update docs

.gitattributes

@@ -1 +1 @@
-archive/** linguist-vendored
+archive/* linguist-vendored

docs/pipeline/README.md

@@ -18,7 +18,6 @@ descriptions via a local GGUF model or a deterministic mock.
   - [Build](#build)
   - [Model](#model)
   - [Run](#run)
-- [Docker / RunPod](#docker--runpod)
 - [Architecture](#architecture)
   - [Pipeline Stages](#pipeline-stages)
   - [Key Components](#key-components)
@@ -52,7 +51,7 @@ step.
 
 ### Build
 
-Requirements: C++20 compiler, CMake 3.31+, OpenSSL, Boost (JSON and
+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.
 
@@ -61,16 +60,6 @@ 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`.
@@ -85,124 +74,33 @@ curl -L \
 ### Run
 
 Run from `build/` so the copied `locations.json` and `prompts/` are available.
-Each run writes a fresh dated SQLite file such as
+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
-./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                                                                                              |
+| Flag            | Purpose                                                 |
-| --------------- | ---------------------------------------------------------------------------------------------------- |
+| --------------- | ------------------------------------------------------- |
-| `--mocked`      | Deterministic mock generator, no model required.                                                     |
+| `--mocked`      | Deterministic mock generator, no model required.        |
-| `--model, -m`   | Path to a GGUF file. Required unless `--mocked` is set.                                              |
+| `--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. |
+| `--temperature` | Sampling temperature. Default: `1.0`.                   |
-| `--output, -o`  | Directory for generated SQLite artifacts. Default: `output`.                                         |
+| `--top-p`       | Nucleus sampling. Default: `0.95`.                      |
-| `--log-path`    | Path for application logs. Default: `pipeline.log`.                                                  |
+| `--top-k`       | Top-k sampling. Default: `64`.                          |
-| `--temperature` | Sampling temperature. Default: `1.0`.                                                                |
+| `--n-ctx`       | Context window size. Default: `8192`.                   |
-| `--top-p`       | Nucleus sampling. Default: `0.95`.                                                                   |
+| `--seed`        | Random seed. Default: `-1` (random at runtime).         |
-| `--top-k`       | Top-k sampling. Default: `64`.                                                                       |
+| `--help, -h`    | Print usage and exit.                                   |
-| `--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.
+editing `prompts/system.md`.
-
----
-
-## 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.
 
 ---
 
@@ -299,18 +197,16 @@ code, latitude, and longitude for each entry.
 ## Tech Stack
 
 - C++20
-- CMake 3.31+
+- CMake 3.24+
 - Boost.JSON, Boost.ProgramOptions, Boost.DI
 - spdlog
-- cpp-httplib (with OpenSSL)
+- libcurl
 - SQLite amalgamation fetched and compiled via CMake FetchContent
-- llama.cpp (auto-detected from system install or fetched via FetchContent)
+- llama.cpp
-- 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
+The build fetches Boost.DI, spdlog, llama.cpp, and SQLite via CMake. Metal is
-only when a system installation is not detected. Metal is enabled on Apple
+enabled on Apple Silicon; CUDA or HIP/ROCm is detected on Linux when the toolkit
-Silicon; CUDA or HIP/ROCm is detected on Linux when the toolkit is present.
+is present.
 
 > **Code Style:** Modern C++20 throughout — RAII for ownership,
 > `std::unique_ptr` for injected dependencies, `std::optional` for parse
@@ -322,7 +218,7 @@ Silicon; CUDA or HIP/ROCm is detected on Linux when the toolkit is present.
 
 ## Tested Hardware
 
-### ARM macOS — M1 Pro
+### ARM macOS - M1 Pro
 
 |           |                                   |
 | --------- | --------------------------------- |
@@ -333,7 +229,7 @@ Silicon; CUDA or HIP/ROCm is detected on Linux when the toolkit is present.
 | Model     | Gemma 4 E4B                       |
 | Inference | llama.cpp with Metal              |
 
-### x86_64 Linux — NVIDIA RTX 2000
+### x86_64 Linux - NVIDIA RTX 2000
 
 |           |                                |
 | --------- | ------------------------------ |
@@ -344,15 +240,6 @@ Silicon; CUDA or HIP/ROCm is detected on Linux when the toolkit is present.
 | 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
@@ -373,9 +260,8 @@ Silicon; CUDA or HIP/ROCm is detected on Linux when the toolkit is present.
 | `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.      |
+| `prompts/`                   | System prompt 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. |
 
 ---
@@ -390,7 +276,6 @@ Silicon; CUDA or HIP/ROCm is detected on Linux when the toolkit is present.
 - `src/data_generation/llama/` — local inference, prompt loading, output
   validation.
 - `src/data_generation/mock/` — deterministic fallback.
-- `tooling/pipeline/runpod/` — container build and runtime launcher.
 
 ---
 

docs/pipeline/diagrams/current/activity.puml

@@ -29,7 +29,7 @@ if (Are arguments valid?) then (no)
 else (yes)
 endif
 
-:Init OpenSSL global state & LlamaBackendState;
+:Init CurlGlobalState & LlamaBackendState;
 :di::make_injector(...);
 :injector.create<std::unique_ptr<BiergartenDataGenerator>>();
 :BiergartenDataGenerator::Run();

docs/pipeline/diagrams/current/class.puml

@@ -52,7 +52,7 @@ interface WebClient <<interface>> {
   + UrlEncode(value : const std::string&) : std::string
 }
 
-class HttpWebClient {
+class CURLWebClient {
   + Get(url : const std::string&) : std::string
   + UrlEncode(value : const std::string&) : std::string
 }
@@ -130,7 +130,7 @@ BiergartenDataGenerator *-- IExportService : owns
 IEnrichmentService <|.. WikipediaService : implements
 WikipediaService *-- WebClient : owns
 
-WebClient <|.. HttpWebClient : implements
+WebClient <|.. CURLWebClient : implements
 
 DataGenerator <|.. MockGenerator : implements
 DataGenerator <|.. LlamaGenerator : implements

docs/pipeline/diagrams/planned/activity.puml

@@ -13,7 +13,7 @@ if (Invalid args?) then (yes)
   stop
 else (no)
 endif
-:Init OpenSSL global state & LlamaBackendState;
+:Init CurlGlobalState & LlamaBackendState;
 :Build DI injector;
 
 :Initialize SqliteExportService;

docs/pipeline/diagrams/planned/class.puml

@@ -356,7 +356,7 @@ package "Infrastructure: Enrichment" {
     + UrlEncode(value : const std::string&) : std::string
   }
 
-  class HttpWebClient {
+  class CURLWebClient {
     + Get(url : const std::string&) : std::string
     + UrlEncode(value : const std::string&) : std::string
   }
@@ -520,7 +520,7 @@ CheckinDistributionStrategy    <|.. RandomCheckinStrategy
 FollowGenerationStrategy       <|.. RandomFollowStrategy
 FollowGenerationStrategy       <|.. ActivityWeightedFollowStrategy
 EnrichmentService              <|.. WikipediaService
-WebClient                      <|.. HttpWebClient
+WebClient                      <|.. CURLWebClient
 DataGenerator                  <|.. MockGenerator
 DataGenerator                  <|.. LlamaGenerator
 PromptFormatter                <|.. Gemma4JinjaPromptFormatter

tooling/pipeline/.dockerignore

@@ -1,9 +0,0 @@
-build/
-cmake-build-debug/
-.git/
-.idea/
-**/*.sqlite
-**/*.log
-**/*.sqlite3
-**/*.db
-

tooling/pipeline/CMakeLists.txt

@@ -1,255 +1,178 @@
-cmake_minimum_required(VERSION 3.31)
+cmake_minimum_required(VERSION 3.24)
 project(biergarten-pipeline)
 
-# Set policy to allow FetchContent_Populate for header-only libraries
+set(CMAKE_POLICY_VERSION_MINIMUM 3.5 CACHE STRING "" FORCE)
-# that have outdated CMakeLists.txt files
-cmake_policy(SET CMP0169 OLD)
 
-# 1. Build Options
+# =============================================================================
-
+# 1. Platform & GPU Detection
-option(BIERGARTEN_MOCK_ONLY "Build with mock data generators only — skips llama.cpp" OFF)
+# =============================================================================
-if(BIERGARTEN_MOCK_ONLY)
+if(WIN32)
-        message(STATUS "[biergarten] MOCK_ONLY build — llama.cpp will not be compiled.")
+    message(FATAL_ERROR "[biergarten] Windows is currently not supported. Please use Linux (Fedora 43) or macOS (M1 Pro).")
-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")
+    if(CMAKE_SYSTEM_PROCESSOR MATCHES "arm64")
-                message(STATUS "[biergarten] Apple Silicon detected — enabling Metal acceleration.")
+        message(STATUS "[biergarten] Apple Silicon detected — enabling Metal acceleration.")
-                set(GGML_METAL ON CACHE BOOL "Enable Metal for Apple Silicon" FORCE)
+        set(GGML_METAL ON CACHE BOOL "Enable Metal for Apple Silicon" FORCE)
-        else()
+    else()
-                message(STATUS "[biergarten] Intel Mac detected — using CPU / Accelerate framework.")
+        message(STATUS "[biergarten] Intel Mac detected — using CPU / Accelerate framework.")
-                set(GGML_METAL OFF CACHE BOOL "Disable Metal for Intel Macs" FORCE)
+        set(GGML_METAL OFF CACHE BOOL "Disable Metal for Intel Macs" FORCE)
-        endif()
+    endif()
-else()
+elseif(UNIX AND NOT APPLE)
-        find_package(CUDAToolkit QUIET)
+    find_package(CUDAToolkit QUIET)
-        find_package(hip CONFIG QUIET)
+    find_package(HIP QUIET)
 
