woody
/
legco_ai_assistant
1
1
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
157 Commits 2 Branches 0 Tags 2.5 MiB
Commit Graph

17 Commits

Author SHA1 Message Date
Woody 76c3bec2ab feat: configurable SubQuestions via Step 1.2 system prompt page 
- Split 'Step 1: Query Decomposition' into Step 1.1 (prompt template) and Step 1.2 (format config with description + max_length)

- Add create_subquestions_model() and parse_decompose_format() to decompose.py

- QueryDecomposer reads decompose_format from DB, creates dynamic Pydantic model at runtime

- PromptEditor renders Step 1.2 as textarea (description) + number input (max_length 1-5)

- Graceful fallback to static SubQuestions when decompose_format unavailable
 2026-05-04 17:22:14 +08:00
Woody 40b338d3ca chore: gitignore .research, switch to flash, tighten sub-questions 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-05-04 16:38:58 +08:00
Woody 5535b42ae2 refactor: tighten SubQuestions to 1-3 with Cantonese format hint 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-05-04 15:18:14 +08:00
Woody 41f59b396f feat: track highlight generation prompt, response, and timing in history (Phase 5.5) 
- Add 3 columns to query_history: highlight_prompt, highlight_response, highlight_time_ms
- HistoryService.update_highlights() updates existing row after batch LLM call
- ChunkHighlightService measures timing, captures prompt and structured JSON response
- SSE completed event includes history_id for frontend to pass back
- Frontend captures historyId, passes as ?history_id= query param in batch POST
- Highlight time tracked separately (excluded from total_time_ms)
- All 153 tests pass (108 backend + 45 frontend)
 2026-04-29 11:18:21 +08:00
Woody b11d31e2d1 feat: add sentence splitter and highlight data models (Phase 5.4.1-5.4.2) 
- sentence_splitter.py: regex-based sentence splitting for English + Chinese punctuation
- highlight.py: 6 Pydantic models (ChunkHighlightTarget, HighlightBatchRequest,
  RelevantSentence, ChunkHighlights, HighlightBatchResult, HighlightBatchResponse)
- 43 tests: 13 sentence splitter + 30 model validation
 2026-04-29 09:26:06 +08:00
Woody f2115ae563 feat: structured LLM output for decompose + citation fuzzy matching (Phase 5) 
Phase 5.1 — Structured LLM output for query decomposition:
- Add SubQuestions Pydantic model with sub_question, keywords, rationale
- Add LLMClient.complete_structured() using langchain with_structured_output
- Update QueryDecomposer with structured output path + legacy json.loads fallback
- Update SQLite seed templates: add subq+citation labeling requirement
- Add tests: structured output, subquestions model validation, logging

Phase 5.2 — Citation format alignment and fallback links:
- Add document_id to SourceMetadata (backend + frontend types)
- Rewrite citationParser.ts with fuzzy matching and fallback document links
- Add RAGDatabasePage auto-expand from ?document= URL param
- Tighten generate_per_subq seed prompt: 'Copy exact bracket labels shown'
- Add citation parser tests for fuzzy match and fallback link scenarios
- Defer: DOCX/TXT PDF generation → Phase 5.3 (fallback links sufficient)
 2026-04-28 15:39:17 +08:00
Woody 23796d6a0c feat(prompts): add JSON export/import for profile prompt configurations 2026-04-27 19:44:35 +08:00
Woody 40393d81f8 feat(models): add SubQuestionSources model and per-sub-q history fields 
Add SubQuestionSources, SubQuestionResult, GeneratingSubquestionEvent Pydantic models for the new per-sub-question response format. Add chunks_retrieved_per_subq_count and chunks_filtered_per_subq_count optional fields to QueryHistoryRecord and QueryHistoryDetail for per-sub-question chunk count tracking.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-04-26 23:28:19 +08:00
Woody 475306f2b1 feat(history): Phase 3.5 — Query History backend (service, API, timing, XML capture) 2026-04-25 22:59:53 +08:00
Woody e49a68b0bd feat(prompts): Phase 3.2 — Prompt Backend (CRUD service, REST API, 33 tests) 
- PromptService (services/prompt_service.py): full CRUD for 3 profiles A/B/C
  with seed template reset, validation, and sqlite3.Row access
- REST API (routers/prompts.py): 6 endpoints on /api/v1/prompts
- Pydantic models (models/prompts.py): 6 schemas
- DI wiring (dependencies.py): get_prompt_service()
- App registration (main.py): prompts router
- Mock fixture (conftest.py): mock_prompt_service
- Tests: test_phase3_prompt_service.py (22) + test_phase3_prompts_router.py (11)
- 162/166 total pass, 4 skipped, 0 fail
 2026-04-25 21:11:17 +08:00
Woody 3b741c1844 feat(query): stream extracted questions immediately via SSE 
Convert /query endpoint from synchronous JSON to Server-Sent Events (SSE)
streaming. The frontend now receives extracted_questions as soon as the
first LLM call completes, without waiting for retrieval, filtering, and
answer generation.

