||||
return 1;
|
||||
}
|
||||
}
|
||||
@@ -1,24 +0,0 @@
|
||||
/**
|
||||
* @file services/sqlite/build_database_path.cc
|
||||
* @brief SqliteExportService::BuildDatabasePath() implementation.
|
||||
*/
|
||||
|
||||
#include <filesystem>
|
||||
#include <string>
|
||||
|
||||
#include "services/sqlite_export_service.h"
|
||||
|
||||
std::filesystem::path SqliteExportService::BuildDatabasePath() const {
|
||||
std::filesystem::path base_filename("biergarten_seed_" + run_timestamp_utc_ +
|
||||
".sqlite");
|
||||
std::filesystem::path candidate =
|
||||
std::filesystem::current_path() / base_filename;
|
||||
|
||||
for (int suffix = 1; std::filesystem::exists(candidate); ++suffix) {
|
||||
candidate = std::filesystem::current_path() /
|
||||
std::filesystem::path("biergarten_seed_" + run_timestamp_utc_ +
|
||||
"-" + std::to_string(suffix) + ".sqlite");
|
||||
}
|
||||
|
||||
return candidate;
|
||||
}
|
||||
@@ -1,28 +0,0 @@
|
||||
/**
|
||||
* @file services/sqlite/build_location_key.cc
|
||||
* @brief SqliteExportService::BuildLocationKey() implementation.
|
||||
*/
|
||||
|
||||
#include <iomanip>
|
||||
#include <sstream>
|
||||
|
||||
#include "services/sqlite_export_service.h"
|
||||
#include "services/sqlite_export_service_helpers.h"
|
||||
|
||||
constexpr int kLocationPrecision = 17;
|
||||
|
||||
std::string SqliteExportService::BuildLocationKey(const Location& location) {
|
||||
std::ostringstream key_stream;
|
||||
key_stream << location.city << '\n'
|
||||
<< location.state_province << '\n'
|
||||
<< location.iso3166_2 << '\n'
|
||||
<< location.country << '\n'
|
||||
<< location.iso3166_1 << '\n'
|
||||
<< std::setprecision(kLocationPrecision) << location.latitude
|
||||
<< '\n'
|
||||
<< std::setprecision(kLocationPrecision) << location.longitude
|
||||
<< '\n'
|
||||
<< sqlite_export_service_internal::SerializeLocalLanguages(
|
||||
location.local_languages);
|
||||
return key_stream.str();
|
||||
}
|
||||
@@ -1,11 +0,0 @@
|
||||
/**
|
||||
* @file services/sqlite/finalize_statements.cc
|
||||
* @brief SqliteExportService::FinalizeStatements() implementation.
|
||||
*/
|
||||
|
||||
#include "services/sqlite_export_service.h"
|
||||
|
||||
void SqliteExportService::FinalizeStatements() noexcept {
|
||||
insert_brewery_stmt_.reset();
|
||||
insert_location_stmt_.reset();
|
||||
}
|
||||
@@ -1,39 +0,0 @@
|
||||
/**
|
||||
* @file services/sqlite/initialize.cc
|
||||
* @brief SqliteExportService::Initialize() implementation.
|
||||
*/
|
||||
|
||||
#include <filesystem>
|
||||
#include <memory>
|
||||
#include <stdexcept>
|
||||
#include <string>
|
||||
|
||||
#include "services/sqlite_export_service.h"
|
||||
#include "services/sqlite_export_service_helpers.h"
|
||||
|
||||
void SqliteExportService::Initialize() {
|
||||
if (db_handle_ != nullptr) {
|
||||
throw std::runtime_error("SQLite export service is already initialized");
|
||||
}
|
||||
|
||||
run_timestamp_utc_ = date_time_provider_->GetUtcTimestamp();
|
||||
database_path_ = BuildDatabasePath();
|
||||
std::filesystem::create_directories(database_path_.parent_path());
|
||||
|
||||
db_handle_ = sqlite_export_service_internal::OpenDatabase(database_path_);
|
||||
|
||||
try {
|
||||
sqlite_export_service_internal::ExecSql(
|
||||
db_handle_, "PRAGMA foreign_keys = ON;",
|
||||
"Failed to enable SQLite foreign keys");
|
||||
InitializeSchema();
|
||||
PrepareStatements();
|
||||
sqlite_export_service_internal::ExecSql(
|
||||
db_handle_, "BEGIN IMMEDIATE TRANSACTION;",
|
||||
"Failed to begin SQLite transaction");
|
||||
transaction_open_ = true;
|
||||
} catch (...) {
|
||||
RollbackAndCloseNoThrow();
|
||||
throw;
|
||||
}
|
||||
}
|
||||
@@ -1,16 +0,0 @@
|
||||
/**
|
||||
* @file services/sqlite/initialize_schema.cc
|
||||
* @brief SqliteExportService::InitializeSchema() implementation.
|
||||
*/
|
||||
|
||||
#include "services/sqlite_export_service.h"
|
||||
#include "services/sqlite_export_service_helpers.h"
|
||||
|
||||
void SqliteExportService::InitializeSchema() {
|
||||
sqlite_export_service_internal::ExecSql(
|
||||
db_handle_, sqlite_export_service_internal::kCreateLocationsTableSql,
|
||||
"Failed to create SQLite locations table");
|
||||
sqlite_export_service_internal::ExecSql(
|
||||
db_handle_, sqlite_export_service_internal::kCreateBreweriesTableSql,
|
||||
"Failed to create SQLite breweries table");
|
||||
}
|
||||
@@ -1,16 +0,0 @@
|
||||
/**
|
||||
* @file services/sqlite/prepare_statements.cc
|
||||
* @brief SqliteExportService::PrepareStatements() implementation.
|
||||
*/
|
||||
|
||||
#include "services/sqlite_export_service.h"
|
||||
#include "services/sqlite_export_service_helpers.h"
|
||||
|
||||
void SqliteExportService::PrepareStatements() {
|
||||
insert_location_stmt_ = sqlite_export_service_internal::PrepareStatement(
|
||||
db_handle_, sqlite_export_service_internal::kInsertLocationSql,
|
||||
"Failed to prepare SQLite location insert statement");
|
||||
insert_brewery_stmt_ = sqlite_export_service_internal::PrepareStatement(
|
||||
db_handle_, sqlite_export_service_internal::kInsertBrewerySql,
|
||||
"Failed to prepare SQLite brewery insert statement");
|
||||
}
|
||||
@@ -1,100 +0,0 @@
|
||||
/**
|
||||
* @file services/sqlite/process_record.cc
|
||||
* @brief SqliteExportService::ProcessRecord() implementation.
