easydoc-ai/easydoc

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1115 stars · 11 forks observed · 2026-08-28

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

EasyDoc is a multimodal document processing API that converts unstructured documents like PDFs into hierarchical, machine-readable JSON. It identifies content blocks, reconstructs document structure, and parses tables and figures to feed LLM pipelines with optimized context.

Use cases

• convert pdf documents to structured json for llm pipelines
• extract tables and figures from documents into machine-readable format
• parse resumes and reports into hierarchical data
• prepare fine-tuning datasets from unstructured documents
• build rag pipelines over pdf documents
• reconstruct document hierarchy into mind maps for ai context

When to choose

• you need high-quality structured extraction from complex pdfs with tables and figures
• you want an api-based document parser purpose-built for llm and rag applications
• you need content-block grouping rather than raw line-by-line text extraction

When to avoid

• you need fully offline processing without calling a hosted api
• you only need simple plain-text extraction from pdfs
• you require a self-contained library with no external service dependency

Facets

service · maturity active

parser ocr pdf rag llm-inference nlp pdf artificial-intelligence large-language-models apis cloud python self-hosted document-parsing multimodal document-to-json llm-pipelines document-processing-api hierarchical-json table-extraction retrieval-augmented-generation data-engineering web-server

Member repositories

For agents

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