-        if(CUDAToolkit_FOUND)
+    if(CUDAToolkit_FOUND)
-                message(STATUS "[biergarten] NVIDIA GPU detected — enabling CUDA acceleration.")
+        message(STATUS "[biergarten] NVIDIA GPU detected — enabling CUDA acceleration.")
-                set(GGML_CUDA ON CACHE BOOL "Enable CUDA for NVIDIA GPUs" FORCE)
+        set(GGML_CUDA ON CACHE BOOL "Enable CUDA for NVIDIA GPUs" FORCE)
-                set(CMAKE_CUDA_ARCHITECTURES native)
+        set(CMAKE_CUDA_ARCHITECTURES native)
-        elseif(hip_FOUND OR DEFINED ENV{ROCM_PATH} OR EXISTS "/opt/rocm")
+    elseif(HIP_FOUND OR EXISTS "/opt/rocm")
-                message(STATUS "[biergarten] AMD GPU detected — enabling HIP/ROCm acceleration.")
+        message(STATUS "[biergarten] AMD GPU detected — enabling HIP/ROCm acceleration.")
-                set(GGML_HIPBLAS ON CACHE BOOL "Enable HIP for AMD GPUs" FORCE)
+        set(GGML_HIPBLAS ON CACHE BOOL "Enable HIP for AMD GPUs" FORCE)
-        else()
+    else()
-                message(STATUS "[biergarten] No NVIDIA or AMD GPU found — falling back to CPU.")
+        message(STATUS "[biergarten] No NVIDIA or AMD GPU found — falling back to CPU.")
-        endif()
+    endif()
 endif()
 
-# 3. Project-wide Settings
+# =============================================================================
+# 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")
 
-# 4. Dependencies
+# =============================================================================
+# 3. Dependencies
+# =============================================================================
 include(FetchContent)
 
-# Boost (system install — via dnf/brew)
+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)
 
-# 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
+    sqlite_amalgamation
-        GIT_REPOSITORY https://github.com/boost-ext/di.git
+    URL https://www.sqlite.org/2026/sqlite-amalgamation-3530000.zip
-        GIT_TAG v1.3.0
+    URL_HASH SHA3_256=c2325c53b3b41761469f91cfb078e96882ac5d85bac10c11b0bd8f253b031e5b
-        GIT_SHALLOW TRUE
 )
-FetchContent_GetProperties(boost-di)
+FetchContent_GetProperties(sqlite_amalgamation)
-if(NOT boost-di_POPULATED)
+if(NOT sqlite_amalgamation_POPULATED)
-        FetchContent_Populate(boost-di)
+    FetchContent_Populate(sqlite_amalgamation)
 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)
+    add_library(sqlite3 STATIC
-        target_include_directories(sqlite3 PUBLIC ${sqlite_amalgamation_SOURCE_DIR})
+        ${sqlite_amalgamation_SOURCE_DIR}/sqlite3.c
-        target_compile_definitions(sqlite3 PUBLIC SQLITE_THREADSAFE=1)
+    )
+    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
+    llama-cpp
-        GIT_REPOSITORY https://github.com/gabime/spdlog.git
+    GIT_REPOSITORY https://github.com/ggml-org/llama.cpp.git
-        GIT_TAG v1.15.3
+    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)
 
-# cpp-httplib — header-only HTTP/HTTPS client replacing libcurl.
+# =============================================================================
-# OpenSSL is required for HTTPS (Wikipedia API). find_package locates
+# 4. Sources
-# libssl/libcrypto; HTTPLIB_REQUIRE_OPENSSL causes a hard build failure
+# =============================================================================
-# if OpenSSL is absent rather than silently producing an HTTP-only binary.
+set(SOURCES
-find_package(OpenSSL REQUIRED)
+    src/main.cc
-FetchContent_Declare(
+    src/biergarten_data_generator/biergarten_data_generator.cc
-        cpp-httplib
+    src/biergarten_data_generator/run.cc
-        GIT_REPOSITORY https://github.com/yhirose/cpp-httplib.git
+    src/biergarten_data_generator/query_cities_with_countries.cc
-        GIT_TAG v0.43.2
+    src/biergarten_data_generator/generate_breweries.cc
-        GIT_SHALLOW TRUE
+    src/biergarten_data_generator/log_results.cc
-        SYSTEM
+    src/services/wikipedia/wikipedia_service.cc
-)
+    src/services/wikipedia/get_summary.cc
-set(HTTPLIB_REQUIRE_OPENSSL ON CACHE BOOL "Require OpenSSL for cpp-httplib" FORCE)
+    src/services/wikipedia/fetch_extract.cc
-FetchContent_MakeAvailable(cpp-httplib)
+    src/services/sqlite/sqlite_export_service.cc
-
+    src/services/sqlite/build_database_path.cc
-# 5. Executable & Sources
+    src/services/sqlite/process_record.cc
-add_executable(${PROJECT_NAME}
+    src/services/sqlite/initialize.cc
-        includes/services/enrichment/mock_enrichment.h)
+    src/services/sqlite/finalize.cc
-
+    src/web_client/curl_global_state.cc
-# --- Entry point ---
+    src/web_client/curl_web_client_get.cc
-target_sources(${PROJECT_NAME} PRIVATE
+    src/web_client/curl_web_client_url_encode.cc
-        src/main.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/services/prompt_directory.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
+    src/services/sqlite/helpers/sqlite_connection_helpers.cpp
+    src/services/sqlite/helpers/sqlite_statement_helpers.cpp
 )
 
-# --- json_handling ---
+# =============================================================================
-target_sources(${PROJECT_NAME} PRIVATE
+# 5. Target
-        src/json_handling/json_loader.cc
+# =============================================================================
-)
+add_executable(${PROJECT_NAME} ${SOURCES})
-
-# --- application_options ---
-target_sources(${PROJECT_NAME} PRIVATE
-        src/application_options/parse_arguments.cc
-)
-
-# --- biergarten_data_generator ---
-target_sources(${PROJECT_NAME} PRIVATE
-        src/biergarten_data_generator/log_results.cc
-        src/biergarten_data_generator/biergarten_data_generator.cc
-        src/biergarten_data_generator/generate_breweries.cc
-        src/biergarten_data_generator/run.cc
-        src/biergarten_data_generator/query_cities_with_countries.cc
-)
-
-# --- web_client ---
-target_sources(${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(${PROJECT_NAME} PRIVATE
-        src/services/sqlite/process_record.cc
-        src/services/sqlite/sqlite_export_service.cc
-        src/services/sqlite/finalize.cc
-        src/services/sqlite/initialize.cc
-        src/services/sqlite/helpers/sqlite_connection_helpers.cc
-        src/services/sqlite/helpers/sqlite_statement_helpers.cc
-)
-
-# --- services (top-level) ---
-target_sources(${PROJECT_NAME} PRIVATE
-        src/services/prompt_directory.cc
-)
-
-# 6. Include Directories, Link Libraries & Compile Definitions
 target_include_directories(${PROJECT_NAME} PRIVATE
-        includes
+    includes
+    ${llama-cpp_SOURCE_DIR}/include
+    ${llama-cpp_SOURCE_DIR}/common
 )
-
 target_link_libraries(${PROJECT_NAME} PRIVATE
-        $<$<NOT:$<BOOL:${BIERGARTEN_MOCK_ONLY}>>:llama>
+    llama
-        boost::di
+    boost::di
-        Boost::json
+    Boost::json
-        Boost::program_options
+    Boost::program_options
-        spdlog::spdlog
+    spdlog::spdlog
-        sqlite3
+    sqlite3
-        httplib::httplib
+    CURL::libcurl
-        OpenSSL::SSL
-        OpenSSL::Crypto
 )
 
