How can the community create high-quality trillion token scientific datasets from literature for training scientific foundation models? Meet AdaParse: A new adaptive PDF parsing engine that delivers 17x throughput while maintaining extraction accuracy by intelligently matching documents with appropriate parsers and op... See more

PDF RAG Agent using Motia, Docling and Weaviate! 100% Open Source Docling parses and intelligently chunks PDFs, making them LLM-ready in just a few lines of code This PDF RAG agent built using Motia leverages Docling to parse and intelligently chunk PDFs and and ... See more