Retrieval Augmented Generation (RAG) is an AI framework for retrieving facts from an external knowledge base to ground large language models (LLMs) on the most accurate and up-to-date information. In this accelerator we convert documents from HTML, PDF, DOC or PPT to plain text, import document segments into an Elasticsearch vector index, deploy a python function that queries the vector index, retrieves top N results, and runs LLM inference (prompts are supplied for both llama2 and granite models) to generate an answer to the question and checks the answer for hallucinations.
Click Create project to get started or Log In. Don't have an account yet? Sign Up for a free account.