-target_compile_definitions(${PROJECT_NAME} PRIVATE
+# =============================================================================
-        # Defined when -DBIERGARTEN_MOCK_ONLY=ON — skips llama.cpp entirely.
+# 6. Runtime Assets
-        # 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>
-)
-
-# 7. Runtime Assets
 configure_file(
-        ${CMAKE_SOURCE_DIR}/locations.json
+    ${CMAKE_SOURCE_DIR}/locations.json
-        ${CMAKE_BINARY_DIR}/locations.json
+    ${CMAKE_BINARY_DIR}/locations.json
-        COPYONLY
+    COPYONLY
 )
+
 add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD
-        COMMAND ${CMAKE_COMMAND} -E copy_directory
+    COMMAND ${CMAKE_COMMAND} -E copy_directory
-        ${CMAKE_SOURCE_DIR}/prompts
+    ${CMAKE_SOURCE_DIR}/prompts
-        ${CMAKE_BINARY_DIR}/prompts
+    ${CMAKE_BINARY_DIR}/prompts
 )

tooling/pipeline/includes/biergarten_data_generator.h

@@ -11,9 +11,11 @@
 #include <vector>
 
 #include "data_generation/data_generator.h"
-#include "data_model/generated_models.h"
+#include "data_model/enriched_city.h"
-#include "services/database/export_service.h"
+#include "data_model/generated_brewery.h"
-#include "services/enrichment/enrichment_service.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.
@@ -32,8 +34,7 @@ class BiergartenDataGenerator {
    */
   BiergartenDataGenerator(std::unique_ptr<IEnrichmentService> context_service,
                           std::unique_ptr<DataGenerator> generator,
-                          std::unique_ptr<IExportService> exporter,
+                          std::unique_ptr<IExportService> exporter);
-                          const ApplicationOptions& application_options);
 
   /**
    * @brief Run the data generation pipeline.
@@ -57,14 +58,12 @@ class BiergartenDataGenerator {
   /// @brief Storage backend for generated brewery records.
   std::unique_ptr<IExportService> exporter_;
 
-  const ApplicationOptions application_options_;
-
   /**
    * @brief Load locations from JSON and sample cities.
    *
    * @return Vector of sampled locations capped at 50 entries.
    */
-  std::vector<Location> QueryCitiesWithCountries();
+  static std::vector<Location> QueryCitiesWithCountries();
 
   /**
    * @brief Generate breweries for enriched cities.

tooling/pipeline/includes/data_generation/data_generator.h

@@ -8,7 +8,9 @@
 
 #include <string>
 
-#include "data_model/generated_models.h"
+#include "data_model/brewery_result.h"
+#include "data_model/location.h"
+#include "data_model/user_result.h"
 
 /**
  * @brief Interface for data generator implementations.

tooling/pipeline/includes/data_generation/llama_generator.h

@@ -14,10 +14,10 @@
 #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/models.h"
+#include "data_model/application_options.h"
+#include "services/prompt_directory.h"
 
 struct llama_model;
 struct llama_context;
@@ -129,7 +129,6 @@ class LlamaGenerator final : public DataGenerator {
   uint32_t sampling_top_k_ = kDefaultSamplingTopK;
   std::mt19937 rng_;
   uint32_t n_ctx_ = kDefaultContextSize;
-  int n_gpu_layers_ = 0;
   std::unique_ptr<IPromptFormatter> prompt_formatter_;
   std::unique_ptr<IPromptDirectory> prompt_directory_;
 };

tooling/pipeline/includes/data_generation/llama_generator_helpers.h

@@ -12,7 +12,7 @@
 #include <string>
 #include <string_view>
 
-#include "data_model/generated_models.h"
+#include "data_model/brewery_result.h"
 
 struct llama_vocab;
 using llama_token = int32_t;

tooling/pipeline/includes/data_generation/prompt_formatting/gemma4_jinja_prompt_formatter.h

@@ -1,5 +1,4 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_GEMMA4_JINJA_PROMPT_FORMATTER_H_
+#pragma once
-#define BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_GEMMA4_JINJA_PROMPT_FORMATTER_H_
 
 #include <string>
 #include <string_view>
@@ -14,5 +13,3 @@ 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_

tooling/pipeline/includes/data_generation/prompt_formatting/prompt_formatter.h

@@ -1,5 +1,4 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_PROMPT_FORMATTER_H_
+#pragma once
-#define BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_PROMPT_FORMATTER_H_
 
 #include <string>
 #include <string_view>
@@ -16,5 +15,3 @@ 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_

tooling/pipeline/includes/data_model/application_options.h

@@ -0,0 +1,72 @@
+#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 <filesystem>
+#include <optional>
+#include <string>
+
+/**
+ * @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 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 Root configuration object for the Biergarten pipeline.
+ */
+struct ApplicationOptions {
+  GeneratorOptions generator;
+  PipelineOptions pipeline;
+};
+
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_APPLICATION_OPTIONS_H_

tooling/pipeline/includes/data_model/brewery_location.h

@@ -0,0 +1,22 @@
+#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_

tooling/pipeline/includes/data_model/brewery_result.h

@@ -0,0 +1,28 @@
+#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_

tooling/pipeline/includes/data_model/enriched_city.h

@@ -0,0 +1,21 @@
+#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_

tooling/pipeline/includes/data_model/generated_brewery.h

@@ -0,0 +1,20 @@
+#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_

tooling/pipeline/includes/data_model/generated_models.h

@@ -1,66 +0,0 @@
-#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_

tooling/pipeline/includes/data_model/generation_models.h

@@ -0,0 +1,13 @@
+#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_

tooling/pipeline/includes/data_model/location.h

@@ -0,0 +1,41 @@
+#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_

tooling/pipeline/includes/data_model/models.h

@@ -1,141 +0,0 @@
-#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 <optional>
-#include <string>
-#include <string_view>
-#include <vector>
-
-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);
-
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_MODELS_H_

tooling/pipeline/includes/data_model/pipeline_models.h

@@ -0,0 +1,12 @@
+#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_

tooling/pipeline/includes/data_model/user_result.h

@@ -0,0 +1,22 @@
+#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_

tooling/pipeline/includes/json_handling/json_loader.h

@@ -9,7 +9,7 @@
 #include <filesystem>
 #include <vector>
 
-#include "data_model/models.h"
+#include "data_model/location.h"
 
 /// @brief Loads curated world locations from a JSON file into memory.
 class JsonLoader {

tooling/pipeline/includes/services/database/sqlite_export_service_helpers.h

@@ -1,10 +0,0 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_EXPORT_SERVICE_HELPERS_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_EXPORT_SERVICE_HELPERS_H_
-
-/* Umbrella header for backward compatibility. */
-
-#include "sqlite_connection_helpers.h"
-#include "sqlite_handle_types.h"
-#include "sqlite_statement_helpers.h"
-
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_EXPORT_SERVICE_HELPERS_H_

tooling/pipeline/includes/services/date_time_provider.h

@@ -1,5 +1,5 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATETIME_DATE_TIME_PROVIDER_H_
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATE_TIME_PROVIDER_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATETIME_DATE_TIME_PROVIDER_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATE_TIME_PROVIDER_H_
 
 /**
  * @file services/date_time_provider.h
@@ -63,4 +63,4 @@ class SystemDateTimeProvider final : public IDateTimeProvider {
   }
 };
 
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATETIME_DATE_TIME_PROVIDER_H_
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATE_TIME_PROVIDER_H_

tooling/pipeline/includes/services/datetime/timer.h

@@ -1,35 +0,0 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATETIME_TIMER_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATETIME_TIMER_H_
-
-#include <chrono>
-
-/**
- * @file services/timer.h
- * @brief Simple timer utility for measuring elapsed time.
- */
-class Timer {
-  std::chrono::steady_clock::time_point start_time =
-      std::chrono::steady_clock::now();
-
- public:
-  Timer(const Timer&) = delete;
-  Timer& operator=(const Timer&) = delete;
-  Timer(Timer&&) = delete;
-  Timer& operator=(Timer&&) = delete;
-  Timer() = default;
-  ~Timer() = default;
-
-  [[nodiscard]] int64_t Elapsed() const {
-    return std::chrono::duration_cast<std::chrono::milliseconds>(
-               std::chrono::steady_clock::now() - start_time)
-        .count();
-  }
-
-  [[nodiscard]] int64_t Reset() {
-    auto previous_elapsed = Elapsed();
-    start_time = std::chrono::steady_clock::now();
-    return previous_elapsed;
-  }
-};
-
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATETIME_TIMER_H_

tooling/pipeline/includes/services/enrichment/mock_enrichment.h

@@ -1,17 +0,0 @@
-//
-// Created by aaronpo on 13/05/2026.
-//
-
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_MOCK_ENRICHMENT_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_MOCK_ENRICHMENT_H_
-#include <string>
-
-#include "enrichment_service.h"
-
-class MockEnrichmentService final : public IEnrichmentService {
- public:
-  std::string GetLocationContext(const Location& /*loc*/) override {
-    return {};
-  }
-};
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_MOCK_ENRICHMENT_H_

tooling/pipeline/includes/services/enrichment_service.h

@@ -1,5 +1,5 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_ENRICHMENT_SERVICE_H_
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_SERVICE_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_ENRICHMENT_SERVICE_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_SERVICE_H_
 
 /**
  * @file services/enrichment_service.h
@@ -8,7 +8,7 @@
 
 #include <string>
 
-#include "data_model/models.h"
+#include "data_model/location.h"
 
