woody
/
legco_ai_assistant
1
1
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
59 Commits 2 Branches 0 Tags 2.6 MiB
Commit Graph

5 Commits

Author SHA1 Message Date
Woody b2dd385443 feat(backend): refactor ingest pipeline for page-aware chunking with PDF generation 
PDF uploads now use parse_pdf_by_page() -> chunk_pages() -> extract page PDFs -> enhanced metadata with page_number, chunk_file_path, and document_id. Same-filename replacement deletes old chunks and PDFs before re-ingest. DOCX/TXT keep original flat flow with document_id added. RAGService.ingest_document() accepts optional document_id parameter.

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

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-04-24 10:53:17 +08:00
Woody b48c23001e fix(backend): preserve original filename in chunk metadata instead of temp file name 
When uploading files, the backend passes them through NamedTemporaryFile, causing os.path.basename to return temp names like 'tmp90i7xqa8.pdf'. Added original_filename parameter to extract_metadata() so the actual upload filename is stored.

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

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-04-24 10:14:58 +08:00
Woody 4a22b906e4 refactor(backend): update ingest and query routers 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-04-23 13:26:32 +08:00
Woody 7493b3aaf6 feat: Phase 1.4 acceptance tests, error handling, and polish 
- Implement acceptance tests for ingest (real ChromaDB) and query (real LLM)
- Full 3-step RAG pipeline verified: decompose → retrieve → filter → generate
- Add logging to ingest and query routers
- Improve error handling: empty doc detection, proper HTTPException re-raising
- Add .txt file support to ingest endpoint
- Fix query router: strip distance from retrieve tuples before relevance filter
- Update plan: Phase 1 backend complete (all acceptance criteria met)
- Tests: 41 unit passed, 5 acceptance passed (real OpenRouter calls)
 2026-04-22 17:45:50 +08:00
Woody d94abaac77 feat: Phase 1.2 ingestion pipeline with chunking and metadata 
- Add document parsers (DOCX, PDF) with lazy imports
- Add TokenChunkingStrategy with ABC for future replacement
- Add metadata extraction (filename, upload_date, content_summary)
- Add RAGService for ChromaDB ingestion/retrieval/response generation
- Add POST /api/v1/ingest endpoint with file validation
- Test-first: 20 passed, 2 skipped (python-docx not installed)
 2026-04-22 16:49:52 +08:00