Skip to content

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

302 B
Raw Blame
# Install torch/torchvision for the target CPU/CUDA/MPS platform separately.
# Versions below match the WeMM model card and the validated service environment.
transformers==5.2.0
qwen-vl-utils==0.0.14
accelerate>=1.1.0,<2
fastapi>=0.115,<1
pydantic>=2,<3
uvicorn>=0.30,<1
pillow>=10,<13
httpx>=0.27,<1