RAG-on-PDF-LLM
PublicA repository for setting up and initializing LLM using langcahain and HuggingFace, generating document embeddings, and connecting to Pinecone for vector database operations. Includes an example of using a Retrieval-Augmented Generation (RAG) model.
huggingfacehuggingface-transformerslangchain-pythonlarge-language-modelsllama3pineconedbpython3retrieval-augmented-generation
Creat：2024-05-22T06:07:30
Update：2024-06-08T08:30:06
1
Stars
0
Stars Increase