legco_ai_assistant/backend/app
Woody 57a130dc96 feat(services): add per-sub-question retrieval, filtering, and response generation
Add retrieve_per_subquestion() that queries ChromaDB independently per sub-question instead of joining all sub-qs into one query string. Add filter_per_subquestion() that evaluates each chunk against its own originating sub-question in a single LLM call with a redesigned grouped prompt. Add generate_response_per_subquestion() that produces markdown sections per sub-question with grouped sources and {context_sections} template support. All existing methods preserved for backward compatibility.

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

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-26 23:27:50 +08:00
..
core feat(history): Phase 3.5 — Query History backend (service, API, timing, XML capture) 2026-04-25 22:59:53 +08:00
models feat(history): Phase 3.5 — Query History backend (service, API, timing, XML capture) 2026-04-25 22:59:53 +08:00
routers feat(history): Phase 3.5 — Query History backend (service, API, timing, XML capture) 2026-04-25 22:59:53 +08:00
services feat(services): add per-sub-question retrieval, filtering, and response generation 2026-04-26 23:27:50 +08:00
test feat(history): Phase 3.5 — Query History backend (service, API, timing, XML capture) 2026-04-25 22:59:53 +08:00
utils feat(backend): add PDF page extractor and chunk PDF storage config 2026-04-24 10:52:57 +08:00
__init__.py feat: Phase 1.1 project setup with config, database, and models 2026-04-22 16:13:52 +08:00
main.py feat(history): Phase 3.5 — Query History backend (service, API, timing, XML capture) 2026-04-25 22:59:53 +08:00