Backend:
- Add StreamingQueryEvent union type (Decomposed, Retrieving, Filtering,
  Generating, Completed, Error)
- Convert /query to return StreamingResponse with SSE format
- Yield events after each pipeline phase

Frontend:
- Add queryDocumentStream() using fetch + ReadableStream
- Add useQueryDocumentStream() hook with phase-aware state
- Update LTTPage to use streaming instead of mutation
- Update ResponsePanel to show phase messages (Searching documents...,
  Filtering passages..., Generating answer...)
- Update ExtractedQuestionsDisplay to accept null

Tests:
- Update query_flow e2e test to mock queryDocumentStream
- 84/85 tests pass (1 pre-existing failure from removed file-input)
 2026-04-25 18:29:22 +08:00
Woody f9dda7bd18 feat(backend): rename keywords to extracted_questions in query pipeline (sub-phase 2.3) 
Change QueryDecomposer prompt to generate 2-5 sub-questions instead of keywords. Rename API field from keywords to extracted_questions across models, service, and router.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-04-24 16:23:53 +08:00
Woody d49756f374 feat: add chunk PDF serving endpoint and frontend clickable source links (1.5.6) 
- Add page_number and chunk_file_path to SourceMetadata model and query router
- Add GET /chunks/{file_path}/pdf endpoint with path traversal protection
- Add View PDF links in ResponsePanel source cards and ChunkList component
- Update TypeScript types and API helper for chunk PDF URLs
- Add backend tests (5) and frontend ChunkList tests (7)
- Update enhancement plan: all 3 features complete
 2026-04-24 11:49:39 +08:00
Woody 178461915a feat(backend): add documents CRUD service methods and Pydantic schemas 
Add list_documents(), list_chunks(), delete_document(), delete_chunk() to RAGService for ChromaDB document management. New schemas: DocumentInfo, ChunkInfo, DocumentListResponse, DeleteResponse.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-04-23 19:02:07 +08:00
Woody 09f8cb7e6d refactor(backend): update Pydantic models for ingestion and query 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-04-23 13:26:20 +08:00
Woody 181f4eca5b feat: Phase 1.3 query pipeline with decomposition, relevance filter, and response 
- Add QueryDecomposer: extracts keywords from question via LLM JSON response
- Add RelevanceFilter: batch scores chunks 0-10, filters by threshold
- Add POST /api/v1/query endpoint with full 3-step pipeline:
  1. QueryDecomposer.decompose() → keywords
  2. RAGService.retrieve() → chunks from ChromaDB
  3. RelevanceFilter.filter() → score and filter chunks
  4. RAGService.generate_response() → bullet-point answer
- Fix SourceMetadata.upload_date type from datetime to str for flexibility
- Test-first: 13 new tests pass (5 decomposer, 5 relevance filter, 3 query endpoint)
- All Phase 1 tests: 41 passed, 2 skipped
 2026-04-22 17:19:21 +08:00
Woody 3712397d64 feat: Phase 1.1 project setup with config, database, and models 
- Add requirements.txt with all dependencies
- Add .env.example with required environment variables
- Add Pydantic Settings (config.py) with .env loading
- Add ChromaDB persistent client (database.py)
- Add Pydantic schemas (ingest.py) for request/response
- Add FastAPI main.py with CORS middleware
- Add package __init__.py files
- Add tests: test_phase1_config.py, test_phase1_database.py
- All 5 tests pass
 2026-04-22 16:13:52 +08:00