Unstructured

API

Document parsing API and open-source library that turn files into LLM-ready data

Fiyat: Free credits, then pay per use
Erişim: Unstructured API key

Hakkında

Unstructured Transform is a hosted API and MCP server that parses PDFs, Office files and images into markdown or elements and extracts fields with a JSON schema. An Apache-2.0 Python library also runs locally. The API takes one file of up to 50 MB per request.

Neler yapabilirsin

Parse PDFs, DOCX, PPTX and scanned images into markdown or typed elements
Extract fields from invoices and other documents into JSON with a schema
Partition, chunk and embed files for RAG from an agent over MCP

Başlarken

Sign in at transform.unstructured.io (first 10,000 pages free)
Create an API key under API keys

Örnek kod

curl https://transform.unstructured.io/api/v2/parse \
  -H "unstructured-api-key: $UNSTRUCTURED_API_KEY" \
  -F "input=@document.pdf"

Ayrıntılar

Barındırma: Hazır hizmet (bulut), Kendi sunucunda, Kendi bilgisayarında
Kullanılabildiği yerler: Tüm dünya
Resmi SDK'lar: Python, JavaScript/TypeScript
MCP sunucusu: Uzak sunucu