# This file was autogenerated by uv via the following command:
#    uv export --no-emit-project --no-default-groups --no-hashes --group model_server -o backend/requirements/model_server.txt
accelerate==1.6.0
agent-client-protocol==0.7.1
    # via onyx
aioboto3==15.1.0
    # via onyx
aiobotocore==2.24.0
    # via aioboto3
aiofiles==25.1.0
    # via aioboto3
aiohappyeyeballs==2.6.1
    # via aiohttp
aiohttp==3.13.4
    # via
    #   aiobotocore
    #   discord-py
    #   litellm
    #   voyageai
aioitertools==0.13.0
    # via aiobotocore
aiolimiter==1.2.1
    # via voyageai
aiosignal==1.4.0
    # via aiohttp
amqp==5.3.1
    # via kombu
annotated-doc==0.0.4
    # via fastapi
annotated-types==0.7.0
    # via pydantic
anyio==4.11.0
    # via
    #   claude-agent-sdk
    #   google-genai
    #   httpx
    #   mcp
    #   openai
    #   sse-starlette
    #   starlette
attrs==25.4.0
    # via
    #   aiohttp
    #   jsonschema
    #   referencing
billiard==4.2.3
    # via celery
boto3==1.39.11
    # via
    #   aiobotocore
    #   cohere
botocore==1.39.11
    # via
    #   aiobotocore
    #   boto3
    #   s3transfer
brotli==1.2.0
    # via onyx
celery==5.5.1
    # via sentry-sdk
certifi==2025.11.12
    # via
    #   httpcore
    #   httpx
    #   kubernetes
    #   requests
    #   sentry-sdk
cffi==2.0.0 ; platform_python_implementation != 'PyPy'
    # via cryptography
charset-normalizer==3.4.4
    # via requests
claude-agent-sdk==0.1.19
    # via onyx
click==8.3.1
    # via
    #   celery
    #   click-didyoumean
    #   click-plugins
    #   click-repl
    #   litellm
    #   typer
    #   uvicorn
click-didyoumean==0.3.1
    # via celery
click-plugins==1.1.1.2
    # via celery
click-repl==0.3.0
    # via celery
cohere==5.6.1
    # via onyx
colorama==0.4.6 ; sys_platform == 'win32'
    # via
    #   click
    #   tqdm
cryptography==46.0.7
    # via
    #   google-auth
    #   pyjwt
decorator==5.2.1
    # via retry
discord-py==2.4.0
    # via onyx
distro==1.9.0
    # via openai
docstring-parser==0.17.0
    # via google-cloud-aiplatform
durationpy==0.10
    # via kubernetes
einops==0.8.1
fastapi==0.133.1
    # via
    #   onyx
    #   sentry-sdk
fastavro==1.12.1
    # via cohere
fastuuid==0.14.0
    # via litellm
filelock==3.20.3
    # via
    #   huggingface-hub
    #   torch
frozenlist==1.8.0
    # via
    #   aiohttp
    #   aiosignal
fsspec==2025.10.0
    # via
    #   huggingface-hub
    #   torch
google-api-core==2.28.1
    # via
    #   google-cloud-aiplatform
    #   google-cloud-bigquery
    #   google-cloud-core
    #   google-cloud-resource-manager
    #   google-cloud-storage
google-auth==2.48.0
    # via
    #   google-api-core
    #   google-cloud-aiplatform
    #   google-cloud-bigquery
    #   google-cloud-core
    #   google-cloud-resource-manager
    #   google-cloud-storage
    #   google-genai
    #   kubernetes
google-cloud-aiplatform==1.133.0
    # via litellm
google-cloud-bigquery==3.41.0
    # via google-cloud-aiplatform
google-cloud-core==2.5.1
    # via
    #   google-cloud-bigquery
    #   google-cloud-storage
google-cloud-resource-manager==1.17.0
    # via google-cloud-aiplatform
google-cloud-storage==3.10.1
    # via google-cloud-aiplatform
google-crc32c==1.8.0
    # via
    #   google-cloud-storage
    #   google-resumable-media
google-genai==1.52.0
    # via
    #   google-cloud-aiplatform
    #   onyx
google-resumable-media==2.8.2
    # via
    #   google-cloud-bigquery
    #   google-cloud-storage
googleapis-common-protos==1.72.0
    # via
    #   google-api-core
    #   grpc-google-iam-v1
    #   grpcio-status
grpc-google-iam-v1==0.14.4
    # via google-cloud-resource-manager
grpcio==1.80.0
    # via
    #   google-api-core
    #   google-cloud-resource-manager
    #   googleapis-common-protos
    #   grpc-google-iam-v1
    #   grpcio-status
grpcio-status==1.80.0
    # via google-api-core
h11==0.16.0
    # via
    #   httpcore
    #   uvicorn
hf-xet==1.4.3 ; platform_machine == 'AMD64' or platform_machine == 'aarch64' or platform_machine == 'amd64' or platform_machine == 'arm64' or platform_machine == 'x86_64'
