| # ── Core serving ─────────────────────────────────────────────────────────────── | |
| fastapi==0.115.0 | |
| uvicorn[standard]==0.30.6 | |
| pydantic==2.7.4 | |
| # ── LLM + fine-tuned model (local backend) ───────────────────────────────────── | |
| # Only needed when LLM_BACKEND=local | |
| # GPU with 6GB+ VRAM required; loads fine on CPU but very slow | |
| torch==2.3.1 | |
| transformers==4.51.3 | |
| peft==0.15.2 | |
| bitsandbytes==0.43.3 # 4-bit NF4 quantization (official Windows wheels since 0.42) | |
| accelerate==1.6.0 | |
| # ── RAG ──────────────────────────────────────────────────────────────────────── | |
| langchain==1.2.13 | |
| langchain-community==0.4.1 | |
| langchain-classic==1.0.3 # provides langchain_classic.chains.RetrievalQA | |
| langchain-groq==1.1.2 | |
| groq==0.37.1 | |
| pinecone-client==3.2.2 # langchain-community expects the v3 Pinecone client API | |
| sentence-transformers==4.1.0 | |
| # ── Utilities ────────────────────────────────────────────────────────────────── | |
| python-dotenv==1.0.1 | |
| requests>=2.31.0 | |