requirements.txt

# Bumped 0.3.2 -> 0.3.32 (Jun 2026) and still built FROM SOURCE (Dockerfile
# --no-binary):
#   * Qwen3.5 uses the `qwen35` architecture, which needs llama.cpp >= b9616.
#     The old 0.3.2 pin can't load it ("unknown architecture 'qwen35'").
#   * 0.3.32 vendors a recent llama.cpp (past the old CPU "set_rows" decode
#     crash) and works on Debian glibc when compiled here.
# If a future wheel regresses, pin the last-known-good 0.3.x that loads qwen35.
llama-cpp-python==0.3.32

# Lightweight CPU embeddings via ONNX (no PyTorch -> small image, fast).
fastembed
faiss-cpu

# API + serving
fastapi
uvicorn[standard]
python-multipart
huggingface_hub
numpy