legco_ai_assistant/.plans
Woody dbae9411c6 docs: Package 8 enhancement plan — Q&A-pair chunking strategy with vision table extraction
- New QuestionChunkingStrategy splits by 問/答 and Q1/Q2 boundaries
- Vision-based table-to-markdown using existing Qwen3.5-35B-A3B (native vision model)
- Strategy selector UI on RAG Database page (token vs question)
- Hybrid approach: regex primary split + LLM verification for edge cases
- Single-model architecture — no separate vision API needed
- 6 sub-phases with test-first delivery, 7 new files, 15+ modified files
2026-05-15 11:10:36 +08:00
..
debug_2026-04-23_upload_500_error.md docs: add debug logs for upload 500 error investigation 2026-04-23 13:25:23 +08:00
debug_2026-05-15_vllm_highlight_failure.md docs: vLLM highlight failure fix plan — confirmed guided_json removed in v0.12.0 2026-05-15 10:13:07 +08:00
debug_vllm_structured_output.md docs: add vLLM structured output fix plan 2026-04-29 16:42:23 +08:00
half_question_enhancement_plan.md feat: Phase 3 — Half Question button, Final Submit rename, ASR text always black 2026-05-14 21:27:21 +08:00
package2_enhancement_plan.md docs: mark sub-phase 2.6 complete — Package 2 all done 2026-04-24 17:53:56 +08:00
package3_enhancement_plan.md feat(frontend): Phase 3.6 — History page with timing bars, expandable cards, and pagination 2026-04-26 13:19:52 +08:00
package4_enhancement_plan.md docs(plan): add Phase PX profile export/import feature plan 2026-04-27 19:26:33 +08:00
package5_enhancement_plan.md feat: track highlight generation prompt, response, and timing in history (Phase 5.5) 2026-04-29 11:18:21 +08:00
package6_enhancement_plan.md docs: add Package 6 enhancement plan 2026-05-04 14:58:24 +08:00
package6_subquestions_config_plan.md docs: add plan for configurable SubQuestions format 2026-05-04 17:22:38 +08:00
package7_enhancement_plan.md docs: Package 7 — switch compact citations to sequential [1] [2] [3] numbering 2026-05-15 09:58:07 +08:00
package8_enhancement_plan.md docs: Package 8 enhancement plan — Q&A-pair chunking strategy with vision table extraction 2026-05-15 11:10:36 +08:00
phase1_backend_plan.md feat: Phase 1.4 acceptance tests, error handling, and polish 2026-04-22 17:45:50 +08:00
phase1_debug_plan.md docs: add debug logs for upload 500 error investigation 2026-04-23 13:25:23 +08:00
phase1_enhancement_plan.md feat: add chunk PDF serving endpoint and frontend clickable source links (1.5.6) 2026-04-24 11:49:39 +08:00
phase1_frontend_plan.md docs: update development plans with Phase 1 completion status 2026-04-23 13:27:52 +08:00
phase2_enhancement_delta_sse.md feat: delta-based ASR transcript — use text field, utterance boundaries, stash on pause 2026-05-07 11:26:19 +08:00
phase2_enhancement_use_text_field.md refactor: remove dead _merge_stash, add Phase 3 YouTube proxy plan 2026-05-09 15:14:01 +08:00
phase2_implementation_plan.md fix: text accumulation — stashes are sliding windows, merge via overlap detection 2026-05-06 20:06:39 +08:00
phase4_system_audio_plan.md docs: sync plan files with actual implementation — Phase 4 complete 2026-05-15 10:00:45 +08:00
streaming_extracted_questions_plan.md feat(query): stream extracted questions immediately via SSE 2026-04-25 18:29:22 +08:00