# easydoc-ai/easydoc

Repository: https://github.com/easydoc-ai/easydoc
Canonical: https://ross.abutalabs.com/products/easydoc
License: MIT
License Family: permissive
Last push: 2025-07-08T09:25:18+00:00

## Health v2 (maintenance only)
Score: 35/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 30, release rhythm 35, longevity 44
- inputs: {"age_days": 616, "days_push": 421, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1115, forks 11 (observed 2026-08-28T04:03:38.443739+00:00)

## What it is
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
- artifact type: service
- maturity: active
- function: parser, ocr, pdf, rag, llm-inference, nlp
- domain: pdf, artificial-intelligence, large-language-models, apis
- platform: cloud, python, self-hosted
- tags: document-parsing, multimodal, document-to-json, llm-pipelines, document-processing-api, hierarchical-json, table-extraction, retrieval-augmented-generation, data-engineering, web-server

## Member repositories
- easydoc-ai/easydoc (main) score 35

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:38.443739+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:42:10.561192+00:00, confidence not recorded.
  - readme: https://github.com/easydoc-ai/easydoc (fetched 2026-08-28T04:03:38.443739+00:00, sha 5bc5540680bd)
- Data as of 2026-08-30T08:39:29.467469+00:00.