|
||||
*/
|
||||
|
||||
#include <stdexcept>
|
||||
#include <string>
|
||||
|
||||
#include "services/sqlite_export_service.h"
|
||||
#include "services/sqlite_export_service_helpers.h"
|
||||
|
||||
void SqliteExportService::ProcessRecord(const GeneratedBrewery& brewery) {
|
||||
if (db_handle_ == nullptr || !transaction_open_) {
|
||||
throw std::runtime_error("SQLite export service is not initialized");
|
||||
}
|
||||
|
||||
const std::string location_key = BuildLocationKey(brewery.location);
|
||||
const auto cached_location = location_cache_.find(location_key);
|
||||
sqlite3_int64 location_id = 0;
|
||||
|
||||
if (cached_location != location_cache_.end()) {
|
||||
location_id = cached_location->second;
|
||||
} else {
|
||||
const std::string local_languages_json =
|
||||
sqlite_export_service_internal::SerializeLocalLanguages(
|
||||
brewery.location.local_languages);
|
||||
|
||||
sqlite_export_service_internal::BindText(
|
||||
insert_location_stmt_,
|
||||
sqlite_export_service_internal::kLocationCityBindIndex,
|
||||
brewery.location.city, "Failed to bind SQLite location city");
|
||||
sqlite_export_service_internal::BindText(
|
||||
insert_location_stmt_,
|
||||
sqlite_export_service_internal::kLocationStateProvinceBindIndex,
|
||||
brewery.location.state_province,
|
||||
"Failed to bind SQLite location state/province");
|
||||
sqlite_export_service_internal::BindText(
|
||||
insert_location_stmt_,
|
||||
sqlite_export_service_internal::kLocationIso31662BindIndex,
|
||||
brewery.location.iso3166_2,
|
||||
"Failed to bind SQLite location ISO 3166-2 code");
|
||||
sqlite_export_service_internal::BindText(
|
||||
insert_location_stmt_,
|
||||
sqlite_export_service_internal::kLocationCountryBindIndex,
|
||||
brewery.location.country, "Failed to bind SQLite location country");
|
||||
sqlite_export_service_internal::BindText(
|
||||
insert_location_stmt_,
|
||||
sqlite_export_service_internal::kLocationIso31661BindIndex,
|
||||
brewery.location.iso3166_1,
|
||||
"Failed to bind SQLite location ISO 3166-1 code");
|
||||
sqlite_export_service_internal::BindText(
|
||||
insert_location_stmt_,
|
||||
sqlite_export_service_internal::kLocationLanguagesBindIndex,
|
||||
local_languages_json, "Failed to bind SQLite location languages");
|
||||
sqlite_export_service_internal::BindDouble(
|
||||
insert_location_stmt_,
|
||||
sqlite_export_service_internal::kLocationLatitudeBindIndex,
|
||||
brewery.location.latitude, "Failed to bind SQLite location latitude");
|
||||
sqlite_export_service_internal::BindDouble(
|
||||
insert_location_stmt_,
|
||||
sqlite_export_service_internal::kLocationLongitudeBindIndex,
|
||||
brewery.location.longitude, "Failed to bind SQLite location longitude");
|
||||
|
||||
sqlite_export_service_internal::StepStatement(
|
||||
db_handle_, insert_location_stmt_,
|
||||
"Failed to insert SQLite location row");
|
||||
|
||||
location_id = sqlite_export_service_internal::LastInsertRowId(db_handle_);
|
||||
location_cache_.emplace(location_key, location_id);
|
||||
sqlite_export_service_internal::ResetStatement(insert_location_stmt_);
|
||||
}
|
||||
|
||||
sqlite_export_service_internal::BindInt64(
|
||||
insert_brewery_stmt_,
|
||||
sqlite_export_service_internal::kBreweryLocationIdBindIndex, location_id,
|
||||
"Failed to bind SQLite brewery location id");
|
||||
sqlite_export_service_internal::BindText(
|
||||
insert_brewery_stmt_,
|
||||
sqlite_export_service_internal::kBreweryEnglishNameBindIndex,
|
||||
brewery.brewery.name_en, "Failed to bind SQLite brewery English name");
|
||||
sqlite_export_service_internal::BindText(
|
||||
insert_brewery_stmt_,
|
||||
sqlite_export_service_internal::kBreweryEnglishDescriptionBindIndex,
|
||||
brewery.brewery.description_en,
|
||||
"Failed to bind SQLite brewery English description");
|
||||
sqlite_export_service_internal::BindText(
|
||||
insert_brewery_stmt_,
|
||||
sqlite_export_service_internal::kBreweryLocalNameBindIndex,
|
||||
brewery.brewery.name_local, "Failed to bind SQLite brewery local name");
|
||||
sqlite_export_service_internal::BindText(
|
||||
insert_brewery_stmt_,
|
||||
sqlite_export_service_internal::kBreweryLocalDescriptionBindIndex,
|
||||
brewery.brewery.description_local,
|
||||
"Failed to bind SQLite brewery local description");
|
||||
|
||||
sqlite_export_service_internal::StepStatement(
|
||||
db_handle_, insert_brewery_stmt_, "Failed to insert SQLite brewery row");
|
||||
|
||||
sqlite_export_service_internal::ResetStatement(insert_brewery_stmt_);
|
||||
}
|
||||
@@ -1,21 +0,0 @@
|
||||
/**
|
||||
* @file services/sqlite/rollback_and_close_no_throw.cc
|
||||
* @brief SqliteExportService::RollbackAndCloseNoThrow() implementation.
|
||||
*/
|
||||
|
||||
#include "services/sqlite_export_service.h"
|
||||
|
||||
void SqliteExportService::RollbackAndCloseNoThrow() noexcept {
|
||||
if (db_handle_ == nullptr) {
|
||||
return;
|
||||
}
|
||||
|
||||
if (transaction_open_) {
|
||||
sqlite_export_service_internal::RollbackTransactionNoThrow(db_handle_);
|
||||
transaction_open_ = false;
|
||||
}
|
||||
|
||||
FinalizeStatements();
|
||||
db_handle_.reset();
|
||||
location_cache_.clear();
|
||||
}
|
||||
@@ -1,61 +0,0 @@
|
||||
/**
|
||||
* @file wikipedia/fetch_extract.cc
|
||||
* @brief WikipediaService::FetchExtract() implementation.
|
||||
*/
|
||||
|
||||
#include <spdlog/spdlog.h>
|
||||
|
||||
#include <boost/json.hpp>
|
||||
#include <string>
|
||||
#include <string_view>
|
||||
|
||||
#include "services/wikipedia_service.h"
|
||||
|
||||
std::string WikipediaService::FetchExtract(std::string_view query) {
|
||||
const std::string cache_key(query);
|
||||
const auto cache_it = this->extract_cache_.find(cache_key);
|
||||
if (cache_it != this->extract_cache_.end()) {
|
||||
return cache_it->second;
|
||||
}
|
||||
|
||||
const std::string encoded = this->client_->UrlEncode(cache_key);
|
||||
const std::string url =
|
||||
"https://en.wikipedia.org/w/api.php?action=query&titles=" + encoded +
|
||||
"&prop=extracts&explaintext=1&format=json";
|
||||
|
||||
const std::string body = this->client_->Get(url);
|
||||
|
||||
boost::system::error_code parse_error;
|
||||
boost::json::value doc = boost::json::parse(body, parse_error);
|
||||
|
||||
if (!parse_error && doc.is_object()) {
|
||||
try {
|
||||
auto& pages = doc.at("query").at("pages").get_object();
|
||||
if (!pages.empty()) {
|
||||
auto& page = pages.begin()->value().get_object();
|
||||
if (page.contains("extract") && page.at("extract").is_string()) {
|
||||
const std::string_view extract_view = page.at("extract").as_string();
|
||||
std::string extract(extract_view);
|
||||
|
||||
spdlog::debug("WikipediaService fetched {} chars for '{}'",
|
||||
extract.size(), query);
|
||||
|
||||
this->extract_cache_.emplace(cache_key, extract);
|
||||
return extract;
|
||||
}
|
||||
}
|
||||
this->extract_cache_.emplace(cache_key, std::string{});
|
||||
} catch (const std::exception& e) {
|
||||
spdlog::warn(
|
||||
"WikipediaService: failed to parse response structure for '{}': "
|
||||
"{}",
|
||||
query, e.what());
|
||||
return {};
|
||||
}
|
||||
} else if (parse_error) {
|
||||
spdlog::warn("WikipediaService: JSON parse error for '{}': {}", query,
|
||||
parse_error.message());
|
||||
}
|
||||
|
||||
return {};
|
||||
}
|
||||
@@ -1,47 +0,0 @@
|
||||
/**
|
||||
* @file wikipedia/get_summary.cc
|
||||
* @brief WikipediaService::GetLocationContext() implementation.
|
||||
*/
|
||||
|
||||
#include <spdlog/spdlog.h>
|
||||
|
||||
#include <string>
|
||||
|
||||
#include "services/wikipedia_service.h"
|
||||
|
||||
std::string WikipediaService::GetLocationContext(const Location& loc) {
|
||||
if (!client_) {
|
||||
return {};
|
||||
}
|
||||
|
||||
std::string result;
|
||||
|
||||
std::string region_query(loc.city);
|
||||
if (!loc.country.empty()) {
|
||||
region_query += ", ";
|
||||
region_query += loc.country;
|
||||
}
|
||||
|
||||
const std::string beer_query = "beer in " + loc.country;
|
||||
const std::string city_beer_query = "beer in " + loc.city;
|
||||
|
||||
auto append_extract = [&result](const std::string& extract) -> void {
|
||||
if (extract.empty()) {
|
||||
return;
|
||||
}
|
||||
if (!result.empty()) {
|
||||
result += "\n\n";
|
||||
}
|
||||
result += extract;
|
||||
};
|
||||
|
||||
try {
|
||||
append_extract(FetchExtract(region_query));
|
||||
append_extract(FetchExtract(beer_query));
|
||||
append_extract(FetchExtract(city_beer_query));
|
||||
} catch (const std::runtime_error& e) {
|
||||
spdlog::debug("WikipediaService lookup failed for '{}': {}", region_query,
|
||||
e.what());
|
||||
}
|
||||
return result;
|
||||
}
|
||||
@@ -1,11 +0,0 @@
|
||||
/**
|
||||
* @file services/wikipedia/wikipedia_service.cc
|
||||
* @brief WikipediaService constructor implementation.
