RAG & Knowledge ★ 11.0k

Unstructured

Turns PDFs, HTML and scans into clean structured elements your retriever can actually use.

Most failed RAG projects are actually failed parsing projects. Unstructured handles the extraction layer: PDFs, Office files, tables and images, outputting consistent JSON elements with layout metadata preserved.

Best for: PDF/Office ingestion and document parsing

Deploy: Self-hostable

#Document Parsing #Retrieval #Data Pipeline #Open Source

Related tools

RAG & Knowledge ★ 25.4k

WeKnora

Document-to-RAG pipeline in a box, from a team that runs it at Tencent scale.

Teams that need a self-hosted knowledge base over internal documents, especially with Chinese-language corpora Read more →

RAG & Knowledge ★ 184.8k

MarkItDown

The unglamorous parsing layer that decides whether your RAG works at all.

The ingest stage of any RAG system that touches real office documents Read more →

RAG & Knowledge ★ 44.0k

LlamaIndex

Data framework for ingestion, indexing and retrieval — strongest on document-heavy RAG.

Document-heavy enterprise RAG pipelines Read more →

RAG & Knowledge ★ 21.0k

RAGFlow

End-to-end RAG engine with template-based chunking you can show to a customer.

Teams that need explainable, tunable chunking Read more →