    # via huggingface-hub
httpcore==1.0.9
    # via httpx
httpx==0.28.1
    # via
    #   cohere
    #   google-genai
    #   huggingface-hub
    #   litellm
    #   mcp
    #   openai
httpx-sse==0.4.3
    # via
    #   cohere
    #   mcp
huggingface-hub==1.12.0
    # via
    #   accelerate
    #   sentence-transformers
    #   tokenizers
    #   transformers
idna==3.11
    # via
    #   anyio
    #   httpx
    #   requests
    #   yarl
importlib-metadata==8.7.0
    # via litellm
jinja2==3.1.6
    # via
    #   litellm
    #   torch
jiter==0.12.0
    # via openai
jmespath==1.0.1
    # via
    #   aiobotocore
    #   boto3
    #   botocore
joblib==1.5.2
    # via scikit-learn
jsonschema==4.25.1
    # via
    #   litellm
    #   mcp
jsonschema-specifications==2025.9.1
    # via jsonschema
kombu==5.5.4
    # via celery
kubernetes==31.0.0
    # via onyx
litellm==1.83.0
    # via onyx
markdown-it-py==4.0.0
    # via rich
markupsafe==3.0.3
    # via jinja2
mcp==1.27.0
    # via claude-agent-sdk
mdurl==0.1.2
    # via markdown-it-py
mpmath==1.3.0
    # via sympy
multidict==6.7.0
    # via
    #   aiobotocore
    #   aiohttp
    #   yarl
networkx==3.5
    # via torch
numpy==2.4.1
    # via
    #   accelerate
    #   scikit-learn
    #   scipy
    #   sentence-transformers
    #   transformers
    #   voyageai
nvidia-cublas-cu12==12.8.4.1 ; platform_machine == 'x86_64' and sys_platform == 'linux'
    # via
    #   nvidia-cudnn-cu12
    #   nvidia-cusolver-cu12
    #   torch
nvidia-cuda-cupti-cu12==12.8.90 ; platform_machine == 'x86_64' and sys_platform == 'linux'
    # via torch
nvidia-cuda-nvrtc-cu12==12.8.93 ; platform_machine == 'x86_64' and sys_platform == 'linux'
    # via torch
nvidia-cuda-runtime-cu12==12.8.90 ; platform_machine == 'x86_64' and sys_platform == 'linux'
    # via torch
nvidia-cudnn-cu12==9.10.2.21 ; platform_machine == 'x86_64' and sys_platform == 'linux'
    # via torch
nvidia-cufft-cu12==11.3.3.83 ; platform_machine == 'x86_64' and sys_platform == 'linux'
    # via torch
nvidia-cufile-cu12==1.13.1.3 ; platform_machine == 'x86_64' and sys_platform == 'linux'
    # via torch
nvidia-curand-cu12==10.3.9.90 ; platform_machine == 'x86_64' and sys_platform == 'linux'
    # via torch
nvidia-cusolver-cu12==11.7.3.90 ; platform_machine == 'x86_64' and sys_platform == 'linux'
    # via torch
nvidia-cusparse-cu12==12.5.8.93 ; platform_machine == 'x86_64' and sys_platform == 'linux'
    # via
    #   nvidia-cusolver-cu12
    #   torch
nvidia-cusparselt-cu12==0.7.1 ; platform_machine == 'x86_64' and sys_platform == 'linux'
    # via torch
nvidia-nccl-cu12==2.27.5 ; platform_machine == 'x86_64' and sys_platform == 'linux'
    # via torch
nvidia-nvjitlink-cu12==12.8.93 ; platform_machine == 'x86_64' and sys_platform == 'linux'
    # via
    #   nvidia-cufft-cu12
    #   nvidia-cusolver-cu12
    #   nvidia-cusparse-cu12
    #   torch
nvidia-nvshmem-cu12==3.3.20 ; platform_machine == 'x86_64' and sys_platform == 'linux'
    # via torch
nvidia-nvtx-cu12==12.8.90 ; platform_machine == 'x86_64' and sys_platform == 'linux'
    # via torch
oauthlib==3.2.2
    # via
    #   kubernetes
    #   requests-oauthlib
openai==2.14.0
    # via
    #   litellm
    #   onyx
packaging==24.2
    # via
    #   accelerate
    #   google-cloud-aiplatform
    #   google-cloud-bigquery
    #   huggingface-hub
    #   kombu
    #   transformers
parameterized==0.9.0
    # via cohere
prometheus-client==0.23.1
    # via
    #   onyx
    #   prometheus-fastapi-instrumentator
prometheus-fastapi-instrumentator==7.1.0
    # via onyx
prompt-toolkit==3.0.52
    # via click-repl
propcache==0.4.1
    # via
    #   aiohttp
    #   yarl
proto-plus==1.26.1
    # via
    #   google-api-core
    #   google-cloud-aiplatform
    #   google-cloud-resource-manager
protobuf==6.33.5
    # via
    #   google-api-core
    #   google-cloud-aiplatform
    #   google-cloud-resource-manager
    #   googleapis-common-protos
    #   grpc-google-iam-v1