 /**
  * @brief Interface for services that can enrich a location with context.
@@ -27,4 +27,4 @@ class IEnrichmentService {
   virtual std::string GetLocationContext(const Location& loc) = 0;
 };
 
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_ENRICHMENT_SERVICE_H_
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_SERVICE_H_

tooling/pipeline/includes/services/export_service.h

@@ -1,5 +1,5 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_EXPORT_SERVICE_H_
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_EXPORT_SERVICE_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_EXPORT_SERVICE_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_EXPORT_SERVICE_H_
 
 /**
  * @file services/export_service.h
@@ -8,7 +8,7 @@
 
 #include <cstdint>
 
-#include "data_model/generated_models.h"
+#include "data_model/generated_brewery.h"
 
 /**
  * @brief Interface for services that persist generated brewery records.
@@ -39,4 +39,4 @@ class IExportService {
   virtual void Finalize() = 0;
 };
 
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_EXPORT_SERVICE_H_
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_EXPORT_SERVICE_H_

tooling/pipeline/includes/services/prompt_directory.h

@@ -1,5 +1,5 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_PROMPTING_PROMPT_DIRECTORY_H_
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_PROMPT_DIRECTORY_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_PROMPTING_PROMPT_DIRECTORY_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_PROMPT_DIRECTORY_H_
 
 /**
  * @file services/prompt_directory.h
@@ -73,4 +73,4 @@ class PromptDirectory final : public IPromptDirectory {
   std::unordered_map<std::string, std::string> cache_;
 };
 
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_PROMPTING_PROMPT_DIRECTORY_H_
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_PROMPT_DIRECTORY_H_

tooling/pipeline/includes/services/sqlite_connection_helpers.h

@@ -1,5 +1,5 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_CONNECTION_HELPERS_H_
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_CONNECTION_HELPERS_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_CONNECTION_HELPERS_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_CONNECTION_HELPERS_H_
 
 /**
  * @file services/sqlite_connection_helpers.h
@@ -12,7 +12,7 @@
 #include <string>
 #include <string_view>
 
-#include "sqlite_handle_types.h"
+#include "services/sqlite_handle_types.h"
 
 namespace sqlite_export_service_internal {
 
@@ -27,4 +27,4 @@ void RollbackTransactionNoThrow(const SqliteDatabaseHandle& db_handle) noexcept;
 
 }  // namespace sqlite_export_service_internal
 
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_CONNECTION_HELPERS_H_
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_CONNECTION_HELPERS_H_

tooling/pipeline/includes/services/sqlite_export_service.h

@@ -1,5 +1,5 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_EXPORT_SERVICE_H_
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_EXPORT_SERVICE_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_EXPORT_SERVICE_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_EXPORT_SERVICE_H_
 
 /**
  * @file services/sqlite_export_service.h
@@ -11,10 +11,10 @@
 #include <string>
 #include <unordered_map>
 
-#include "data_model/models.h"
+#include "data_model/application_options.h"
-#include "../datetime/date_time_provider.h"
+#include "services/date_time_provider.h"
-#include "export_service.h"
+#include "services/export_service.h"
-#include "sqlite_export_service_helpers.h"
+#include "services/sqlite_export_service_helpers.h"
 
 /**
  * @brief Persists generated brewery records into a fresh SQLite database.
@@ -57,4 +57,4 @@ class SqliteExportService final : public IExportService {
   std::unordered_map<std::string, sqlite3_int64> location_cache_;
 };
 
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_EXPORT_SERVICE_H_
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_EXPORT_SERVICE_H_

tooling/pipeline/includes/services/sqlite_export_service_helpers.h

@@ -0,0 +1,10 @@
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_EXPORT_SERVICE_HELPERS_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_EXPORT_SERVICE_HELPERS_H_
+
+/* Umbrella header for backward compatibility. */
+
+#include "services/sqlite_connection_helpers.h"
+#include "services/sqlite_handle_types.h"
+#include "services/sqlite_statement_helpers.h"
+
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_EXPORT_SERVICE_HELPERS_H_

tooling/pipeline/includes/services/sqlite_handle_types.h

@@ -1,5 +1,5 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_HANDLE_TYPES_H_
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_HANDLE_TYPES_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_HANDLE_TYPES_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_HANDLE_TYPES_H_
 
 /**
  * Shared handle and parameter type declarations used by SQLite helper units.
@@ -33,4 +33,4 @@ struct BindParam {
 
 }  // namespace sqlite_export_service_internal
 
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_HANDLE_TYPES_H_
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_HANDLE_TYPES_H_

tooling/pipeline/includes/services/sqlite_statement_helpers.h

@@ -1,5 +1,5 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_STATEMENT_HELPERS_H_
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_STATEMENT_HELPERS_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_STATEMENT_HELPERS_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_STATEMENT_HELPERS_H_
 
 /**
  * @file services/sqlite_statement_helpers.h
@@ -13,7 +13,7 @@
 #include <string_view>
 #include <vector>
 
-#include "sqlite_handle_types.h"
+#include "services/sqlite_handle_types.h"
 
 namespace sqlite_export_service_internal {
 
@@ -113,4 +113,4 @@ std::string SerializeVector(const std::vector<std::string>& str_vec);
 
 }  // namespace sqlite_export_service_internal
 
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_STATEMENT_HELPERS_H_
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_STATEMENT_HELPERS_H_

tooling/pipeline/includes/services/wikipedia_service.h

@@ -1,5 +1,5 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_WIKIPEDIA_SERVICE_H_
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_WIKIPEDIA_SERVICE_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_WIKIPEDIA_SERVICE_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_WIKIPEDIA_SERVICE_H_
 
 /**
  * @file services/wikipedia_service.h
@@ -11,14 +11,14 @@
 #include <string_view>
 #include <unordered_map>
 
-#include "enrichment_service.h"
+#include "services/enrichment_service.h"
 #include "web_client/web_client.h"
 
 /// @brief Provides Wikipedia summary lookups backed by cached raw extracts.
-class WikipediaEnrichmentService final : public IEnrichmentService {
+class WikipediaService final : public IEnrichmentService {
  public:
   /// @brief Creates a new Wikipedia service with the provided web client.
-  explicit WikipediaEnrichmentService(std::unique_ptr<WebClient> client);
+  explicit WikipediaService(std::unique_ptr<WebClient> client);
 
   /// @brief Returns the Wikipedia-derived context for a location.
   [[nodiscard]] std::string GetLocationContext(const Location& loc) override;
@@ -30,4 +30,4 @@ class WikipediaEnrichmentService final : public IEnrichmentService {
   std::unordered_map<std::string, std::string> extract_cache_;
 };
 
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_WIKIPEDIA_SERVICE_H_
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_WIKIPEDIA_SERVICE_H_

tooling/pipeline/includes/web_client/curl_web_client.h

@@ -0,0 +1,54 @@
+#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_

tooling/pipeline/includes/web_client/http_web_client.h

@@ -1,49 +0,0 @@
-/**
-* @file web_client/http_web_client.h
-* @brief cpp-httplib implementation of the WebClient interface.
-*/
-
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_HTTP_WEB_CLIENT_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_HTTP_WEB_CLIENT_H_
-
-
-#include "web_client/web_client.h"
-
-#include <string>
-
-/**
- * @brief WebClient implementation backed by cpp-httplib.
- *
- * Supports HTTP and HTTPS (requires OpenSSL; see HTTPLIB_REQUIRE_OPENSSL
- * in CMakeLists.txt).
- *
- * URL parsing splits a full URL into origin (scheme://host[:port]) and
- * path + query so that httplib::Client can be constructed correctly.
- * A new client instance is created per request because the client is
- * bound to a single origin at construction time.
- */
-class HttpWebClient final : public WebClient {
-public:
-  HttpWebClient() = default;
-  ~HttpWebClient() override = default;
-
-  /**
-   * @brief Executes a blocking HTTP/HTTPS GET request against a full URL.
-   *
-   * @param url Fully-qualified URL, e.g. "https://en.wikipedia.org/api/rest_v1/page/summary/Berlin"
-   * @return Response body on HTTP 2xx; throws std::runtime_error otherwise.
-   */
-  std::string Get(const std::string& url) override;
-
-  /**
-   * @brief Percent-encodes a single URI component (query parameter value or
-   *        path segment). Delegates to httplib::encode_uri_component().
-   *
-   * @param value Raw string to encode.
-   * @return Percent-encoded string safe for use in a URL.
-   */
-  std::string EncodeURL(const std::string& value) override;
-};
-
-
-#endif

tooling/pipeline/includes/web_client/web_client.h

@@ -30,7 +30,7 @@ class WebClient {
    * @param value Raw string value.
    * @return Encoded value safe for URL usage.
    */
-  virtual std::string EncodeURL(const std::string& value) = 0;
+  virtual std::string UrlEncode(const std::string& value) = 0;
 };
 