|
||||
*/
|
||||
|
||||
#include "services/wikipedia_service.h"
|
||||
|
||||
#include <utility>
|
||||
|
||||
WikipediaService::WikipediaService(std::unique_ptr<WebClient> client)
|
||||
: client_(std::move(client)) {}
|
||||
@@ -1,19 +0,0 @@
|
||||
/**
|
||||
* @file web_client/curl_global_state.cc
|
||||
* @brief CurlGlobalState constructor and destructor implementation.
|
||||
*/
|
||||
|
||||
#include <curl/curl.h>
|
||||
|
||||
#include <stdexcept>
|
||||
|
||||
#include "web_client/curl_web_client.h"
|
||||
|
||||
CurlGlobalState::CurlGlobalState() {
|
||||
if (curl_global_init(CURL_GLOBAL_DEFAULT) != CURLE_OK) {
|
||||
throw std::runtime_error(
|
||||
"[CURLWebClient] Failed to initialize libcurl globally");
|
||||
}
|
||||
}
|
||||
|
||||
CurlGlobalState::~CurlGlobalState() { curl_global_cleanup(); }
|
||||
@@ -1,86 +0,0 @@
|
||||
/**
|
||||
* @file web_client/curl_web_client_get.cc
|
||||
* @brief CURLWebClient::Get() implementation.
|
||||
*/
|
||||
|
||||
#include <curl/curl.h>
|
||||
|
||||
#include <cstdint>
|
||||
#include <limits>
|
||||
#include <memory>
|
||||
#include <stdexcept>
|
||||
#include <string>
|
||||
|
||||
#include "web_client/curl_web_client.h"
|
||||
|
||||
using CurlHandle = std::unique_ptr<CURL, decltype(&curl_easy_cleanup)>;
|
||||
|
||||
static constexpr long kConnectionTimeout = 10;
|
||||
static constexpr long kRequestTimeout = 30;
|
||||
static constexpr int32_t kOkHttpStatus = 200;
|
||||
|
||||
static CurlHandle CreateHandle() {
|
||||
CURL* handle = curl_easy_init();
|
||||
if (handle == nullptr) {
|
||||
throw std::runtime_error(
|
||||
"[CURLWebClient] Failed to initialize libcurl handle");
|
||||
}
|
||||
return {handle, &curl_easy_cleanup};
|
||||
}
|
||||
|
||||
static void SetCommonGetOptions(CURL* curl, const std::string& url) {
|
||||
curl_easy_setopt(curl, CURLOPT_URL, url.c_str());
|
||||
curl_easy_setopt(curl, CURLOPT_USERAGENT, "biergarten-pipeline/0.1.0");
|
||||
curl_easy_setopt(curl, CURLOPT_FOLLOWLOCATION, 1L);
|
||||
curl_easy_setopt(curl, CURLOPT_MAXREDIRS, 5L);
|
||||
curl_easy_setopt(curl, CURLOPT_CONNECTTIMEOUT, kConnectionTimeout);
|
||||
curl_easy_setopt(curl, CURLOPT_TIMEOUT, kRequestTimeout);
|
||||
curl_easy_setopt(curl, CURLOPT_ACCEPT_ENCODING, "gzip");
|
||||
}
|
||||
|
||||
// curl write callback that appends response data into a std::string
|
||||
static size_t WriteCallbackString(void* contents, const size_t size,
|
||||
const size_t nmemb, void* userp) {
|
||||
const size_t real_size = size * nmemb;
|
||||
auto* str = static_cast<std::string*>(userp);
|
||||
str->append(static_cast<char*>(contents), real_size);
|
||||
return real_size;
|
||||
}
|
||||
|
||||
std::string CURLWebClient::Get(const std::string& url) {
|
||||
const CurlHandle curl = CreateHandle();
|
||||
|
||||
std::string response_string;
|
||||
|
||||
SetCommonGetOptions(curl.get(), url);
|
||||
|
||||
curl_easy_setopt(curl.get(), CURLOPT_WRITEFUNCTION, WriteCallbackString);
|
||||
curl_easy_setopt(curl.get(), CURLOPT_WRITEDATA, &response_string);
|
||||
|
||||
CURLcode curl_result = curl_easy_perform(curl.get());
|
||||
|
||||
if (curl_result != CURLE_OK) {
|
||||
const auto error = std::string("[CURLWebClient] GET failed: ") +
|
||||
curl_easy_strerror(curl_result);
|
||||
throw std::runtime_error(error);
|
||||
}
|
||||
|
||||
long curl_http_code = 0;
|
||||
curl_easy_getinfo(curl.get(), CURLINFO_RESPONSE_CODE, &curl_http_code);
|
||||
|
||||
if (curl_http_code < std::numeric_limits<int32_t>::min() ||
|
||||
curl_http_code > std::numeric_limits<int32_t>::max()) {
|
||||
throw std::runtime_error("[CURLWebClient] Invalid HTTP status code: " +
|
||||
std::to_string(curl_http_code));
|
||||
}
|
||||
|
||||
const int32_t http_code = static_cast<int32_t>(curl_http_code);
|
||||
|
||||
if (http_code != kOkHttpStatus) {
|
||||
const std::string error = "[CURLWebClient] HTTP error " +
|
||||
std::to_string(http_code) + " for URL " + url;
|
||||
throw std::runtime_error(error);
|
||||
}
|
||||
|
||||
return response_string;
|
||||
}
|
||||
@@ -1,24 +0,0 @@
|
||||
/**
|
||||
* @file web_client/curl_web_client_url_encode.cc
|
||||
* @brief CURLWebClient::UrlEncode() implementation.
|
||||
*/
|
||||
|
||||
#include <curl/curl.h>
|
||||
|
||||
#include <stdexcept>
|
||||
#include <string>
|
||||
|
||||
#include "web_client/curl_web_client.h"
|
||||
|
||||
std::string CURLWebClient::UrlEncode(const std::string& value) {
|
||||
// A NULL handle is fine for UTF-8 encoding according to libcurl docs.
|
||||
char* output = curl_easy_escape(nullptr, value.c_str(), 0);
|
||||
|
||||
if (!output) {
|
||||
throw std::runtime_error("[CURLWebClient] curl_easy_escape failed");
|
||||
}
|
||||
|
||||
std::string result(output);
|
||||
curl_free(output);
|
||||
return result;
|
||||
}
|
||||
9
tooling/pipeline/.dockerignore
Normal file
9
tooling/pipeline/.dockerignore
Normal file
@@ -0,0 +1,9 @@
|
||||
build/
|
||||
cmake-build-debug/
|
||||
.git/
|
||||
.idea/
|
||||
**/*.sqlite
|
||||
**/*.log
|
||||
**/*.sqlite3
|
||||
**/*.db
|
||||
|
||||
@@ -6,3 +6,4 @@ data
|
||||
models
|
||||
*.gguf
|
||||
BiergartenPipeline.png
|
||||
output
|
||||
268
tooling/pipeline/CMakeLists.txt
Normal file
268
tooling/pipeline/CMakeLists.txt
Normal file
@@ -0,0 +1,268 @@
|
||||
cmake_minimum_required(VERSION 3.31)
|
||||
project(biergarten-pipeline)
|
||||
|
||||
# Set policy to allow FetchContent_Populate for header-only libraries
|
||||
# that have outdated CMakeLists.txt files
|
||||
cmake_policy(SET CMP0169 OLD)
|
||||
|
||||
# 1. Build Options
|
||||
|
||||
option(BIERGARTEN_MOCK_ONLY "Build with mock data generators only — skips llama.cpp" OFF)
|
||||
if(BIERGARTEN_MOCK_ONLY)
|
||||
message(STATUS "[biergarten] MOCK_ONLY build — llama.cpp will not be compiled.")