    #   grpcio-status
    #   proto-plus
psutil==7.1.3
    # via accelerate
py==1.11.0
    # via retry
pyasn1==0.6.3
    # via
    #   pyasn1-modules
    #   rsa
pyasn1-modules==0.4.2
    # via google-auth
pycparser==2.23 ; implementation_name != 'PyPy' and platform_python_implementation != 'PyPy'
    # via cffi
pydantic==2.11.7
    # via
    #   agent-client-protocol
    #   cohere
    #   fastapi
    #   google-cloud-aiplatform
    #   google-genai
    #   litellm
    #   mcp
    #   onyx
    #   openai
    #   pydantic-settings
pydantic-core==2.33.2
    # via pydantic
pydantic-settings==2.12.0
    # via mcp
pygments==2.20.0
    # via rich
pyjwt==2.12.0
    # via mcp
python-dateutil==2.8.2
    # via
    #   aiobotocore
    #   botocore
    #   celery
    #   google-cloud-bigquery
    #   kubernetes
python-dotenv==1.2.2
    # via
    #   litellm
    #   pydantic-settings
python-multipart==0.0.26
    # via mcp
pywin32==311 ; sys_platform == 'win32'
    # via mcp
pyyaml==6.0.3
    # via
    #   accelerate
    #   huggingface-hub
    #   kubernetes
    #   transformers
referencing==0.37.0
    # via
    #   jsonschema
    #   jsonschema-specifications
regex==2025.11.3
    # via
    #   tiktoken
    #   transformers
requests==2.33.0
    # via
    #   cohere
    #   google-api-core
    #   google-cloud-bigquery
    #   google-cloud-storage
    #   google-genai
    #   kubernetes
    #   requests-oauthlib
    #   tiktoken
    #   voyageai
requests-oauthlib==1.3.1
    # via kubernetes
retry==0.9.2
    # via onyx
rich==14.2.0
    # via typer
rpds-py==0.29.0
    # via
    #   jsonschema
    #   referencing
rsa==4.9.1
    # via google-auth
s3transfer==0.13.1
    # via boto3
safetensors==0.5.3
    # via
    #   accelerate
    #   transformers
scikit-learn==1.7.2
    # via sentence-transformers
scipy==1.16.3
    # via
    #   scikit-learn
    #   sentence-transformers
sentence-transformers==5.4.1
sentry-sdk==2.14.0
    # via onyx
setuptools==80.9.0 ; python_full_version >= '3.12'
    # via torch
shellingham==1.5.4
    # via typer
six==1.17.0
    # via
    #   kubernetes
    #   python-dateutil
sniffio==1.3.1
    # via
    #   anyio
    #   openai
sse-starlette==3.0.3
    # via mcp
starlette==0.49.3
    # via
    #   fastapi
    #   mcp
    #   prometheus-fastapi-instrumentator
    #   sentry-sdk
sympy==1.14.0
    # via torch
tenacity==9.1.2
    # via
    #   google-genai
    #   voyageai
threadpoolctl==3.6.0
    # via scikit-learn
tiktoken==0.7.0
    # via litellm
tokenizers==0.22.2
    # via
    #   cohere
    #   litellm
    #   transformers
torch==2.9.1
    # via
    #   accelerate
    #   sentence-transformers
tqdm==4.67.1
    # via
    #   huggingface-hub
    #   openai
    #   sentence-transformers
    #   transformers
transformers==5.5.4
    # via sentence-transformers
triton==3.5.1 ; platform_machine == 'x86_64' and sys_platform == 'linux'
    # via torch
typer==0.20.0
    # via
    #   huggingface-hub
    #   transformers
types-requests==2.32.0.20250328
    # via cohere
typing-extensions==4.15.0
    # via
    #   aiosignal
    #   anyio
    #   cohere
    #   fastapi
    #   google-cloud-aiplatform
    #   google-genai
    #   grpcio
    #   huggingface-hub
    #   mcp
    #   openai
    #   pydantic
    #   pydantic-core
    #   referencing
    #   sentence-transformers
    #   starlette
    #   torch
    #   typer
    #   typing-inspection
typing-inspection==0.4.2
    # via
    #   fastapi
    #   mcp
    #   pydantic
    #   pydantic-settings
tzdata==2025.2
    # via kombu
urllib3==2.6.3
    # via
    #   botocore
    #   kubernetes
    #   requests
    #   sentry-sdk
    #   types-requests
uvicorn==0.35.0
    # via
    #   mcp
    #   onyx
vine==5.1.0
    # via
    #   amqp
    #   celery
    #   kombu
voyageai==0.2.3
    # via onyx
wcwidth==0.2.14
    # via prompt-toolkit
websocket-client==1.9.0
    # via kubernetes
websockets==15.0.1
    # via google-genai
wrapt==1.17.3
    # via aiobotocore
yarl==1.23.0
    # via aiohttp
zipp==3.23.0
    # via importlib-metadata
