Spaces:
Running
Running
| # Backend dependencies for the HuggingFace API Space and local development. | |
| # sentence-transformers is NOT included here — in prod, embedder/reranker | |
| # are separate HF Spaces. For local in-process models, install it manually | |
| # or create a requirements.local.txt with sentence-transformers added. | |
| # mlflow/dagshub are intentionally excluded: they add ~300MB to the Docker | |
| # image and are imported lazily only when DAGSHUB_TOKEN is set. Install them | |
| # in requirements.local.txt for local experiment tracking. | |
| fastapi>=0.115.0 | |
| uvicorn[standard]>=0.29.0 | |
| uvloop>=0.19.0 | |
| python-multipart>=0.0.9 | |
| pydantic-settings>=2.2.1 | |
| langgraph>=0.2.0 | |
| qdrant-client==1.9.1 | |
| groq>=0.5.0 | |
| httpx>=0.27.0 | |
| numpy>=1.26.0 | |
| slowapi>=0.1.9 | |
| # presidio-analyzer was removed (Issue 4): spaCy-based NLP added 50-100ms to every | |
| # request for near-zero real-world PII risk. Replaced with six compiled regex | |
| # patterns in sanitizer.py that run in microseconds. See copilot-instructions.md. | |
| tenacity>=8.3.0 | |
| python-jose[cryptography]>=3.3.0 | |
| google-genai>=1.0.0 | |
| # fastembed: powers BM25 sparse retrieval (Stage 2). Qdrant/bm25 vocabulary | |
| # downloads ~5 MB on first use then runs fully local — no GPU, no network at query time. | |
| fastembed>=0.3.6 | |
| toon_format @ git+https://github.com/toon-format/toon-python.git |