RAG: Document ingestion and search

A retrieval-augmented generation (RAG) system allows you to retrieve relevant information from an external knowledge base and use this information to enhance the response generated by an LLM. This method helps improve the accuracy and relevance of the LLM’s response, especially when dealing with domains that require up-to-date or factual information.

For more information, see the RAG tutorials to create a RAG application with open-source models with BentoML.