# This file was autogenerated by uv via the following command: # uv pip compile pyproject.toml -o requirements.txt aiofiles==24.1.0 # via gradio aiohappyeyeballs==2.6.1 # via aiohttp aiohttp==3.11.18 # via vllm aiosignal==1.3.2 # via aiohttp airportsdata==20250224 # via outlines annotated-types==0.7.0 # via pydantic anyio==4.9.0 # via # google-genai # gradio # httpx # openai # starlette # watchfiles astor==0.8.1 # via depyf attrs==25.3.0 # via # aiohttp # jsonschema # referencing blake3==1.0.4 # via vllm cachetools==5.5.2 # via # google-auth # vllm certifi==2025.4.26 # via # httpcore # httpx # requests charset-normalizer==3.4.2 # via requests click==8.1.8 # via # ray # rich-toolkit # typer # uvicorn cloudpickle==3.1.1 # via # outlines # vllm coloredlogs==15.0.1 # via onnxruntime-gpu compressed-tensors==0.9.3 # via vllm cupy-cuda12x==13.4.1 # via ray deprecated==1.2.18 # via # opentelemetry-api # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http # opentelemetry-semantic-conventions depyf==0.18.0 # via vllm dill==0.4.0 # via depyf diskcache==5.6.3 # via outlines distro==1.9.0 # via openai dnspython==2.7.0 # via email-validator einops==0.8.1 # via vllm email-validator==2.2.0 # via fastapi fastapi==0.115.12 # via # gradio # vllm fastapi-cli==0.0.7 # via fastapi fastembed-gpu==0.6.1 # via qdrant-client fastrlock==0.8.3 # via cupy-cuda12x ffmpy==0.5.0 # via gradio filelock==3.18.0 # via # huggingface-hub # ray # torch # transformers # vllm flatbuffers==25.2.10 # via onnxruntime-gpu frozenlist==1.6.0 # via # aiohttp # aiosignal fsspec==2025.3.2 # via # gradio-client # huggingface-hub # torch gguf==0.16.2 # via vllm google-auth==2.39.0 # via google-genai google-genai==1.13.0 # via sdmrec-demo (pyproject.toml) googleapis-common-protos==1.70.0 # via # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http gradio==5.29.0 # via sdmrec-demo (pyproject.toml) gradio-client==1.10.0 # via gradio groovy==0.1.2 # via gradio grpcio==1.71.0 # via # opentelemetry-exporter-otlp-proto-grpc # qdrant-client h11==0.16.0 # via # httpcore # uvicorn h2==4.2.0 # via httpx hf-xet==1.1.0 # via huggingface-hub hpack==4.1.0 # via h2 httpcore==1.0.9 # via httpx httptools==0.6.4 # via uvicorn httpx==0.28.1 # via # fastapi # google-genai # gradio # gradio-client # openai # qdrant-client # safehttpx huggingface-hub==0.30.2 # via # fastembed-gpu # gradio # gradio-client # sentence-transformers # tokenizers # transformers # vllm humanfriendly==10.0 # via coloredlogs hyperframe==6.1.0 # via h2 idna==3.10 # via # anyio # email-validator # httpx # requests # yarl importlib-metadata==8.0.0 # via # opentelemetry-api # vllm interegular==0.3.3 # via # lm-format-enforcer # outlines # outlines-core jinja2==3.1.6 # via # fastapi # gradio # outlines # torch jiter==0.9.0 # via openai joblib==1.5.0 # via scikit-learn jsonschema==4.23.0 # via # mistral-common # outlines # outlines-core # ray jsonschema-specifications==2025.4.1 # via jsonschema lark==1.2.2 # via # outlines # vllm llguidance==0.7.19 # via vllm llvmlite==0.44.0 # via numba lm-format-enforcer==0.10.11 # via vllm loguru==0.7.3 # via fastembed-gpu markdown-it-py==3.0.0 # via rich markupsafe==3.0.2 # via # gradio # jinja2 mdurl==0.1.2 # via markdown-it-py mistral-common==1.5.4 # via