Deploying Medical-RAG requires the following key steps to be completed:
Preparation of the basic environment
- Cloning Project Warehouse:
git clone https://github.com/yolo-hyl/medical-rag - Install Python dependencies: Go to the src directory and execute the
pip install -e .
Core service startup
- vector database: Start Milvus using the Docker script that comes with the project
cd Milvus bash standalone_embed.sh start - Local modeling services (optional): Loading embedded models and Q&A models via Ollama
ollama pull bge-m3:latest ollama pull qwen2:7b
Configuration file adjustment
modification requiredsrc/MedicalRag/config/default.yamlThe key parameters in the
- Milvus connection address and authentication information
- Embedded model selection (supports Ollama/OpenAI/HuggingFace multiple sources)
- Search strategy and weighting configuration
Once you have completed the above steps, you can pass thepython scripts/search_pipline.pyLaunch the interactive query interface.
This answer comes from the articleMedical-RAG: A Retrieval-Augmented Generation Framework for Constructing Chinese Medical Q&AsThe
May not be reproduced without permission:AI productivity tools " How do I deploy a local test environment for Medical-RAG?
