DocumindHQ/documind

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

1521 stars · 63 forks observed · 2026-08-28

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

Documind is an open-source Node.js library that uses AI/LLMs to extract structured JSON data from PDFs and other documents based on customizable schemas. It supports OpenAI as well as local vision models (Llava, Llama3.2-vision) and converts documents to Markdown.

Use cases

• extract structured data from pdf documents
• parse bank statements into
• convert pdfs to markdown
• auto-generate extraction schemas from documents
• run document extraction with local llms
• extract fields from invoices or receipts with a custom schema

When to choose

• you need schema-driven structured JSON output from unstructured documents
• you want an npm library that works with OpenAI or local vision models
• you need multi-format support (PDF, DOCX, PNG, JPG, TXT, HTML)

When to avoid

• you need a fully managed hosted extraction API without self-setup
• you require a non-AGPL license for commercial embedding
• you need high-throughput OCR without LLM costs

Facets

library · maturity active

ocr parser pdf llm-inference nlp machine-learning artificial-intelligence large-language-models pdf files developer-tools cross-platform cli document-extraction structured-data pdf-to- schema-driven-extraction llm openai local-llm markdown-conversion natural-language-processing nodejs

Member repositories

For agents

markdown · JSON · MCP: product_card(name="DocumindHQ/documind")