vllm mmh3==5.1.0 # via fastembed-gpu mpmath==1.3.0 # via sympy msgpack==1.1.0 # via ray msgspec==0.19.0 # via vllm multidict==6.4.3 # via # aiohttp # yarl nest-asyncio==1.6.0 # via outlines networkx==3.4.2 # via torch ninja==1.11.1.4 # via # vllm # xgrammar numba==0.61.2 # via vllm numpy==2.2.5 # via # cupy-cuda12x # fastembed-gpu # gguf # gradio # mistral-common # numba # onnxruntime-gpu # opencv-python-headless # outlines # pandas # qdrant-client # scikit-learn # scipy # torchvision # transformers # vllm # xformers nvidia-cublas-cu12==12.4.5.8 # via # nvidia-cudnn-cu12 # nvidia-cusolver-cu12 # torch nvidia-cuda-cupti-cu12==12.4.127 # via torch nvidia-cuda-nvrtc-cu12==12.4.127 # via torch nvidia-cuda-runtime-cu12==12.4.127 # via torch nvidia-cudnn-cu12==9.1.0.70 # via torch nvidia-cufft-cu12==11.2.1.3 # via torch nvidia-curand-cu12==10.3.5.147 # via torch nvidia-cusolver-cu12==11.6.1.9 # via torch nvidia-cusparse-cu12==12.3.1.170 # via # nvidia-cusolver-cu12 # torch nvidia-cusparselt-cu12==0.6.2 # via torch nvidia-nccl-cu12==2.21.5 # via torch nvidia-nvjitlink-cu12==12.4.127 # via # nvidia-cusolver-cu12 # nvidia-cusparse-cu12 # torch nvidia-nvtx-cu12==12.4.127 # via torch onnxruntime-gpu==1.21.1 # via fastembed-gpu openai==1.77.0 # via vllm opencv-python-headless==4.11.0.86 # via # mistral-common # vllm opentelemetry-api==1.26.0 # via # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http # opentelemetry-sdk # opentelemetry-semantic-conventions # vllm opentelemetry-exporter-otlp==1.26.0 # via vllm opentelemetry-exporter-otlp-proto-common==1.26.0 # via # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http opentelemetry-exporter-otlp-proto-grpc==1.26.0 # via opentelemetry-exporter-otlp opentelemetry-exporter-otlp-proto-http==1.26.0 # via opentelemetry-exporter-otlp opentelemetry-proto==1.26.0 # via # opentelemetry-exporter-otlp-proto-common # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http opentelemetry-sdk==1.26.0 # via # opentelemetry-exporter-otlp-proto-grpc # opentelemetry-exporter-otlp-proto-http # vllm opentelemetry-semantic-conventions==0.47b0 # via opentelemetry-sdk opentelemetry-semantic-conventions-ai==0.4.5 # via vllm orjson==3.10.18 # via gradio outlines==0.1.11 # via vllm outlines-core==0.1.26 # via outlines packaging==25.0 # via # gradio # gradio-client # huggingface-hub # lm-format-enforcer # onnxruntime-gpu # ray # transformers pandas==2.2.3 # via # sdmrec-demo (pyproject.toml) # gradio partial-json-parser==0.2.1.1.post5 # via vllm pillow==11.2.1 # via # fastembed-gpu # gradio # mistral-common # sentence-transformers # torchvision # vllm portalocker==2.10.1 # via qdrant-client prometheus-client==0.21.1 # via # prometheus-fastapi-instrumentator # vllm prometheus-fastapi-instrumentator==7.1.0 # via vllm propcache==0.3.1 # via # aiohttp # yarl protobuf==4.25.7 # via # googleapis-common-protos # onnxruntime-gpu # opentelemetry-proto # qdrant-client # ray # vllm psutil==7.0.0 # via vllm py-cpuinfo==9.0.0 # via vllm py-rust-stemmers==0.1.5 # via fastembed-gpu pyarrow==20.0.0 # via sdmrec-demo (pyproject.toml) pyasn1==0.6.1 # via # pyasn1-modules # rsa pyasn1-modules==0.4.2 # via google-auth pycountry==24.6.1 # via outlines pydantic==2.11.4 # via # sdmrec-demo (pyproject.toml) # compressed-tensors # fastapi # google-genai # gradio # lm-format-enforcer # mistral-common # openai # outlines # qdrant-client # vllm # xgrammar pydantic-core==2.33.2 # via pydantic pydub==0.25.1 # via gradio pygments==2.19.1 # via rich python-dateutil==2.9.0.post0 # via pandas python-dotenv==1.1.0 # via uvicorn python-json-logger==3.3.0 # via vllm python-multipart==0.0.20 # via # fastapi # gradio pytz==2025.2 # via pandas pyyaml==6.0.2 # via # gguf # gradio # huggingface-hub # lm-format-enforcer # ray # transformers # uvicorn # vllm pyzmq==26.4.0 # via vllm qdrant-client==1.14.2 # via sdmrec-demo (pyproject.toml) ray==2.45.0 # via vllm referencing==0.36.2 # via # jsonschema # jsonschema-specifications # outlines regex==2024.11.6 # via # tiktoken # transformers requests==2.32.3 # via # fastembed-gpu # google-genai # huggingface-hub # mistral-common # opentelemetry-exporter-otlp-proto-http # outlines # ray # tiktoken # transformers # vllm rich==14.0.0 # via # rich-toolkit # typer rich-toolkit==0.14.5 # via fastapi-cli rpds-py==0.24.0 # via # jsonschema # referencing rsa==4.9.1 # via google-auth ruff==0.11.8 # via gradio safehttpx==0.1.6 # via gradio safetensors==0.5.3 # via transformers scikit-learn==1.6.1 # via sentence-transformers scipy==1.15.2 # via # scikit-learn # sentence-transformers # vllm semantic-version==2.10.0 # via gradio sentence-transformers==4.1.0 # via sdmrec-demo (pyproject.toml) sentencepiece==0.2.0 # via # gguf # mistral-common # vllm # xgrammar setuptools==80.3.1 # via # torch # vllm shellingham==1.5.4 # via typer six==1.17.0 # via # python-dateutil # vllm sniffio==1.3.1 # via # anyio # openai starlette==0.46.2 # via # fastapi # gradio # prometheus-fastapi-instrumentator sympy==1.13.1 # via # onnxruntime-gpu # torch threadpoolctl==3.6.0 # via scikit-learn tiktoken==0.9.0 # via # mistral-common # vllm # xgrammar tokenizers==0.21.1 # via # fastembed-gpu # transformers # vllm tomlkit==0.13.2 # via gradio torch==2.6.0 # via # compressed-tensors # outlines # sentence-transformers # torchaudio # torchvision # vllm # xformers # xgrammar torchaudio==2.6.0 # via vllm torchvision==0.21.0 # via vllm tqdm==4.67.1 # via # fastembed-gpu # gguf # huggingface-hub # openai # outlines # sentence-transformers # transformers # vllm transformers==4.51.3 # via # compressed-tensors # sentence-transformers # vllm # xgrammar triton==3.2.0 # via # torch # xgrammar typer==0.15.3 # via # fastapi-cli # gradio typing-extensions==4.13.2 # via # anyio # fastapi # google-genai # gradio # gradio-client # huggingface-hub # mistral-common # openai # opentelemetry-sdk # outlines # pydantic # pydantic-core # referencing # rich-toolkit # sentence-transformers # torch # typer # typing-inspection # vllm typing-inspection==0.4.0 # via pydantic tzdata==2025.2 # via pandas urllib3==2.4.0 # via # qdrant-client # requests uvicorn==0.34.2 # via # fastapi # fastapi-cli # gradio uvloop==0.21.0 # via uvicorn vllm==0.8.5.post1 # via sdmrec-demo (pyproject.toml) watchfiles==1.0.5 # via # uvicorn # vllm websockets==15.0.1 # via # google-genai # gradio-client # uvicorn wrapt==1.17.2 # via deprecated xformers==0.0.29.post2 # via vllm xgrammar==0.1.18 # via vllm yarl==1.20.0 # via aiohttp zipp==3.21.0 # via importlib-metadata