GH Repository · enoch3712
ExtractThinker
ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction for flexible and powerful document workflows.
- stars
- 1,598
- 30-day movement
- starts with the next reading
- Related entries
- 60
- Connections
- 1
python/poetryagent-frameworkpdf-to-textainlpocropenaillmpythonmachine-learningdocument-image-analysisdocument-intelligencedocument-parsingPythondocument-processingpdflangchain
ExtractThinker is a Python Document Intelligence library for LLMs that provides ORM-style interaction for building document workflows. Its topics indicate support for OCR, PDF-to-text parsing, and document processing, with references to OpenAI and LangChain.
Reach for it when you want structured, ORM-like handling of document extraction pipelines powered by LLMs.
Use it to
- Parse PDFs into structured data with LLMs
- Run OCR on document images
- Build document processing workflows
- Integrate extraction with LangChain pipelines
For Python developers building LLM-based document extraction pipelines
- Role
- agent-framework
- Language
- Python
- Licence
- Apache-2.0
- Forks
- 153
- Last push
- 2026-09-16
- Latest release
- v0.0.2 · 2024-05-20
topicsdocument-intelligencellmocrpdfpythonlangchain