|
||||
endif()
|
||||
|
||||
# 2. Platform & GPU Detection
|
||||
if(NOT UNIX)
|
||||
message(FATAL_ERROR "[biergarten] Windows is not supported. Please use Linux (Fedora 43) or macOS (M1 Pro).")
|
||||
endif()
|
||||
|
||||
if(APPLE)
|
||||
if(CMAKE_SYSTEM_PROCESSOR MATCHES "arm64")
|
||||
message(STATUS "[biergarten] Apple Silicon detected — enabling Metal acceleration.")
|
||||
set(GGML_METAL ON CACHE BOOL "Enable Metal for Apple Silicon" FORCE)
|
||||
else()
|
||||
message(STATUS "[biergarten] Intel Mac detected — using CPU / Accelerate framework.")
|
||||
set(GGML_METAL OFF CACHE BOOL "Disable Metal for Intel Macs" FORCE)
|
||||
endif()
|
||||
else()
|
||||
find_package(CUDAToolkit QUIET)
|
||||
find_package(hip CONFIG QUIET)
|
||||
|
||||
if(CUDAToolkit_FOUND)
|
||||
message(STATUS "[biergarten] NVIDIA GPU detected — enabling CUDA acceleration.")
|
||||
set(GGML_CUDA ON CACHE BOOL "Enable CUDA for NVIDIA GPUs" FORCE)
|
||||
set(CMAKE_CUDA_ARCHITECTURES native)
|
||||
elseif(hip_FOUND OR DEFINED ENV{ROCM_PATH} OR EXISTS "/opt/rocm")
|
||||
message(STATUS "[biergarten] AMD GPU detected — enabling HIP/ROCm acceleration.")
|
||||
set(GGML_HIPBLAS ON CACHE BOOL "Enable HIP for AMD GPUs" FORCE)
|
||||
else()
|
||||
message(STATUS "[biergarten] No NVIDIA or AMD GPU found — falling back to CPU.")
|
||||
endif()
|
||||
endif()
|
||||
|
||||
# 3. Project-wide Settings
|
||||
set(CMAKE_CXX_STANDARD 20)
|
||||
set(CMAKE_CXX_STANDARD_REQUIRED ON)
|
||||
set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
|
||||
set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -O3 -march=native -flto")
|
||||
set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -Og -g")
|
||||
|
||||
# 4. Dependencies
|
||||
include(FetchContent)
|
||||
|
||||
# Boost (system install — via dnf/brew)
|
||||
find_package(Boost REQUIRED COMPONENTS json program_options)
|
||||
|
||||
# Boost.DI (unofficial Boost extension, must declare separately from main Boost dependency)
|
||||
# Header-only library, so we only fetch without invoking its CMakeLists.txt
|
||||
FetchContent_Declare(
|
||||
boost-di
|
||||
GIT_REPOSITORY https://github.com/boost-ext/di.git
|
||||
GIT_TAG v1.3.0
|
||||
GIT_SHALLOW TRUE
|
||||
)
|
||||
FetchContent_GetProperties(boost-di)
|
||||
if(NOT boost-di_POPULATED)
|
||||
FetchContent_Populate(boost-di)
|
||||
endif()
|
||||
|
||||
add_library(boost_di INTERFACE)
|
||||
add_library(boost::di ALIAS boost_di)
|
||||
target_include_directories(boost_di INTERFACE
|
||||
$<BUILD_INTERFACE:${boost-di_SOURCE_DIR}/include>
|
||||
)
|
||||
# SQLite amalgamation
|
||||
FetchContent_Declare(
|
||||
sqlite_amalgamation
|
||||
URL https://www.sqlite.org/2026/sqlite-amalgamation-3530000.zip
|
||||
URL_HASH SHA3_256=c2325c53b3b41761469f91cfb078e96882ac5d85bac10c11b0bd8f253b031e5b
|
||||
EXCLUDE_FROM_ALL
|
||||
)
|
||||
FetchContent_MakeAvailable(sqlite_amalgamation)
|
||||
if(NOT TARGET sqlite3)
|
||||
add_library(sqlite3 STATIC ${sqlite_amalgamation_SOURCE_DIR}/sqlite3.c)
|
||||
target_include_directories(sqlite3 PUBLIC ${sqlite_amalgamation_SOURCE_DIR})
|
||||
target_compile_definitions(sqlite3 PUBLIC SQLITE_THREADSAFE=1)
|
||||
endif()
|
||||
|
||||
# llama.cpp — skipped for mock-only builds
|
||||
if(NOT BIERGARTEN_MOCK_ONLY)
|
||||
find_library(LLAMA_LIB NAMES llama)
|
||||
find_library(GGML_LIB NAMES ggml)
|
||||
find_library(GGML_BASE_LIB NAMES ggml-base)
|
||||
find_path(LLAMA_INC_DIR NAMES llama.h PATH_SUFFIXES include)
|
||||
|
||||
if(LLAMA_LIB AND GGML_LIB AND GGML_BASE_LIB AND LLAMA_INC_DIR)
|
||||
message(STATUS "[biergarten] Found system llama.cpp — skipping FetchContent")
|
||||
|
||||
add_library(llama SHARED IMPORTED)
|
||||
set_target_properties(llama PROPERTIES
|
||||
IMPORTED_LOCATION "${LLAMA_LIB}"
|
||||
INTERFACE_INCLUDE_DIRECTORIES "${LLAMA_INC_DIR}"
|
||||
INTERFACE_LINK_LIBRARIES "${GGML_LIB};${GGML_BASE_LIB}"
|
||||
)
|
||||
else()
|
||||
message(STATUS "[biergarten] System llama.cpp not found — fetching via FetchContent")
|
||||
FetchContent_Declare(
|
||||
llama-cpp
|
||||
GIT_REPOSITORY https://github.com/ggml-org/llama.cpp.git
|
||||
GIT_TAG b9012
|
||||
)
|
||||
FetchContent_MakeAvailable(llama-cpp)
|
||||
endif()
|
||||
endif()
|
||||
|
||||
# spdlog
|
||||
FetchContent_Declare(
|
||||
spdlog
|
||||
GIT_REPOSITORY https://github.com/gabime/spdlog.git
|
||||
GIT_TAG v1.15.3
|
||||
)
|
||||
FetchContent_MakeAvailable(spdlog)
