Overview
Documind is a document processing tool that uses AI to extract structured data from PDFs. It is built to handle PDF conversions, extract relevant information, and format results as specified by customizable schemas. The project provides features such as extracting structured JSON output from unstructured documents, converting documents into Markdown format, and supporting custom schemas for data extraction.
Documind includes pre-defined templates for common schemas and works with OpenAI and custom LLM setups such as Llava and Llama3.2-vision. It can auto-generate schemas based on document content. A hosted version is offered with fully managed APIs, and users can join the beta to access the hosted service.
Released features include PDF extraction, basic schema definition, structured JSON output, template schemas, local LLM integration with Llama3.2, auto-generated schemas, document formatters for text and Markdown, multi-file support for DOCX, PNG, JPG, TXT, and HTML, and additional schema field types such as Boolean and Enum. Upcoming features listed are additional models, image extraction, advanced document formatters, data classification, and use of fine-tuned models.
Documind requires Ghostscript and GraphicsMagick for PDF and image processing, plus Node.js v18+ and NPM. It can be installed via npm, requires an .env file with an OpenAI API key, and is licensed under AGPL v3.0. The repository was built on top of Zerox.
Pricing
Free
Detailed plans have not been confirmed in our catalog. Check the official website for current limits and billing terms.
Visit WebsitePrices and limits may change. Confirm the currency, billing period, seat minimum and usage caps on the official website.
Use Cases
- Teams use Documind to extract structured JSON output from unstructured documents.
- Teams use Documind to convert documents into Markdown format.
- Teams use Documind to extract data using custom schemas.
- Teams use Documind to process common document types with built-in templates.
- Teams use Documind to auto-generate schemas based on document content.
- Teams use Documind to work with OpenAI and custom LLM setups.
- Teams use Documind to process multiple file types including DOCX, PNG, JPG, TXT, and HTML.
- Teams use Documind to extract data from PDFs.
Features
Open-source document processing
Structured data extraction from PDFs
Data extraction from other files
Configurable AI extraction schemas
Document question answering
Reviews
No reviews yet. Be the first to share your experience!