docs: add full bilingual README with RAG architecture and Groq usage 39c7c75 FabIndy commited on Jan 31
Switch to Groq-only LLM, remove GGUF dependency, speed up build and inference 56a777c FabIndy commited on Jan 30
Stabilize RAG core: add SUMMARY_AI, speed up LIST, clean resources and config feddcd9 FabIndy commited on Jan 26
Fix LIST retrieval with robust FAISS fallback and lexical normalization b4a2740 FabIndy commited on Jan 15
Improve LIST reliability with score threshold and lexical guard; align UI with extractive synthesis and faster QA 6a852cd FabIndy commited on Jan 15
Refactor UI and RAG modes: extractive synthesis for EXPLAIN, faster QA with warnings 229fbd9 FabIndy commited on Jan 15
Speed up EXPLAIN: reduce LLM input and allow extractive-style explanation 1e8b426 FabIndy commited on Jan 15
Fix EXPLAIN mode: dedicated LLM prompt, longer output, strict article handling b00b20e FabIndy commited on Jan 14
Add EXPLAIN mode (requires article id) and force single-article context 14fa239 FabIndy commited on Jan 14