AaronPo/the-biergarten-app
1
0
Fork 0
mirror of https://github.com/aaronpo97/the-biergarten-app.git synced 2026-06-01 01:54:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor(pipeline): restructure config, add PromptDirectory, consolidate SQLite layer (#217)

Browse Source 
* Refactor ApplicationOptions to separate config concerns

* add prompt dir app option

* readability updates: remove magic numbers, update comments

* codebase formatting

* Update docs

* Extract argument parsing, timer out of
This commit is contained in:
Aaron Po
2026-05-02 18:27:14 -04:00
committed by GitHub
parent 641a479b6a
commit b1dc8e0b5d
35 changed files with 561 additions and 310 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
tooling/pipeline/includes/data_generation/llama_generator.h
View File

@@ -17,6 +17,7 @@
#include "data_generation/data_generator.h"
#include "data_generation/prompt_formatting/prompt_formatter.h"
#include "data_model/application_options.h"
#include "services/prompt_directory.h"
struct llama_model;
struct llama_context;
@@ -33,10 +34,12 @@ class LlamaGenerator final : public DataGenerator {
* @param options Parsed application options.
* @param model_path Filesystem path to GGUF model assets.
* @param prompt_formatter Formatter that produces model-specific prompts.
* @param prompt_directory Directory service for loading named prompt files.
*/
LlamaGenerator(const ApplicationOptions& options,
const std::string& model_path,
std::unique_ptr<IPromptFormatter> prompt_formatter);
std::unique_ptr<IPromptFormatter> prompt_formatter,
std::unique_ptr<IPromptDirectory> prompt_directory);
~LlamaGenerator() override;
@@ -119,15 +122,6 @@ class LlamaGenerator final : public DataGenerator {
int max_tokens = kDefaultMaxTokens,
std::string_view grammar = {});
/**
* @brief Loads the brewery system prompt from disk.
*
* @param prompt_file_path Prompt file path to try first.
* @return Loaded prompt text.
*/
std::string LoadBrewerySystemPrompt(
const std::filesystem::path& prompt_file_path);
ModelHandle model_;
ContextHandle context_;
float sampling_temperature_ = 1.0F;
@@ -135,8 +129,8 @@ class LlamaGenerator final : public DataGenerator {
uint32_t sampling_top_k_ = kDefaultSamplingTopK;
std::mt19937 rng_;
uint32_t n_ctx_ = kDefaultContextSize;
std::string brewery_system_prompt_;
std::unique_ptr<IPromptFormatter> prompt_formatter_;
std::unique_ptr<IPromptDirectory> prompt_directory_;
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_LLAMA_GENERATOR_H_

7
tooling/pipeline/includes/data_generation/mock_generator.h
View File

@@ -44,6 +44,13 @@ class MockGenerator final : public DataGenerator {
*/
static size_t DeterministicHash(const Location& location);
// Hash stride constants for deterministic distribution across fixed-size
// arrays. These coprime strides spread hash values uniformly without
// clustering, ensuring diverse output across different hash inputs.
static constexpr size_t kNounHashStride = 7;
static constexpr size_t kDescriptionHashStride = 13;
static constexpr size_t kBioHashStride = 11;
static constexpr std::array<std::string_view, 18> kBreweryAdjectives = {
"Craft", "Heritage", "Local", "Artisan", "Pioneer", "Golden",
"Modern", "Classic", "Summit", "Northern", "Riverstone", "Barrel",