ModelRefs / Document Loader — AI Glossary

Document Loader — AI Glossary

A connector that reads raw documents from a source (file system, URL, API, database) and converts them to a standardized text format.

Overview

Document loaders handle format heterogeneity: PDFs (PyMuPDF, pdfplumber), HTML (BeautifulSoup), DOCX, CSV, JSON, Confluence, Notion, Google Drive, SharePoint. LangChain and LlamaIndex provide 200+ loader integrations. Output: Document objects with page_content and metadata fields ready for splitting and embedding.

Reference details

Topicrag
Last reviewed2026-06-24

Commonly confused with

Runs before any of this: it reads a source and produces text, where the splitter divides that text. Confusing the two hides the most common RAG failure — a PDF loader that returns garbled column order or drops table structure means the chunks were wrong before chunking began. When retrieval quality is poor, read the loader's raw output before touching chunk size.

Continue your research

Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Document Loader — AI Glossary.

Frequently asked questions

What is Document Loader?

A connector that reads raw documents from a source (file system, URL, API, database) and converts them to a standardized text format.

What concepts are related to Document Loader?

Closely related concepts include indexing pipeline, text splitter, retrieval pipeline.