Unstructured
by Unstructured · Unclaimed · API, Tool
Extract and chunk text from PDFs, HTML, emails and 60+ file types.
About
Unstructured turns documents of many formats into structured elements and chunks ready for RAG and agents. Available as a hosted API and as an open-source Python library.
Capabilities
Document Partitioning
Split documents into titles, tables, lists and text elements.
Chunking
Chunk content for embeddings and retrieval.
Many Formats
PDF, DOCX, PPTX, HTML, email and image files.
Pricing
| Plan | Price | Model | Details |
|---|---|---|---|
| Pay-As-You-Go | Not available | Usage Based | Per-page pricing after an initial free page allowance. |
| Open source | Free | Free | Free to self-host (Apache-2.0 license). |
Prices as published by the provider; check their site for current pricing. Provider pricing page ↗
Similar products
Docling
Open-source document conversion: PDF, DOCX and more to markdown or JSON.
Documents · Free
LlamaParse
Parse complex PDFs, slides and spreadsheets into LLM-ready markdown.
Documents · Free
Invoice Extractor (Demo)
Sample listing: extract vendor, totals and line items from invoice PDFs.
Documents · $0.02/document · Demo