 #endif  // BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_WEB_CLIENT_H_

tooling/pipeline/runpod/.dockerignore

@@ -1,9 +0,0 @@
-# Ignore model files!
-*.gguf
-*.bin
-models/
-weights/
-
-# Ignore local build folders
-build/
-.git/

tooling/pipeline/runpod/Dockerfile

@@ -1,72 +0,0 @@
-# --- Stage 1: Build Environment (The "Heavy" Stage) ---
-FROM nvidia/cuda:12.6.3-devel-ubuntu24.04 AS builder
-
-ENV DEBIAN_FRONTEND=noninteractive \
-  CMAKE_GENERATOR=Ninja
-
-RUN apt-get update && apt-get install -y --no-install-recommends \
-  build-essential ca-certificates curl git libboost-json-dev \
-  libboost-program-options-dev libssl-dev ninja-build pkg-config zlib1g-dev \
-  && rm -rf /var/lib/apt/lists/*
-
-# Install modern CMake
-RUN curl -L https://github.com/Kitware/CMake/releases/download/v3.31.0/cmake-3.31.0-linux-x86_64.sh -o cmake.sh && \
-  sh cmake.sh --skip-license --prefix=/usr/local && rm cmake.sh
-
-# Get headers for C++ build
-RUN curl -L https://github.com/ggml-org/llama.cpp/archive/refs/tags/b9012.tar.gz -o /tmp/llama-src.tar.gz && \
-  tar -xzf /tmp/llama-src.tar.gz -C /tmp && \
-  cp -r /tmp/llama.cpp-b9012/include/* /usr/local/include/ && \
-  cp -r /tmp/llama.cpp-b9012/ggml/include/* /usr/local/include/
-
-# Pull llama.cpp binaries to use during build if needed
-COPY --from=ghcr.io/ggml-org/llama.cpp:full-cuda /app/lib*.so* /usr/local/lib/
-
-WORKDIR /app
-COPY . .
-
-# Build the C++ pipeline
-RUN cmake -S . -B build -G Ninja -DCMAKE_BUILD_TYPE=Release && \
-  cmake --build build -j$(nproc)
-
-# --- Stage 2: Runtime Environment (The "Slim" Stage) ---
-FROM nvidia/cuda:12.6.3-runtime-ubuntu24.04 AS runtime
-
-# Install only necessary runtime shared libraries
-RUN apt-get update && apt-get install -y --no-install-recommends \
-  curl \
-  ca-certificates \
-  libboost-json1.83.0 \
-  libboost-program-options1.83.0 \
-  libgomp1 \
-  libssl3 \
-  zlib1g \
-  && rm -rf /var/lib/apt/lists/*
-
-ENV APP_ROOT=/app \
-  LD_LIBRARY_PATH="/usr/local/lib:${LD_LIBRARY_PATH}"
-
-WORKDIR /app/build
-
-# Copy only the compiled binaries from the builder
-COPY --from=builder /app/build/biergarten-pipeline ./
-
-# Copy required config files
-COPY locations.json /app/build/
-COPY beer-styles.json /app/build/
-
-# Copy prompt templates
-COPY prompts /app/prompts
-
-# Copy only the necessary shared libraries from builder/llama-bin
-COPY --from=ghcr.io/ggml-org/llama.cpp:full-cuda /app/lib*.so* /usr/local/lib/
-
-# Co-locate plugins
-RUN cp /usr/local/lib/libggml-cuda.so . 2>/dev/null || true && \
-  cp /usr/local/lib/libggml-cpu*.so . 2>/dev/null || true
-
-# Setup Start Script
-COPY ./runpod/start.sh /usr/local/bin/biergarten-start
-RUN chmod +x /usr/local/bin/biergarten-start
-
-ENTRYPOINT ["/usr/local/bin/biergarten-start"]

tooling/pipeline/runpod/README.md

@@ -1,8 +0,0 @@
-```bash
-touch runpod/start.sh
-docker build \
- --progress=plain \
- -t biergarten-pipeline:latest \
- -f runpod/Dockerfile \
- . 2>&1 | tee build.log
-```

tooling/pipeline/runpod/pod-template.yaml

@@ -1,22 +0,0 @@
-name: biergarten-pipeline-live
-imageName: biergarten-pipeline:latest
-category: NVIDIA
-containerDiskInGb: 50
-volumeInGb: 50
-volumeMountPath: /workspace
-dockerEntrypoint:
-  - /usr/local/bin/biergarten-start
-dockerStartCmd: []
-isPublic: false
-isServerless: false
-env:
-  BIERGARTEN_MODE: live
-  BIERGARTEN_MODEL_PATH: /workspace/models/google_gemma-4-E4B-it-Q6_K.gguf
-  BIERGARTEN_PROMPT_DIR: /workspace/app/build/prompts
-  BIERGARTEN_OUTPUT_DIR: /workspace/output
-  BIERGARTEN_LOG_PATH: /workspace/logs/pipeline.log
-  BIERGARTEN_TEMPERATURE: "1.0"
-  BIERGARTEN_TOP_P: "0.95"
-  BIERGARTEN_TOP_K: "64"
-  BIERGARTEN_N_CTX: "8192"
-  BIERGARTEN_SEED: "-1"

tooling/pipeline/runpod/start.sh

@@ -1,58 +0,0 @@
-#!/bin/bash
-set -e
-
-MODEL_PATH="${BIERGARTEN_MODEL_PATH:-/workspace/models/google_gemma-4-E4B-it-Q6_K.gguf}"
-OUTPUT_DIR="${BIERGARTEN_OUTPUT_DIR:-/workspace/output}"
-LOG_PATH="${BIERGARTEN_LOG_PATH:-/workspace/logs/pipeline.log}"
-EXECUTABLE="/app/build/biergarten-pipeline"
-PROMPT_DIR="/app/prompts"
-
-echo "--- Starting Biergarten Pipeline Environment Check ---"
-
-# Ensure directories exist
-mkdir -p "$OUTPUT_DIR"
-mkdir -p "$(dirname "$LOG_PATH")"
-mkdir -p "$(dirname "$MODEL_PATH")"
-
-# Download model if missing
-if [ ! -f "$MODEL_PATH" ]; then
-    echo "Model not found. Downloading (this may take a while)..."
-
-    curl -L -C - \
-      -o "$MODEL_PATH" \
-      "https://huggingface.co/bartowski/google_gemma-4-E4B-it-GGUF/resolve/main/google_gemma-4-E4B-it-Q6_K.gguf?download=true"
-
-    echo "Download complete."
-fi
-
-# Verify model exists
-if [ ! -f "$MODEL_PATH" ]; then
-    echo "ERROR: Model still not found after download attempt."
-    exit 1
-fi
-
-# Default GPU layers
-GL_LAYERS="${BIERGARTEN_GL_LAYERS:-40}"
-
-# Build args
-ARGS=(
-    "--model"      "$MODEL_PATH"
-    "--prompt-dir" "$PROMPT_DIR"
-    "--output"     "$OUTPUT_DIR"
-    "--log-path"   "$LOG_PATH"
-    "--n-gpu-layers" "$GL_LAYERS"
-)
-
-# Optional params
-[[ -n "$BIERGARTEN_TEMPERATURE" ]] && ARGS+=("--temperature"  "$BIERGARTEN_TEMPERATURE")
-[[ -n "$BIERGARTEN_TOP_P" ]]       && ARGS+=("--top-p"        "$BIERGARTEN_TOP_P")
-[[ -n "$BIERGARTEN_TOP_K" ]]       && ARGS+=("--top-k"        "$BIERGARTEN_TOP_K")
-[[ -n "$BIERGARTEN_N_CTX" ]]       && ARGS+=("--n-ctx"        "$BIERGARTEN_N_CTX")
-[[ -n "$BIERGARTEN_SEED" ]]        && ARGS+=("--seed"         "$BIERGARTEN_SEED")
-
-# Extra args
-[[ -n "$BIERGARTEN_EXTRA_ARGS" ]] && ARGS+=($BIERGARTEN_EXTRA_ARGS)
-
-echo "--- Executing: $EXECUTABLE ${ARGS[*]} ---"
-
-exec "$EXECUTABLE" "${ARGS[@]}"