|
||||
|
||||
# cpp-httplib — header-only HTTP/HTTPS client replacing libcurl.
|
||||
# OpenSSL is required for HTTPS (Wikipedia API). find_package locates
|
||||
# libssl/libcrypto; HTTPLIB_REQUIRE_OPENSSL causes a hard build failure
|
||||
# if OpenSSL is absent rather than silently producing an HTTP-only binary.
|
||||
find_package(OpenSSL REQUIRED)
|
||||
FetchContent_Declare(
|
||||
cpp-httplib
|
||||
GIT_REPOSITORY https://github.com/yhirose/cpp-httplib.git
|
||||
GIT_TAG v0.43.2
|
||||
GIT_SHALLOW TRUE
|
||||
SYSTEM
|
||||
)
|
||||
set(HTTPLIB_REQUIRE_OPENSSL ON CACHE BOOL "Require OpenSSL for cpp-httplib" FORCE)
|
||||
FetchContent_MakeAvailable(cpp-httplib)
|
||||
|
||||
# 5. Executable & Sources
|
||||
add_executable(${PROJECT_NAME}
|
||||
includes/services/enrichment/mock_enrichment.h
|
||||
includes/json_handling/pretty_print.h)
|
||||
|
||||
# --- Entry point ---
|
||||
target_sources(${PROJECT_NAME} PRIVATE
|
||||
src/main.cc
|
||||
)
|
||||
|
||||
# --- json_handling ---
|
||||
target_sources(${PROJECT_NAME} PRIVATE
|
||||
src/json_handling/json_loader.cc
|
||||
)
|
||||
|
||||
# --- application_options ---
|
||||
target_sources(${PROJECT_NAME} PRIVATE
|
||||
src/application_options/parse_arguments.cc
|
||||
)
|
||||
|
||||
# --- biergarten_pipeline_orchestrator ---
|
||||
target_sources(${PROJECT_NAME} PRIVATE
|
||||
src/biergarten_pipeline_orchestrator/log_results.cc
|
||||
src/biergarten_pipeline_orchestrator/biergarten_pipeline_orchestrator.cc
|
||||
src/biergarten_pipeline_orchestrator/generate_breweries.cc
|
||||
src/biergarten_pipeline_orchestrator/run.cc
|
||||
src/biergarten_pipeline_orchestrator/query_cities_with_countries.cc
|
||||
)
|
||||
|
||||
# --- web_client ---
|
||||
target_sources(${PROJECT_NAME} PRIVATE
|
||||
src/web_client/http_web_client.cc
|
||||
)
|
||||
|
||||
# --- data_generation: prompt_formatting ---
|
||||
target_sources(${PROJECT_NAME} PRIVATE
|
||||
src/data_generation/prompt_formatting/gemma4_jinja_prompt_formatter.cc
|
||||
)
|
||||
|
||||
# --- data_generation: mock ---
|
||||
target_sources(${PROJECT_NAME} PRIVATE
|
||||
src/data_generation/mock/generate_brewery.cc
|
||||
src/data_generation/mock/generate_user.cc
|
||||
src/data_generation/mock/deterministic_hash.cc
|
||||
)
|
||||
|
||||
# --- data_generation: llama (skipped for mock-only builds) ---
|
||||
if(NOT BIERGARTEN_MOCK_ONLY)
|
||||
target_sources(${PROJECT_NAME} PRIVATE
|
||||
src/data_generation/llama/load.cc
|
||||
src/data_generation/llama/helpers.cc
|
||||
src/data_generation/llama/generate_brewery.cc
|
||||
src/data_generation/llama/infer.cc
|
||||
src/data_generation/llama/llama_generator.cc
|
||||
src/data_generation/llama/generate_user.cc
|
||||
)
|
||||
endif()
|
||||
|
||||
# --- services: wikipedia ---
|
||||
target_sources(${PROJECT_NAME} PRIVATE
|
||||
src/services/enrichment/wikipedia/wikipedia_service.cc
|
||||
src/services/enrichment/wikipedia/fetch_extract.cc
|
||||
src/services/enrichment/wikipedia/get_summary.cc
|
||||
)
|
||||
|
||||
# --- services: sqlite ---
|
||||
target_sources(${PROJECT_NAME} PRIVATE
|
||||
src/services/sqlite/process_record.cc
|
||||
src/services/sqlite/sqlite_export_service.cc
|
||||
src/services/sqlite/finalize.cc
|
||||
src/services/sqlite/initialize.cc
|
||||
src/services/sqlite/helpers/sqlite_connection_helpers.cc
|
||||
src/services/sqlite/helpers/sqlite_statement_helpers.cc
|
||||
)
|
||||
|
||||
# --- services: logging ---
|
||||
target_sources(${PROJECT_NAME} PRIVATE
|
||||
"src/services/logging/log_producer.cc"
|
||||
src/services/logging/log_dispatcher.cc
|
||||
)
|
||||
|
||||
# --- services (top-level) ---
|
||||
target_sources(${PROJECT_NAME} PRIVATE
|
||||
src/services/prompt_directory.cc
|
||||
)
|
||||
|
||||
# 6. Include Directories, Link Libraries & Compile Definitions
|
||||
target_include_directories(${PROJECT_NAME} PRIVATE
|
||||
includes
|
||||
)
|
||||
|
||||
target_link_libraries(${PROJECT_NAME} PRIVATE
|
||||
$<$<NOT:$<BOOL:${BIERGARTEN_MOCK_ONLY}>>:llama>
|
||||
boost::di
|
||||
Boost::json
|
||||
Boost::program_options
|
||||
spdlog::spdlog
|
||||
sqlite3
|
||||
httplib::httplib
|
||||
OpenSSL::SSL
|
||||
OpenSSL::Crypto
|
||||
)
|
||||
|
||||
target_compile_definitions(${PROJECT_NAME} PRIVATE
|
||||
# Defined when -DBIERGARTEN_MOCK_ONLY=ON — skips llama.cpp entirely.
|
||||
# Use #ifdef BIERGARTEN_MOCK_ONLY in source to guard llama-specific code.
|
||||
$<$<BOOL:${BIERGARTEN_MOCK_ONLY}>:BIERGARTEN_MOCK_ONLY>
|
||||
|
||||
# Defined for Debug configuration builds.
|
||||
# Use #ifdef DEBUG in source to enable debug-only behaviour (e.g. verbose logging).
|
||||
$<$<CONFIG:Debug>:DEBUG>
|
||||
)
|
||||
|
||||
target_compile_options(biergarten-pipeline PRIVATE
|
||||
-fmacro-prefix-map=${CMAKE_SOURCE_DIR}/tooling/pipeline/src/=
|
||||
)
|
||||
|
||||
|
||||
# 7. Runtime Assets
|
||||
configure_file(
|
||||
${CMAKE_SOURCE_DIR}/locations.json
|
||||
${CMAKE_BINARY_DIR}/locations.json
|
||||
COPYONLY
|
||||
)
|
||||
add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD
|
||||
COMMAND ${CMAKE_COMMAND} -E copy_directory
|
||||
${CMAKE_SOURCE_DIR}/prompts
|
||||
${CMAKE_BINARY_DIR}/prompts
|
||||
)
|
||||
|
||||
1
tooling/pipeline/docs
Symbolic link
1
tooling/pipeline/docs
Symbolic link
@@ -0,0 +1 @@
|
||||
../../docs/pipeline/
|
||||
102
tooling/pipeline/includes/biergarten_pipeline_orchestrator.h
Normal file
102
tooling/pipeline/includes/biergarten_pipeline_orchestrator.h
Normal file
@@ -0,0 +1,102 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
|
||||
|
||||
/**
|
||||
* @file biergarten_data_generator.h
|
||||
* @brief Orchestration for end-to-end brewery data generation pipeline.
|
||||
*
|
||||
* Intent: Coordinates location loading, enrichment, and generation phases
|
||||
* to produce a complete dataset. Coordinates dependencies via composition root.
|
||||
*/
|
||||
|
||||
#include <memory>
|
||||
#include <span>
|
||||
#include <vector>
|
||||
|
||||
#include "data_generation/data_generator.h"
|
||||
#include "data_model/generated_models.h"
|
||||
#include "services/database/export_service.h"
|
||||
#include "services/enrichment/enrichment_service.h"
|
||||
|
||||
#include "services/logging/logger.h"
|
||||
|
||||
/**
|
||||
* @brief Main data generator class for the Biergarten pipeline.
|
||||
*
|
||||
* This class encapsulates the core logic for generating brewery data.
|
||||
* It handles location loading, city enrichment, and brewery generation.
|
||||
*/
|
||||
class BiergartenPipelineOrchestrator {
|
||||
public:
|
||||
/**
|
||||
* @brief Constructs the orchestrator with injected pipeline dependencies.
|
||||
*
|
||||
* @param context_service Provides regional context for locations.
|
||||
* @param generator Implementation (Llama or Mock) for brewery/user generation.
|
||||
* @param exporter Database backend for persisting generated records.
|
||||
* @param application_options CLI configuration and paths.
|
||||
*/
|
||||
BiergartenPipelineOrchestrator(
|
||||
std::shared_ptr<ILogger> logger,
|
||||
std::unique_ptr<IEnrichmentService> context_service,
|
||||
std::unique_ptr<DataGenerator> generator,
|
||||
std::unique_ptr<IExportService> exporter,
|
||||
const ApplicationOptions& application_options);
|
||||
|
||||
/**
|
||||
* @brief Run the data generation pipeline.
|
||||
*
|
||||
* Performs the following steps:
|
||||
* 1. Load curated locations from JSON
|
||||
* 2. Resolve context for each city using the injected context service
|
||||
* 3. Generate brewery data for sampled cities
|
||||
*
|
||||
* @note STRUCTURAL CONCURRENCY REQUIREMENT:
|
||||
* When transitioned to a multithreaded design, this method MUST structurally
|
||||
* enforce that all deployed worker threads are joined before returning (e.g.
|
||||
* by using std::jthread or a structured concurrency primitive). This ensures
|
||||
* workers do not attempt to log to a closed channel during application teardown.
