yobix-ai/extractous

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1772 stars · 95 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Extractous is a fast Rust library for extracting content and metadata from unstructured documents like PDF, Word, Excel, HTML, CSV, and email, with bindings for multiple languages including Python. It uses a natively compiled Apache Tika internally for formats not natively supported and is positioned as a much faster alternative to unstructured-io.

Use cases

• extract text from pdf files
• parse docx documents into plain text
• build rag document ingestion pipelines
• extract content from emails and html locally without external apis
• replace unstructured-io for faster document parsing
• preprocess documents for llm pipelines

When to choose

• you need fast, in-process document extraction without calling external services
• performance and memory efficiency matter for large extraction workloads
• you want a Rust core with Python bindings for etl or rag pipelines

When to avoid

• you need deep document structure analysis or chunking strategies rather than raw extraction
• you rely on unstructured-io's element classification features
• you need a managed extraction API service

Facets

library · maturity active

parser ocr pdf etl rag pdf files rust python cross-platform unstructured-data document-extraction apache-tika text-extraction docx bindings natural-language-processing data-engineering retrieval-augmented-generation

Member repositories

For agents

markdown · JSON · MCP: product_card(name="yobix-ai/extractous")