tooling/pipeline/src/application_options/parse_arguments.cc

@@ -1,158 +0,0 @@
-#include <spdlog/spdlog.h>
-
-#include <optional>
-#include <sstream>
-#include <string>
-
-#include "data_model/models.h"
-
-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");
-
-  // Defaults sourced from SamplingOptions{} so the CLI and LlamaGenerator
-  // share a single source of truth — changing the struct updates both.
-  auto add_sampling_options = [&]() -> void {
-    const SamplingOptions sampling_defaults{};
-    opt("temperature",
-        prog_opts::value<float>()->default_value(sampling_defaults.temperature),
-        "Sampling temperature (higher = more random)");
-    opt("top-p",
-        prog_opts::value<float>()->default_value(sampling_defaults.top_p),
-        "Nucleus sampling top-p in (0,1] (higher = more random)");
-    opt("top-k",
-        prog_opts::value<uint32_t>()->default_value(sampling_defaults.top_k),
-        "Top-k sampling parameter (higher = more candidate tokens)");
-    opt("n-ctx",
-        prog_opts::value<uint32_t>()->default_value(sampling_defaults.n_ctx),
-        "Context window size in tokens");
-    opt("seed", prog_opts::value<int>()->default_value(sampling_defaults.seed),
-        "Sampler seed: -1 for random, otherwise non-negative integer");
-    opt("n-gpu-layers", prog_opts::value<int>()->default_value(0),
-        "Number of layers to offload to GPU");
-  };
-
-  // --mocked and --model are mutually exclusive; validation is enforced below
-  // rather than at registration to produce a clear diagnostic message.
-  auto add_generator_options = [&]() -> void {
-    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)");
-  };
-
-  auto add_pipeline_options = [&]() -> void {
-    opt("output,o", prog_opts::value<std::string>()->default_value("output"),
-        "Directory for generated artifacts");
-    opt("log-path",
-        prog_opts::value<std::string>()->default_value("pipeline.log"),
-        "Path for application logs");
-    opt("prompt-dir", prog_opts::value<std::string>()->default_value(""),
-        "Directory containing named prompt files (e.g. BREWERY_GENERATION.md)."
-        " Required when not using --mocked.");
-    opt("location-count", prog_opts::value<uint32_t>()->default_value(10));
-  };
-
-  add_sampling_options();
-  add_generator_options();
-  add_pipeline_options();
-
-  // No flags provided — treat as a help request rather than an error.
-  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 var_map;
-    prog_opts::store(prog_opts::parse_command_line(argc, argv, desc), var_map);
-    prog_opts::notify(var_map);
-
-    if (var_map.contains("help")) {
-      std::stringstream help_stream;
-      help_stream << "\n" << desc;
-      spdlog::info(help_stream.str());
-      return std::nullopt;
-    }
-
-    ApplicationOptions options;
-
-    options.pipeline.output_path = var_map["output"].as<std::string>();
-    options.pipeline.log_path = var_map["log-path"].as<std::string>();
-    options.pipeline.prompt_dir = var_map["prompt-dir"].as<std::string>();
-    options.pipeline.location_count =
-      var_map["location-count"].as<uint32_t>();
-
-    const bool use_mocked = var_map["mocked"].as<bool>();
-    const std::string model_path = var_map["model"].as<std::string>();
-    const int n_gpu_layers = var_map["n-gpu-layers"].as<int>();
-
-    // Enforce mutual exclusivity before any further configuration is applied.
-    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;
-    }
-
-    // Prompt directory is only meaningful for live inference — the mock
-    // generator has no use for it and should not require it to be present.
-    if (!use_mocked && options.pipeline.prompt_dir.empty()) {
-      spdlog::error(
-          "Invalid arguments: --prompt-dir is required when not using "
-          "--mocked");
-      return std::nullopt;
-    }
-
-    options.generator.use_mocked = use_mocked;
-    options.generator.model_path = model_path;
-    // options.generator.n_gpu_layers = n_gpu_layers;
-
-    // Only populate sampling config when the user explicitly overrides at
-    // least one value. Leaving it as std::nullopt lets LlamaGenerator fall
-    // back to its own SamplingOptions{} defaults, keeping the two paths
-    // consistent without redundant copies.
-    const bool user_provided_sampling =
-        !var_map["temperature"].defaulted() || !var_map["top-p"].defaulted() ||
-        !var_map["top-k"].defaulted() || !var_map["n-ctx"].defaulted() ||
-        !var_map["seed"].defaulted() || !var_map["n_gpu_layers"].defaulted();
-
-    if (user_provided_sampling) {
-      // Warn but do not fail — the run is still valid, the flags are just
-      // silently irrelevant when no model is loaded.
-      if (use_mocked) {
-        spdlog::warn("Sampling parameters are ignored when using --mocked");
-      } else {
-        SamplingOptions sampling;
-        sampling.temperature = var_map["temperature"].as<float>();
-        sampling.top_p = var_map["top-p"].as<float>();
-        sampling.top_k = var_map["top-k"].as<uint32_t>();
-        sampling.n_ctx = var_map["n-ctx"].as<uint32_t>();
-        sampling.seed = var_map["seed"].as<int>();
-        sampling.n_gpu_layers = var_map["n-gpu-layers"].as<int>();
-
-        options.generator.sampling = sampling;
-      }
-    }
-
-    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;
-  }
-}

tooling/pipeline/src/biergarten_data_generator/biergarten_data_generator.cc

@@ -10,9 +10,7 @@
 BiergartenDataGenerator::BiergartenDataGenerator(
     std::unique_ptr<IEnrichmentService> context_service,
     std::unique_ptr<DataGenerator> generator,
-    std::unique_ptr<IExportService> exporter,
+    std::unique_ptr<IExportService> exporter)
-    const ApplicationOptions &app_options)
     : context_service_(std::move(context_service)),
       generator_(std::move(generator)),
-      exporter_(std::move(exporter)),
+      exporter_(std::move(exporter)) {}
-      application_options_(app_options) {}

tooling/pipeline/src/biergarten_data_generator/query_cities_with_countries.cc

@@ -13,6 +13,8 @@
 #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 ===");
 
@@ -21,9 +23,7 @@ std::vector<Location> BiergartenDataGenerator::QueryCitiesWithCountries() {
   auto all_locations = JsonLoader::LoadLocations(locations_path);
   spdlog::info("  Locations available: {}", all_locations.size());
 
-  const size_t sample_count = std::min(
+  const size_t sample_count = std::min(kBreweryAmount, all_locations.size());
-      static_cast<size_t>(application_options_.pipeline.location_count),
-      all_locations.size());
 
   const auto sample_count_signed =
       static_cast<std::iter_difference_t<decltype(all_locations.cbegin())>>(

tooling/pipeline/src/biergarten_data_generator/run.cc

@@ -21,8 +21,8 @@ bool BiergartenDataGenerator::Run() {
     for (auto& city : cities) {
       try {
         std::string region_context = context_service_->GetLocationContext(city);
-        // spdlog::debug("[Pipeline] Context for '{}' ({}) gathered:\n{}",
+        spdlog::debug("[Pipeline] Context for '{}' ({}) gathered:\n{}",
-        //               city.city, city.iso3166_2, region_context);
+                      city.city, city.country, region_context);
 
         enriched.push_back(
             EnrichedCity{.location = std::move(city),

tooling/pipeline/src/data_generation/llama/llama_generator.cc

@@ -11,7 +11,7 @@
 #include <stdexcept>
 #include <string>
 
-#include "data_model/models.h"
+#include "data_model/application_options.h"
 #include "llama.h"
 
 static constexpr uint32_t kMaxContextSize = 32768U;
@@ -89,7 +89,6 @@ LlamaGenerator::LlamaGenerator(
   }
 
   n_ctx_ = sampling.n_ctx;
-  n_gpu_layers_ = sampling.n_gpu_layers;
 
   this->Load(model_path);
 }

tooling/pipeline/src/data_generation/llama/load.cc

@@ -12,7 +12,6 @@
 #include <utility>
 
 #include "data_generation/llama_generator.h"
-#include "ggml-backend.h"
 #include "llama.h"
 
 // Maximum batch size for decode operations. Capping the batch prevents
@@ -23,12 +22,7 @@ void LlamaGenerator::Load(const std::string& model_path) {
   context_.reset();
   model_.reset();
 
-  // Specifically load dynamic ggml backends (like CUDA) that are provided
+  const llama_model_params model_params = llama_model_default_params();
-  // externally before attempting to load a model.
-  ggml_backend_load_all();
-
-  llama_model_params model_params = llama_model_default_params();
-  model_params.n_gpu_layers = n_gpu_layers_;
   LlamaGenerator::ModelHandle loaded_model(
       llama_model_load_from_file(model_path.c_str(), model_params));
   if (!loaded_model) {

