Woody c6d4a38013 feat: add LLM-based batch highlight service and HTML rendering (Phase 5.4.4) ... - ChunkHighlightService.compute_highlights_batch(): single LLM call across all cited chunks, grouped by sub-question, with structured output - render_highlight_html(): self-contained HTML page with yellow-highlighted relevant sentences, LLM reason annotations, and View Original PDF footer - Per-target error isolation, ChromaDB miss handling, graceful degradation - 14 tests: 7 batch service + 7 HTML rendering		2026-04-29 09:26:33 +08:00
..
core	feat(prompts): enforce bullet-point output in generate template	2026-04-28 16:42:55 +08:00
models	feat: add sentence splitter and highlight data models (Phase 5.4.1-5.4.2)	2026-04-29 09:26:06 +08:00
routers	feat(ingest): generate per-chunk PDFs for DOCX/TXT documents (Phase 5.3)	2026-04-28 17:32:22 +08:00
services	feat: add LLM-based batch highlight service and HTML rendering (Phase 5.4.4)	2026-04-29 09:26:33 +08:00
test	feat: add LLM-based batch highlight service and HTML rendering (Phase 5.4.4)	2026-04-29 09:26:33 +08:00
utils	feat: add sentence splitter and highlight data models (Phase 5.4.1-5.4.2)	2026-04-29 09:26:06 +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(deploy): add Dockerfile, compose, nginx config, and README	2026-04-27 17:17:53 +08:00