CodeGeeX4 supports RAG functionality and is compatible with the Langchain framework to achieve project-level retrieval Q&A.
Navigate to the langchain_demo directory and install the required packages.
cd langchain_demo
pip install -r requirements.txtThis project uses the Embedding API from the Zhipu Open Platform for vectorization. Please register and obtain an API Key first.
Then, configure the API Key in models/embedding.py.
For more details, refer to https://open.bigmodel.cn/dev/api#text_embedding.
python vectorize.py --workspace . --output_path vectors
>>> File vectorization completed, saved to vectorspython chat.py --vector_path vectors
>>> Running on local URL: http://127.0.0.1:8080