tooling/pipeline/src/main.cc

@@ -8,43 +8,178 @@
 
 #include <boost/di.hpp>
 #include <boost/program_options.hpp>
+#include <chrono>
+#include <cstdint>
 #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/models.h"
+#include "data_model/application_options.h"
 #include "llama_backend_state.h"
-#include "services/database/export_service.h"
+#include "services/enrichment_service.h"
-#include "services/database/sqlite_export_service.h"
+#include "services/export_service.h"
-#include "services/datetime/timer.h"
+#include "services/prompt_directory.h"
-#include "services/enrichment/enrichment_service.h"
+#include "services/sqlite_export_service.h"
-#include "services/enrichment/mock_enrichment.h"
+#include "services/wikipedia_service.h"
-#include "services/enrichment/wikipedia_service.h"
+#include "web_client/curl_web_client.h"
-#include "services/prompting/prompt_directory.h"
-#include "web_client/http_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");
+
+  // Generator Options
+  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)");
+
+  // Sampling Options - defaults driven from SamplingOptions struct
+  const SamplingOptions kSamplingDefaults{};
+  opt("temperature",
+      prog_opts::value<float>()->default_value(kSamplingDefaults.temperature),
+      "Sampling temperature (higher = more random)");
+  opt("top-p",
+      prog_opts::value<float>()->default_value(kSamplingDefaults.top_p),
+      "Nucleus sampling top-p in (0,1] (higher = more random)");
+  opt("top-k",
+      prog_opts::value<uint32_t>()->default_value(kSamplingDefaults.top_k),
+      "Top-k sampling parameter (higher = more candidate tokens)");
+  opt("n-ctx",
+      prog_opts::value<uint32_t>()->default_value(kSamplingDefaults.n_ctx),
+      "Context window size in tokens");
+  opt("seed", prog_opts::value<int>()->default_value(kSamplingDefaults.seed),
+      "Sampler seed: -1 for random, otherwise non-negative integer");
+
+  // Pipeline Options
+  opt("output,o", prog_opts::value<std::string>()->default_value("output"),
+      "Directory for generated artifacts");
+  opt("log-path",
+      prog_opts::value<std::string>()->default_value("pipeline.log"),
+      "Path for application logs");
+  opt("prompt-dir", prog_opts::value<std::string>()->default_value(""),
+      "Directory containing named prompt files (e.g. BREWERY_GENERATION.md)."
+      " Required when not using --mocked.");
+
+  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 var_map;
+    prog_opts::store(prog_opts::parse_command_line(argc, argv, desc), var_map);
+    prog_opts::notify(var_map);
+
+    if (var_map.contains("help")) {
+      std::stringstream help_stream;
+      help_stream << "\n" << desc;
+      spdlog::info(help_stream.str());
+      return std::nullopt;
+    }
+
+    ApplicationOptions options;
+
+    options.pipeline.output_path = var_map["output"].as<std::string>();
+    options.pipeline.log_path = var_map["log-path"].as<std::string>();
+    options.pipeline.prompt_dir = var_map["prompt-dir"].as<std::string>();
+
+    const bool use_mocked = var_map["mocked"].as<bool>();
+    const std::string model_path = var_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;
+    }
+
+    if (!use_mocked && options.pipeline.prompt_dir.empty()) {
+      spdlog::error(
+          "Invalid arguments: --prompt-dir is required when not using "
+          "--mocked");
+      return std::nullopt;
+    }
+
+    options.generator.use_mocked = use_mocked;
+    options.generator.model_path = model_path;
+
+    const bool user_provided_sampling =
+        !var_map["temperature"].defaulted() || !var_map["top-p"].defaulted() ||
+        !var_map["top-k"].defaulted() || !var_map["n-ctx"].defaulted() ||
+        !var_map["seed"].defaulted();
+
+    if (use_mocked) {
+      if (user_provided_sampling) {
+        spdlog::warn("Sampling parameters are ignored when using --mocked");
+      }
+    } else if (user_provided_sampling) {
+      SamplingOptions sampling;
+      sampling.temperature = var_map["temperature"].as<float>();
+      sampling.top_p = var_map["top-p"].as<float>();
+      sampling.top_k = var_map["top-k"].as<uint32_t>();
+      sampling.n_ctx = var_map["n-ctx"].as<uint32_t>();
+      sampling.seed = var_map["seed"].as<int>();
+
+      options.generator.sampling = sampling;
+    }
+
+    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");
 
-#ifndef BIERGARTEN_MOCK_ONLY
+    const auto parsed_options = ParseArguments(argc, argv);
-    const LlamaBackendState llama_backend_state;
-#endif
-#ifdef DEBUG
-    spdlog::set_level(spdlog::level::debug);
-#endif
-
-    const std::optional<ApplicationOptions> parsed_options =
-        ParseArguments(argc, argv);
-
     if (!parsed_options.has_value()) {
       return 0;
     }
@@ -66,20 +201,12 @@ int main(const int argc, char** argv) {
     }
 
     const auto injector = di::make_injector(
+        di::bind<WebClient>().to<CURLWebClient>(),
         di::bind<ApplicationOptions>().to(options),
-        di::bind<std::string>().to(model_path),
+        di::bind<IEnrichmentService>().to<WikipediaService>(),
-        di::bind<WebClient>().to<HttpWebClient>(),
         di::bind<IExportService>().to<SqliteExportService>(),
         di::bind<IPromptFormatter>().to<Gemma4JinjaPromptFormatter>(),
-        di::bind<IEnrichmentService>().to(
+        di::bind<std::string>().to(model_path),
-            [options](const auto& inj) -> std::unique_ptr<IEnrichmentService> {
-              if (options.generator.use_mocked) {
-                return std::make_unique<MockEnrichmentService>();
-              }
-
-              return std::make_unique<WikipediaEnrichmentService>(
-                  inj.template create<std::unique_ptr<WebClient>>());
-            }),
         di::bind<DataGenerator>().to(
             [options, model_path, sampling, &prompt_directory](
                 const auto& inj) -> std::unique_ptr<DataGenerator> {
@@ -98,11 +225,9 @@ int main(const int argc, char** argv) {
                   options, model_path,
                   inj.template create<std::unique_ptr<IPromptFormatter>>(),
                   std::move(prompt_directory));
-            })
+            }));
 
-    );
+    auto generator =
-
-    const auto generator =
         injector.create<std::unique_ptr<BiergartenDataGenerator>>();
 
     if (!generator->Run()) {

tooling/pipeline/src/services/enrichment/wikipedia/fetch_extract.cc

@@ -1,112 +0,0 @@
-/**
- * @file wikipedia/fetch_extract.cc
- */
-
-#include <spdlog/spdlog.h>
-
-#include <boost/json.hpp>
-#include <chrono>
-#include <format>
-#include <string>
-#include <string_view>
-#include <thread>
-
-#include "services/enrichment/wikipedia_service.h"
-
-using namespace boost;
-
-std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
-
-  const std::string cache_key(query);
-
-  // 1. Cache Lookup
-  if (const auto cache_it = this->extract_cache_.find(cache_key);
-      cache_it != this->extract_cache_.end()) {
-    spdlog::debug("Wikipedia: Cache hit for {}!", cache_key);
-    return cache_it->second;
-  }
-
-  const std::string encoded = this->client_->EncodeURL(cache_key);
-  const std::string url = std::format(
-      "https://en.wikipedia.org/w/"
-      "api.php?action=query&titles={}&prop=extracts&explaintext=1&format=json",
-      encoded);
-
-
-  const std::string body = this->client_->Get(url);
-  {
-    using namespace std::literals::chrono_literals;
-    std::this_thread::sleep_for(1s);
-  }
-
-  // 2. Parse JSON
-  system::error_code ec;
-  json::value doc = json::parse(body, ec);
-
-  if (ec) {
-    spdlog::warn("WikipediaService: JSON parse error for '{}': {}", query,
-                 ec.message());
-    return {};
-  }
-
-  // 3. Safe Extraction
-  const json::object* obj = doc.if_object();
-  if (obj == nullptr) {
-    spdlog::warn("WikipediaService: Expected root object for '{}'", query);
-    return {};
-  }
-
-  const json::value* query_ptr = obj->if_contains("query");
-  const json::value* pages_ptr =
-      ((query_ptr != nullptr) && query_ptr->is_object())
-          ? query_ptr->get_object().if_contains("pages")
-          : nullptr;
-
-  if ((pages_ptr == nullptr) || !pages_ptr->is_object()) {
-    spdlog::warn("WikipediaService: Missing query.pages for '{}'", query);
-    return {};
-  }
-
-  const json::object& pages = pages_ptr->get_object();
-
-  if (pages.empty()) {
-    spdlog::warn("WikipediaService: No pages returned for '{}'", query);
-    this->extract_cache_.emplace(cache_key, "");
-    return {};
-  }
-
-  // Wikipedia returns the page under a dynamic ID key; we just want the first
-  // one
-  const json::value& page_val = pages.begin()->value();
-
-  if (!page_val.is_object()) {
-    spdlog::warn("WikipediaService: Unexpected page format for '{}'", query);
-    return {};
-  }
-
-  const json::object& page = page_val.get_object();
-
-  // Handle 404/Missing status
-  if (page.contains("missing")) {
-    spdlog::warn("WikipediaService: Page '{}' does not exist", query);
-    this->extract_cache_.emplace(cache_key, "");
-    return {};
-  }
-
-  const json::value* extract_ptr = page.if_contains("extract");
-
-  if ((extract_ptr == nullptr) || !extract_ptr->is_string()) {
-    spdlog::warn("WikipediaService: No extract string found for '{}'", query);
-    this->extract_cache_.emplace(cache_key, "");
-    return {};
-  }
-
-  // 4. Success
-  std::string extract(extract_ptr->as_string());
-  spdlog::info("WikipediaService: Fetched {} chars for '{}'", extract.size(),
-                query);
-
-  this->extract_cache_.insert_or_assign(cache_key, extract);
-
-  return extract;
-}

