easydoc  by easydoc-ai

Multimodal document processing API for LLM pipelines

created 7 months ago
1,107 stars

Top 35.2% on sourcepulse

GitHubView on GitHub
Project Summary

EasyDoc provides a multimodal document processing API designed to convert unstructured documents into structured, hierarchical JSON. This platform is targeted at developers building AI and LLM applications, offering enriched data for model inference, fine-tuning, and optimized context windows by identifying content blocks and extracting semantic information.

How It Works

EasyDoc employs AI to parse documents, moving beyond simple text extraction to identify meaningful content blocks and reconstruct document hierarchies. It supports multimodal content, converting tables, figures, and visual data into machine-readable JSON, enabling LLMs to process complex information more effectively.

Quick Start & Requirements

Highlighted Details

  • Content block identification for meaningful data grouping.
  • Semantic extraction to reconstruct document hierarchies.
  • Multimodal parsing of tables, figures, and visual data into JSON.
  • Offers "Lite" and "Pro" modes, with a "Premium" beta.

Maintenance & Community

Licensing & Compatibility

  • Licensing: Not specified in the README.
  • Compatibility: REST API is language-agnostic.

Limitations & Caveats

The "Premium" tier is in beta with a waitlist for API keys. Pricing is per 1000 pages, with different rates for Lite and Pro modes.

Health Check
Last commit

3 weeks ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
0
Star History
958 stars in the last 90 days

Explore Similar Projects

Starred by Chip Huyen Chip Huyen(Author of AI Engineering, Designing Machine Learning Systems) and Elie Bursztein Elie Bursztein(Cybersecurity Lead at Google DeepMind).

LightRAG by HKUDS

1.0%
19k
RAG framework for fast, simple retrieval-augmented generation
created 10 months ago
updated 23 hours ago
Feedback? Help us improve.