Future-House/paper-qa: High accuracy RAG for answering questions from scientific documents with citations
PaperQA2 is a high-accuracy retrieval augmented generation (RAG) tool designed for answering questions from scientific documents. It automates metadata retrieval, parses and indexes PDFs, and uses LLM agents to generate responses with in-text citations. The tool supports OpenAI embeddings and can be customized with different models. Users can easily install PaperQA2 via pip and use it to index and search through scientific papers. It includes features like automatic citation extraction, document metadata-awareness, and customizable settings.