tooling/pipeline/src/services/enrichment/wikipedia/get_summary.cc

@@ -1,58 +0,0 @@
-/**
- * @file wikipedia/get_summary.cc
- * @brief WikipediaService::GetLocationContext() implementation.
- */
-
-#include <spdlog/spdlog.h>
-
-#include <chrono>
-#include <format>
-#include <string>
-#include <thread>
-
-#include "services/enrichment/wikipedia_service.h"
-
-std::string WikipediaEnrichmentService::GetLocationContext(const Location& loc) {
-  using namespace std::literals::chrono_literals;
-  if (!this->client_) {
-    spdlog::warn("Client is nullptr.");
-    return {};
-  }
-
-  std::string result;
-
-  // std::string region_query(loc.city);
-  // if (!loc.country.empty()) {
-  //   region_query += loc.state_province,
-  //   region_query += ", ";
-  //   region_query += loc.country;
-  // }
-
-  constexpr std::string_view brewing_query = "brewing";
-  const std::string location_query =
-      std::format("{}, {}", loc.city, loc.iso3166_2);
-  const std::string beer_query = std::format("beer in {}", loc.country);
-
-  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(brewing_query));
-    append_extract(FetchExtract(beer_query));
-    spdlog::info("Done fetching for {}. Sleeping for 10 seconds.",
-                 location_query);
-    std::this_thread::sleep_for(10s);
-
-  } catch (const std::runtime_error& e) {
-    spdlog::debug("WikipediaService lookup failed for '{}': {}", location_query,
-                  e.what());
-  }
-  return result;
-}

tooling/pipeline/src/services/prompt_directory.cc

@@ -4,7 +4,7 @@
  * construction and loads named prompt files on demand with in-process caching.
  */
 
-#include "services/prompting/prompt_directory.h"
+#include "services/prompt_directory.h"
 
 #include <spdlog/spdlog.h>
 

tooling/pipeline/src/services/sqlite/build_database_path.cc

@@ -0,0 +1,23 @@
+/**
+ * @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 = output_path_ / base_filename;
+
+  for (int suffix = 1; std::filesystem::exists(candidate); ++suffix) {
+    candidate = output_path_ /
+                std::filesystem::path("biergarten_seed_" + run_timestamp_utc_ +
+                                      "-" + std::to_string(suffix) + ".sqlite");
+  }
+
+  return candidate;
+}

tooling/pipeline/src/services/sqlite/finalize.cc

@@ -5,8 +5,8 @@
 
 #include <stdexcept>
 
-#include "services/database/sqlite_export_service.h"
+#include "services/sqlite_export_service.h"
-#include "services/database/sqlite_export_service_helpers.h"
+#include "services/sqlite_export_service_helpers.h"
 
 void SqliteExportService::Finalize() {
   if (db_handle_ == nullptr) {
@@ -28,4 +28,4 @@ void SqliteExportService::Finalize() {
     RollbackAndCloseNoThrow();
     throw;
   }
-}
+}

tooling/pipeline/src/services/sqlite/helpers/sqlite_connection_helpers.cpp

@@ -1,4 +1,4 @@
-#include "services/database/sqlite_connection_helpers.h"
+#include "services/sqlite_connection_helpers.h"
 
 #include <stdexcept>
 

tooling/pipeline/src/services/sqlite/helpers/sqlite_statement_helpers.cpp

@@ -1,4 +1,4 @@
-#include "services/database/sqlite_statement_helpers.h"
+#include "services/sqlite_statement_helpers.h"
 
 #include <boost/json.hpp>
 #include <cstring>
@@ -6,7 +6,7 @@
 #include <memory>
 #include <stdexcept>
 
-#include "services/database/sqlite_connection_helpers.h"
+#include "services/sqlite_connection_helpers.h"
 
 namespace sqlite_export_service_internal {
 

tooling/pipeline/src/services/sqlite/initialize.cc

@@ -8,22 +8,8 @@
 #include <stdexcept>
 #include <string>
 
-#include "services/database/sqlite_export_service.h"
+#include "services/sqlite_export_service.h"
-#include "services/database/sqlite_export_service_helpers.h"
+#include "services/sqlite_export_service_helpers.h"
-
-std::filesystem::path SqliteExportService::BuildDatabasePath() const {
-  std::filesystem::path base_filename("biergarten_seed_" + run_timestamp_utc_ +
-                                      ".sqlite");
-  std::filesystem::path candidate = output_path_ / base_filename;
-
-  for (int suffix = 1; std::filesystem::exists(candidate); ++suffix) {
-    candidate = output_path_ /
-                std::filesystem::path("biergarten_seed_" + run_timestamp_utc_ +
-                                      "-" + std::to_string(suffix) + ".sqlite");
-  }
-
-  return candidate;
-}
 
 void SqliteExportService::InitializeSchema() const {
   sqlite_export_service_internal::ExecSql(

tooling/pipeline/src/services/sqlite/process_record.cc

@@ -8,8 +8,8 @@
 #include <stdexcept>
 #include <string>
 
-#include "services/database/sqlite_export_service.h"
+#include "services/sqlite_export_service.h"
-#include "services/database/sqlite_export_service_helpers.h"
+#include "services/sqlite_export_service_helpers.h"
 
 constexpr int kLocationPrecision = 17;
 

tooling/pipeline/src/services/sqlite/sqlite_export_service.cc

@@ -3,7 +3,7 @@
  * @brief SqliteExportService constructor and destructor implementation.
  */
 
-#include "services/database/sqlite_export_service.h"
+#include "services/sqlite_export_service.h"
 
 #include <memory>
 

tooling/pipeline/src/services/wikipedia/fetch_extract.cc

@@ -0,0 +1,61 @@
+/**
+ * @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 {};
+}

tooling/pipeline/src/services/wikipedia/get_summary.cc

@@ -0,0 +1,47 @@
+/**
+ * @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;
+}

tooling/pipeline/src/services/wikipedia/wikipedia_service.cc

@@ -3,10 +3,9 @@
  * @brief WikipediaService constructor implementation.
  */
 
-#include "services/enrichment/wikipedia_service.h"
+#include "services/wikipedia_service.h"
 
 #include <utility>
 
-WikipediaEnrichmentService::WikipediaEnrichmentService(
+WikipediaService::WikipediaService(std::unique_ptr<WebClient> client)
-    std::unique_ptr<WebClient> client)
     : client_(std::move(client)) {}

tooling/pipeline/src/web_client/curl_global_state.cc

@@ -0,0 +1,19 @@
+/**
+ * @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(); }

tooling/pipeline/src/web_client/curl_web_client_get.cc

@@ -0,0 +1,87 @@
+/**
+ * @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 long kMaxRedirects = 5;
+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, kMaxRedirects);
+  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;
+}

tooling/pipeline/src/web_client/curl_web_client_url_encode.cc

@@ -0,0 +1,24 @@
+/**
+ * @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;
+}

tooling/pipeline/src/web_client/http_web_client.cc

@@ -1,68 +0,0 @@
-/**
-* @file web_client/http_web_client.cc
- * @brief cpp-httplib implementation of WebClient.
- */
-
-#include "web_client/http_web_client.h"
-
-#include <httplib.h>
-
-#include <regex>
-#include <stdexcept>
-#include <string>
-#include <utility>
-
-#include "spdlog/spdlog.h"
-
-namespace {
-constexpr time_t kConnectionTimeoutSeconds = 5;
-constexpr time_t kReadTimeoutSeconds = 10;
-
-constexpr int kSuccessMin = 200;
-constexpr int kSuccessMax = 300;
-const std::regex kUrlRegex(
-    R"(^(https?://[^/?#]+)(/[^?#]*(?:\?[^#]*)?(?:#.*)?)?)");
-
-std::pair<std::string, std::string> SplitUrl(const std::string& url) {
-  std::smatch match;
-  if (!std::regex_match(url, match, kUrlRegex)) {
-    throw std::invalid_argument("[HttpWebClient] Malformed URL: " + url);
-  }
-
-  return {match[1].str(), match[2].matched ? match[2].str() : "/"};
-}
-} // namespace
-
-std::string HttpWebClient::Get(const std::string& url) {
-  const auto [origin, path] = SplitUrl(url);
-
-  httplib::Client client(origin);
-  client.set_follow_location(true);
-  client.set_connection_timeout(kConnectionTimeoutSeconds);
-  client.set_read_timeout(kReadTimeoutSeconds);
-  client.set_default_headers({
-     {"Accept", "application/json"},
-     {"User-Agent", "biergarten-pipeline/1.0"}
- });
-
-  const httplib::Result result = client.Get(path);
-
-  if (!result) {
-    throw std::runtime_error(
-        "[HttpWebClient] Request failed for URL: " + url +
-        " — " + httplib::to_string(result.error()));
-  }
-
-  if (result->status < kSuccessMin || result->status >= kSuccessMax) {
-    spdlog::error("[HttpWebClient] Request failed for URL: " + url);
-    throw std::runtime_error(
-        "[HttpWebClient] HTTP " + std::to_string(result->status) +
-        " for URL: " + url);
-  }
-
-  return result->body;
-}
-
-std::string HttpWebClient::EncodeURL(const std::string& value) {
-  return httplib::encode_uri_component(value);
-}