|
||||
*
|
||||
* @return true if successful, false if not
|
||||
*/
|
||||
bool Run();
|
||||
|
||||
private:
|
||||
/// @brief Logger instance for emitting pipeline messages.
|
||||
std::shared_ptr<ILogger> logger_;
|
||||
|
||||
/// @brief Owning context provider dependency.
|
||||
std::unique_ptr<IEnrichmentService> context_service_;
|
||||
|
||||
/// @brief Generator dependency selected in the composition root.
|
||||
std::unique_ptr<DataGenerator> generator_;
|
||||
|
||||
/// @brief Storage backend for generated brewery records.
|
||||
std::unique_ptr<IExportService> exporter_;
|
||||
|
||||
/// @brief CLI configuration: paths, model settings, generation parameters.
|
||||
ApplicationOptions application_options_;
|
||||
|
||||
/**
|
||||
* @brief Load locations from JSON and sample cities.
|
||||
*
|
||||
* @return Vector of sampled locations capped at 50 entries.
|
||||
*/
|
||||
std::vector<Location> QueryCitiesWithCountries();
|
||||
|
||||
/**
|
||||
* @brief Generate breweries for enriched cities.
|
||||
*
|
||||
* @param cities Span of enriched city data.
|
||||
*/
|
||||
void GenerateBreweries(std::span<const EnrichedCity> cities);
|
||||
|
||||
/**
|
||||
* @brief Log the generated brewery results.
|
||||
*/
|
||||
void LogResults() const;
|
||||
|
||||
/// @brief Stores generated brewery data.
|
||||
std::vector<GeneratedBrewery> generated_breweries_;
|
||||
};
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
|
||||
73
tooling/pipeline/includes/concurrency/bounded_channel.h
Normal file
73
tooling/pipeline/includes/concurrency/bounded_channel.h
Normal file
@@ -0,0 +1,73 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_CONCURRENCY_BOUNDED_CHANNEL_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_CONCURRENCY_BOUNDED_CHANNEL_H_
|
||||
|
||||
#include <condition_variable>
|
||||
#include <cstddef>
|
||||
#include <mutex>
|
||||
#include <optional>
|
||||
#include <queue>
|
||||
|
||||
/**
|
||||
* @file bounded_channel.h
|
||||
* @brief Thread-safe, bounded multi-producer/multi-consumer synchronous channel.
|
||||
*
|
||||
* Intent: Enables asynchronous inter-thread communication with backpressure.
|
||||
* Models a synchronous channel where producers/consumers block on capacity limits.
|
||||
*/
|
||||
|
||||
/**
|
||||
* @class BoundedChannel
|
||||
* @brief MPMC channel with fixed capacity and blocking semantics.
|
||||
*
|
||||
* Producers block when buffer is full; consumers block when empty.
|
||||
* Close() unblocks all waiters and signals channel exhaustion.
|
||||
*/
|
||||
template <typename T>
|
||||
class BoundedChannel {
|
||||
// -------------------------------------------------------------------------
|
||||
// Internal state — all access must be guarded by mutex_.
|
||||
// -------------------------------------------------------------------------
|
||||
|
||||
std::queue<T> queue_;
|
||||
|
||||
std::mutex mutex_;
|
||||
|
||||
std::condition_variable not_full_;
|
||||
|
||||
std::condition_variable not_empty_;
|
||||
|
||||
std::size_t capacity_;
|
||||
|
||||
bool closed_ = false;
|
||||
|
||||
public:
|
||||
/**
|
||||
* @brief Construct a bounded channel with the given capacity.
|
||||
* @param capacity Maximum number of items the channel may hold.
|
||||
*/
|
||||
explicit BoundedChannel(std::size_t capacity) : capacity_(capacity) {}
|
||||
|
||||
/**
|
||||
* @brief Send an item into the channel. Blocks when the channel is full.
|
||||
* @param item Move-only item to enqueue.
|
||||
*/
|
||||
void Send(T item);
|
||||
|
||||
/**
|
||||
* @brief Receive an item from the channel. Blocks when the channel is
|
||||
* empty.
|
||||
* @return std::optional<T> containing the item, or std::nullopt when the
|
||||
* channel is closed and drained.
|
||||
*/
|
||||
std::optional<T> Receive();
|
||||
|
||||
/**
|
||||
* @brief Close the channel and unblock all waiting threads. Idempotent.
|
||||
*/
|
||||
void Close();
|
||||
};
|
||||
|
||||
// Include the template implementation
|
||||
#include "bounded_channel.tcc"
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_CONCURRENCY_BOUNDED_CHANNEL_H_
|
||||
57
tooling/pipeline/includes/concurrency/bounded_channel.tcc
Normal file
57
tooling/pipeline/includes/concurrency/bounded_channel.tcc
Normal file
@@ -0,0 +1,57 @@
|
||||
#include "bounded_channel.h"
|
||||
|
||||
template <typename T>
|
||||
void BoundedChannel<T>::Send(T item) {
|
||||
// Acquire exclusive ownership of the mutex; released automatically on scope exit.
|
||||
std::unique_lock lock(mutex_);
|
||||
|
||||
// Block until there is space in the queue or the channel has been closed.
|
||||
// The predicate guards against spurious wakeups.
|
||||
not_full_.wait(lock, [&] { return queue_.size() < capacity_ || closed_; });
|
||||
|
||||
// If the channel was closed while waiting, discard the item and return.
|
||||
if (closed_) return;
|
||||
|
||||
// Move the item into the queue to avoid an unnecessary copy.
|
||||
queue_.push(std::move(item));
|
||||
|
||||
// Wake one blocked Receive() call to signal that data is now available.
|
||||
not_empty_.notify_one();
|
||||
}
|
||||
|
||||
template <typename T>
|
||||
std::optional<T> BoundedChannel<T>::Receive() {
|
||||
// Acquire exclusive ownership of the mutex.
|
||||
std::unique_lock lock(mutex_);
|
||||
|
||||
// Block until the queue is non-empty or the channel has been closed.
|
||||
// The predicate guards against spurious wakeups.
|
||||
not_empty_.wait(lock, [&] { return !queue_.empty() || closed_; });
|
||||
|
||||
// If woken due to closure and no items remain, signal exhaustion via nullopt.
|
||||
if (queue_.empty()) return std::nullopt;
|
||||
|
||||
// Move the front item out of the queue to avoid an unnecessary copy.
|
||||
T item = std::move(queue_.front());
|
||||
queue_.pop();
|
||||
|
||||
// Wake one blocked Send() call to signal that a slot has opened.
|
||||
not_full_.notify_one();
|
||||
|
||||
return item;
|
||||
}
|
||||
|
||||
template <typename T>
|
||||
void BoundedChannel<T>::Close() {
|
||||
// Acquire exclusive ownership of the mutex to ensure visibility of the flag.
|
||||
std::unique_lock lock(mutex_);
|
||||
|
||||
// Mark the channel as closed; subsequent Send() calls will be dropped.
|
||||
closed_ = true;
|
||||
|
||||
// Wake all blocked Send() callers so they can observe the closed flag and exit.
|
||||
not_full_.notify_all();
|
||||
|
||||
// Wake all blocked Receive() callers so they can drain remaining items or return nullopt.
|
||||
not_empty_.notify_all();
|
||||
}
|
||||
@@ -8,9 +8,7 @@
|
||||
|
||||
#include <string>
|
||||
|
||||
#include "data_model/brewery_result.h"
|
||||
#include "data_model/location.h"
|
||||
#include "data_model/user_result.h"
|
||||
#include "data_model/generated_models.h"
|
||||
|
||||
/**
|
||||
* @brief Interface for data generator implementations.
|
||||
@@ -14,9 +14,11 @@
|
||||
#include <string>
|
||||
#include <string_view>
|
||||
|
||||
#include "../services/prompting/prompt_directory.h"
|
||||
#include "data_generation/data_generator.h"
|
||||
#include "data_generation/prompt_formatting/prompt_formatter.h"
|
||||
#include "data_model/application_options.h"
|
||||
#include "data_model/models.h"
|
||||
#include "services/logging/logger.h"
|
||||
|
||||
struct llama_model;
|
||||
struct llama_context;
|
||||
@@ -33,10 +35,12 @@ class LlamaGenerator final : public DataGenerator {
|
||||
* @param options Parsed application options.
