DeepMedAI / backend /app /tools /llm_client.py

Commit History

Gemini thinking: budget 1024 tokens instead of fully disabled
1da9f9b

PBThuong commited on

Perf: add SSE streaming, disable Gemini thinking, skip query rewrite when no history
5354bc3

PBThuong commited on

feat: Gemini multi-key rotation (key1 → key2 → key3 → NVIDIA → OpenRouter)
ae6f621

PBThuong commited on

feat: switch fallback LLM to DeepSeek V3.2 via NVIDIA Build (free)
dce8f48

PBThuong commited on

Thiết lập lại thư viện y khoa sạch và cập nhật chroma_db
8eaa451

PBThuong commited on