Description
Retrieval Augmented Generation (RAG) is an AI framework that retrieves facts from external knowledge bases to provide accurate, up-to-date information to large language models (LLMs). This accelerator converts HTML, PDF, DOC, or PPT documents to plain text, imports document segments into a vector database (Milvus or Elasticsearch). It deploys a Python function that queries this index, retrieves the top N results and runs LLM inference using prompts for various models to generate and verify answers for hallucinations. A feedback log collects usage data and user feedback, complemented by a notebook for insights. Click Create a project to get started or Log In. Don't have an account yet? Sign Up for a free account.