Document Loaders
Every retrieval pipeline starts by turning some external source — a PDF, a web page, a database table — into LangChain's shared unit: the Document.
Every retrieval pipeline starts by turning some external source — a PDF, a web page, a database table — into LangChain's shared unit: the Document.
A citation-aware version of the RAG pipeline: load a folder of PDFs, chunk them while keeping page numbers, embed into Chroma, and answer with a reference back to the source page.