|
||||
* @param model_path Filesystem path to GGUF model assets.
|
||||
* @param prompt_formatter Formatter that produces model-specific prompts.
|
||||
* @param prompt_directory Directory service for loading named prompt files.
|
||||
*/
|
||||
LlamaGenerator(const ApplicationOptions& options,
|
||||
const std::string& model_path,
|
||||
std::unique_ptr<IPromptFormatter> prompt_formatter);
|
||||
const std::string& model_path, std::shared_ptr<ILogger> logger,
|
||||
std::unique_ptr<IPromptFormatter> prompt_formatter,
|
||||
std::unique_ptr<IPromptDirectory> prompt_directory);
|
||||
|
||||
~LlamaGenerator() override;
|
||||
|
||||
@@ -119,15 +123,6 @@ class LlamaGenerator final : public DataGenerator {
|
||||
int max_tokens = kDefaultMaxTokens,
|
||||
std::string_view grammar = {});
|
||||
|
||||
/**
|
||||
* @brief Loads the brewery system prompt from disk.
|
||||
*
|
||||
* @param prompt_file_path Prompt file path to try first.
|
||||
* @return Loaded prompt text.
|
||||
*/
|
||||
std::string LoadBrewerySystemPrompt(
|
||||
const std::filesystem::path& prompt_file_path);
|
||||
|
||||
ModelHandle model_;
|
||||
ContextHandle context_;
|
||||
float sampling_temperature_ = 1.0F;
|
||||
@@ -135,8 +130,10 @@ class LlamaGenerator final : public DataGenerator {
|
||||
uint32_t sampling_top_k_ = kDefaultSamplingTopK;
|
||||
std::mt19937 rng_;
|
||||
uint32_t n_ctx_ = kDefaultContextSize;
|
||||
std::string brewery_system_prompt_;
|
||||
int n_gpu_layers_ = 0;
|
||||
std::shared_ptr<ILogger> logger_;
|
||||
std::unique_ptr<IPromptFormatter> prompt_formatter_;
|
||||
std::unique_ptr<IPromptDirectory> prompt_directory_;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_LLAMA_GENERATOR_H_
|
||||
@@ -12,7 +12,7 @@
|
||||
#include <string>
|
||||
#include <string_view>
|
||||
|
||||
#include "data_model/brewery_result.h"
|
||||
#include "data_model/generated_models.h"
|
||||
|
||||
struct llama_vocab;
|
||||
using llama_token = int32_t;
|
||||
@@ -44,6 +44,13 @@ class MockGenerator final : public DataGenerator {
|
||||
*/
|
||||
static size_t DeterministicHash(const Location& location);
|
||||
|
||||
// Hash stride constants for deterministic distribution across fixed-size
|
||||
// arrays. These coprime strides spread hash values uniformly without
|
||||
// clustering, ensuring diverse output across different hash inputs.
|
||||
static constexpr size_t kNounHashStride = 7;
|
||||
static constexpr size_t kDescriptionHashStride = 13;
|
||||
static constexpr size_t kBioHashStride = 11;
|
||||
|
||||
static constexpr std::array<std::string_view, 18> kBreweryAdjectives = {
|
||||
"Craft", "Heritage", "Local", "Artisan", "Pioneer", "Golden",
|
||||
"Modern", "Classic", "Summit", "Northern", "Riverstone", "Barrel",
|
||||
@@ -1,4 +1,5 @@
|
||||
#pragma once
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_GEMMA4_JINJA_PROMPT_FORMATTER_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_GEMMA4_JINJA_PROMPT_FORMATTER_H_
|
||||
|
||||
#include <string>
|
||||
#include <string_view>
|
||||
@@ -13,3 +14,5 @@ class Gemma4JinjaPromptFormatter final : public IPromptFormatter {
|
||||
[[nodiscard]] std::string Format(std::string_view system_prompt,
|
||||
std::string_view user_prompt) const override;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_GEMMA4_JINJA_PROMPT_FORMATTER_H_
|
||||
@@ -1,4 +1,5 @@
|
||||
#pragma once
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_PROMPT_FORMATTER_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_PROMPT_FORMATTER_H_
|
||||
|
||||
#include <string>
|
||||
#include <string_view>
|
||||
@@ -15,3 +16,5 @@ class IPromptFormatter {
|
||||
[[nodiscard]] virtual std::string Format(
|
||||
std::string_view system_prompt, std::string_view user_prompt) const = 0;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_PROMPT_FORMATTER_H_
|
||||
66
tooling/pipeline/includes/data_model/generated_models.h
Normal file
66
tooling/pipeline/includes/data_model/generated_models.h
Normal file
@@ -0,0 +1,66 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATED_MODELS_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATED_MODELS_H_
|
||||
|
||||
/**
|
||||
* @file data_model/generated_models.h
|
||||
* @brief Generated output models from the pipeline: brewery/user results, enriched data,
|
||||
* and complete generation results.
|
||||
*/
|
||||
|
||||
#include <string>
|
||||
|
||||
#include "data_model/models.h"
|
||||
|
||||
// ============================================================================
|
||||
// Generation Output Models
|
||||
// ============================================================================
|
||||
|
||||
/**
|
||||
* @brief Generated brewery payload.
|
||||
*/
|
||||
struct BreweryResult {
|
||||
/// @brief Brewery display name in English.
|
||||
std::string name_en;
|
||||
|
||||
/// @brief Brewery description text in English.
|
||||
std::string description_en;
|
||||
|
||||
/// @brief Brewery display name in the local language.
|
||||
std::string name_local;
|
||||
|
||||
/// @brief Brewery description text in the local language.
|
||||
std::string description_local;
|
||||
};
|
||||
|
||||
/**
|
||||
* @brief Generated user profile payload.
|
||||
*/
|
||||
struct UserResult {
|
||||
/// @brief Username handle.
|
||||
std::string username{};
|
||||
|
||||
/// @brief Short user biography.
|
||||
std::string bio{};
|
||||
};
|
||||
|
||||
// ============================================================================
|
||||
// Pipeline Data Models
|
||||
// ============================================================================
|
||||
|
||||
/**
|
||||
* @brief Enriched city data with Wikipedia context.
|
||||
*/
|
||||
struct EnrichedCity {
|
||||
Location location;
|
||||
std::string region_context{};
|
||||
};
|
||||
|
||||
/**
|
||||
* @brief Helper struct to store generated brewery data.
|
||||
*/
|
||||
struct GeneratedBrewery {
|
||||
Location location;
|
||||
BreweryResult brewery;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATED_MODELS_H_
|
||||
145
tooling/pipeline/includes/data_model/models.h
Normal file
145
tooling/pipeline/includes/data_model/models.h
Normal file
@@ -0,0 +1,145 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_MODELS_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_MODELS_H_
|
||||
|
||||
/**
|
||||
* @file data_model/models.h
|
||||
* @brief Core data models: locations, application configuration, and generation
|
||||
* inputs.
|
||||
*/
|
||||
|
||||
#include <boost/program_options.hpp>
|
||||
#include <cstdint>
|
||||
#include <filesystem>
|
||||
#include <memory>
|
||||
#include <optional>
|
||||
#include <string>
|
||||
#include <string_view>
|
||||
#include <vector>
|
||||
|
||||
class ILogger;
|
||||
|
||||
namespace prog_opts = boost::program_options;
|
||||
|
||||
// ============================================================================
|
||||
// Location Models
|
||||
// ============================================================================
|
||||
|
||||
/**
|
||||
* @brief Canonical location record for city-level generation.
|
||||
*/
|
||||
struct Location {
|
||||
/// @brief City name.
|
||||
std::string city{};
|
||||
|
||||
/// @brief State or province name.
|
||||
std::string state_province{};
|
||||
|
||||
/// @brief ISO 3166-2 subdivision code.
|
||||
std::string iso3166_2{};
|
||||
|
||||
/// @brief Country name.
|
||||
std::string country{};
|
||||
|
||||
/// @brief ISO 3166-1 country code.
|
||||
std::string iso3166_1{};
|
||||
|
||||
/// @brief Local language codes in priority order.
|
||||
std::vector<std::string> local_languages{};
|
||||
|
||||
/// @brief Latitude in decimal degrees.
