Retrieval Augmented Generation (RAG)

Summarizing Reviews at Scale: Leveraging LLM, Pinecone, and LangChain with Konko AI.

This is a guide about synthesizing reviews at scale using an LLM (via Konko AI), a vector database (pinecone) and LangChain.

Specifically, we will use Retrieval Augmented Generation (RAG) to give Llama 2 the context it needs to summarize customer reviews for two products from Amazon (2k+ reviews each).

πŸ“Œ Code Notebook