Custom-LLM-Chat / rag /embedder.py

Commit History

fix: model singleton cache, dedup guard, Gradio type=messages
9edd318

Bhaskar Ram commited on

fix: sentence-aware chunking, score threshold, DOCX tables, streaming error handling, LLM_MODEL env var
2623b17

Bhaskar Ram commited on

feat: apply all 15 upgrades — BGE embeddings, cosine FAISS, streaming LLM, tenacity retry, dotenv, Dockerfile, tests
a465955

Bhaskar Ram commited on

Fix Gradio 6.x compatibility errors
55953aa

Bhaskar Ram commited on