|
||||
double latitude{};
|
||||
|
||||
/// @brief Longitude in decimal degrees.
|
||||
double longitude{};
|
||||
};
|
||||
|
||||
/**
|
||||
* @brief Non-owning brewery location input.
|
||||
*/
|
||||
struct BreweryLocation {
|
||||
/// @brief City name.
|
||||
std::string_view city_name;
|
||||
|
||||
/// @brief Country name.
|
||||
std::string_view country_name;
|
||||
};
|
||||
|
||||
// ============================================================================
|
||||
// Configuration Models
|
||||
// ============================================================================
|
||||
|
||||
/**
|
||||
* @brief LLM sampling parameters.
|
||||
*/
|
||||
struct SamplingOptions {
|
||||
/// @brief LLM sampling temperature (0.0 to 1.0, higher = more random).
|
||||
float temperature = 1.0F;
|
||||
|
||||
/// @brief LLM nucleus sampling top-p parameter.
|
||||
float top_p = 0.95F;
|
||||
|
||||
/// @brief LLM top-k sampling parameter.
|
||||
uint32_t top_k = 64;
|
||||
|
||||
/// @brief Context window size (tokens).
|
||||
uint32_t n_ctx = 8192;
|
||||
|
||||
/// @brief Random seed (-1 for random, otherwise non-negative).
|
||||
int seed = -1;
|
||||
|
||||
/// @brief Number of layers to offload to GPU.
|
||||
int n_gpu_layers = 0;
|
||||
};
|
||||
|
||||
/**
|
||||
* @brief Configuration for the LLM generator component.
|
||||
*/
|
||||
struct GeneratorOptions {
|
||||
/// @brief Path to the LLM model file (gguf format).
|
||||
std::filesystem::path model_path;
|
||||
|
||||
/// @brief Use mocked generator instead of actual LLM inference.
|
||||
bool use_mocked = false;
|
||||
|
||||
|
||||
|
||||
/// @brief Specific sampling parameters for this generator.
|
||||
/// If nullopt, the application should use global defaults.
|
||||
std::optional<SamplingOptions> sampling;
|
||||
};
|
||||
|
||||
/**
|
||||
* @brief Configuration for the pipeline execution and output.
|
||||
*/
|
||||
struct PipelineOptions {
|
||||
/// @brief Directory for generated artifacts.
|
||||
std::filesystem::path output_path;
|
||||
|
||||
/// @brief Directory that contains named prompt files (e.g.
|
||||
/// BREWERY_GENERATION.md).
|
||||
std::filesystem::path prompt_dir;
|
||||
|
||||
/// @brief Path for application logs.
|
||||
std::filesystem::path log_path;
|
||||
|
||||
/// @brief Number of locations to sample from the dataset
|
||||
/// More locations -> more users/more breweries
|
||||
uint32_t location_count;
|
||||
};
|
||||
|
||||
/**
|
||||
* @brief Root configuration object for the Biergarten pipeline.
|
||||
*/
|
||||
struct ApplicationOptions {
|
||||
GeneratorOptions generator;
|
||||
PipelineOptions pipeline;
|
||||
};
|
||||
|
||||
// ============================================================================
|
||||
// Function Declarations
|
||||
// ============================================================================
|
||||
|
||||
std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv,
|
||||
std::shared_ptr<ILogger> logger = nullptr);
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_MODELS_H_
|
||||
@@ -7,16 +7,19 @@
|
||||
*/
|
||||
|
||||
#include <filesystem>
|
||||
#include <memory>
|
||||
#include <vector>
|
||||
|
||||
#include "data_model/location.h"
|
||||
#include "data_model/models.h"
|
||||
#include "services/logging/logger.h"
|
||||
|
||||
/// @brief Loads curated world locations from a JSON file into memory.
|
||||
class JsonLoader {
|
||||
public:
|
||||
/// @brief Parses a JSON array file and returns all location records.
|
||||
static std::vector<Location> LoadLocations(
|
||||
const std::filesystem::path& filepath);
|
||||
const std::filesystem::path& filepath,
|
||||
std::shared_ptr<ILogger> logger = nullptr);
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_JSON_HANDLING_JSON_LOADER_H_
|
||||
109
tooling/pipeline/includes/json_handling/pretty_print.h
Normal file
109
tooling/pipeline/includes/json_handling/pretty_print.h
Normal file
@@ -0,0 +1,109 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_JSON_HANDLING_PRETTY_PRINT_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_JSON_HANDLING_PRETTY_PRINT_H_
|
||||
|
||||
/**
|
||||
* @file json_handling/pretty_print.h
|
||||
* @brief Pretty-printing utilities for JSON values.
|
||||
*
|
||||
* Provides formatting capability for boost::json::value with indentation and
|
||||
* readable output. Adapted from Boost JSON library examples.
|
||||
*/
|
||||
|
||||
#include <boost/json.hpp>
|
||||
#include <ostream>
|
||||
#include <string>
|
||||
|
||||
/**
|
||||
* @brief Pretty-prints a JSON value to an output stream with indentation.
|
||||
*
|
||||
* Recursively formats JSON objects and arrays with consistent 4-space
|
||||
* indentation. Adapted from:
|
||||
* https://raw.githubusercontent.com/boostorg/json/refs/heads/develop/example/pretty.cpp
|
||||
*
|
||||
* @param outstream Output stream to write formatted JSON.
|
||||
* @param json_val JSON value to format.
|
||||
* @param indent Optional indentation string (managed internally on first call).
|
||||
*/
|
||||
inline void PrettyPrint(std::ostream& outstream,
|
||||
boost::json::value const& json_val,
|
||||
std::string* indent = nullptr) {
|
||||
std::string str;
|
||||
if (indent == nullptr) {
|
||||
indent = &str;
|
||||
}
|
||||
switch (json_val.kind()) {
|
||||
case boost::json::kind::object: {
|
||||
outstream << "{\n";
|
||||
indent->append(4, ' ');
|
||||
auto const& obj = json_val.get_object();
|
||||
if (!obj.empty()) {
|
||||
const auto* iter = obj.begin();
|
||||
for (;;) {
|
||||
outstream << *indent << boost::json::serialize(iter->key()) << " : ";
|
||||
PrettyPrint(outstream, iter->value(), indent);
|
||||
iter = std::next(iter);
|
||||
if (iter == obj.end()) {
|
||||
break;
|
||||
}
|
||||
|
||||
outstream << ",\n";
|
||||
}
|
||||
}
|
||||
outstream << "\n";
|
||||
indent->resize(indent->size() - 4);
|
||||
outstream << *indent << "}";
|
||||
break;
|
||||
}
|
||||
|
||||
case boost::json::kind::array: {
|
||||
outstream << "[\n";
|
||||
indent->append(4, ' ');
|
||||
auto const& arr = json_val.get_array();
|
||||
if (!arr.empty()) {
|
||||
const auto* iter = arr.begin();
|
||||
for (;;) {
|
||||
outstream << *indent;
|
||||
PrettyPrint(outstream, *iter, indent);
|
||||
iter = std::next(iter);
|
||||
if (iter == arr.end()) {
|
||||
break;
|
||||
}
|
||||
outstream << ",\n";
|
||||
}
|
||||
}
|
||||
outstream << "\n";
|
||||
indent->resize(indent->size() - 4);
|
||||
outstream << *indent << "]";
|
||||
break;
|
||||
}
|
||||
|
||||
case boost::json::kind::string: {
|
||||
outstream << serialize(json_val.get_string());
|
||||
break;
|
||||
}
|
||||
|
||||
case boost::json::kind::uint64:
|
||||
case boost::json::kind::int64:
|
||||
case boost::json::kind::double_:
|
||||
outstream << json_val;
|
||||
break;
|
||||
|
||||
case boost::json::kind::bool_:
|
||||
if (json_val.get_bool()) {
|
||||
outstream << "true";
|
||||
} else {
|
||||
outstream << "false";
|
||||
}
|
||||
break;
|
||||
|
||||
case boost::json::kind::null:
|
||||
outstream << "null";
|
||||
break;
|
||||
}
|
||||
|
||||
if (indent->empty()) {
|
||||
outstream << "\n";
|
||||
}
|
||||
}
|
||||
|
||||
#endif
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user