Find companies offering a document-parsing API with an official Python SDK committed to in the last 90 days and a public status page.

On-premise Windows ID Document Recognition SDK for parsing passports, ID cards, and driver licenses. Extracts OCR, MRZ, barcode, and QR data with document detection and face extraction. Local HTTP REST API + Python bindings. No cloud, full data privacy.

Official Python SDK for the Arina Document Intelligence API — schema-driven extraction with citations, layout parsing, and reusable extractors.

OCR-aware document classification and field extraction with provenance, CLI, API, and TS SDK

Standalone Python SDK for local PDF and document processing — OCR, text and structured extraction, Markdown, searchable PDFs, and PDF markup.

Multi-agent trade document pipeline — vision extraction, rule validation, and decision routing (LangGraph + Claude Agent SDK), with FastAPI, SQLite persistence, crash resume, and a grounded NL-to-SQL query layer

A Python client for the Parseur's document parser API. Create extraction workflows, manage mailboxes, documents, uploads, and listen for new parsing events.

Open, independent benchmark on document parsing APIs and frontier VLMs for AI agents and RAG: does a struck-out clause in a redlined contract PDF survive the parse? Open source code + open data. LlamaParse, Reducto, Datalab, Extend, Pulse, Mistral OCR, GPT-6 Astra, Claude Fable 5.1.

NaviDC-OCR: This Tiny 1.2B Model Beats Paid OCR APIs (100% Local) - Lightweight 1.2B open-source vision parser for local document & whiteboard OCR.

Give text-only LLMs eyes. A Pi Agent skill + zero-dependency Python CLI that adds image understanding and document parsing (OCR, tables, formulas, PDF → Markdown) to any text-only model such as DeepSeek, using free-tier third-party multimodal APIs.

Self-hosted RAG x LLM Wiki knowledge base framework: document parsing/chunking/vectorization, knowledge graph, hybrid retrieval (vector + graph), multi-tenant API-key isolation, session memory, vision RAG, MCP server. FastAPI + Vue3, data stays on your LAN.

A production-minded, local-network API for the official OvisOCR2 compact 0.8B document parser. Upload a PDF or image and receive reading-order Markdown, HTML tables, LaTeX formulas, and extracted figure regions.

GroupDocs.Parser Cloud MCP server that gives AI assistants the power to parse text, barcodes, and images from 50+ document formats and format families (PDF, Word, Excel) using the robust GroupDocs.Parser Cloud API.

RAG前的文档解析与切片

Document parsing/OCR API powered by unstructured for RunPod serverless

Algorythmos document-processing API — api.algorythmos.fr/docs; multi-tenant files, parse, workflows (FastAPI)

Structural extraction service for Acessilia, providing document parsing and canonical structure through REST API and MCP.

High-throughput document extraction API: multimodal invoice/receipt parsing, Pydantic math validation, Celery workers, and a human review queue.

RAG pipeline for unstructured document intelligence: layout-aware parsing → ChromaDB vector store → dbt medallion architecture → REST API. 87% F1, <30s/doc, live on Streamlit.

AI-powered legal document parser and risk analyzer built with Streamlit, AWS Lambda, API Gateway, and Claude AI. Generates document summaries and identifies legal, financial, compliance, and operational risks from uploaded documents.

An internal tool for automated financial API testing. It can parse API documents and complete the full workflow of test‑case generation, API invocation and assertion with one click.

Backend service for the Tri9T AI Engineering Internship assignment featuring CT-200 PDF parsing, document versioning, hybrid diffing, Gemini-powered QA generation, stale detection, and FastAPI APIs with comprehensive testing.

Local-first document embedding and retrieval platform with a REST API and MCP server for LLM agents. Supports hybrid BM25 + semantic search across workspaces and collections, with pluggable parsers, embedders, and vector stores.

Document parsing API — PDFs, contracts & scans → clean Markdown via one API call

Python client and CLI for the MinerU document parsing API.

API Documentation Agent is an autonomous, version-aware documentation system for FastAPI and OpenAPI 3.x. It maintains synchronization between API source and documentation through deterministic parsing, change intelligence, drift detection, impact reasoning, bounded self-correction, and structured API knowledge memory

Wrapper image for the MinerU CPU document-parsing API Railway template

Logics-Parsing-v2 on AMD ROCm — Apache 2.0 document parsing via vLLM + Python API. OmniDocBench v1.6 Overall 93.19 (-0.04 vs official NVIDIA).

AI agent for parsing OpenAPI specifications (YAML/JSON, OpenAPI 3.x / Swagger 2.0) and accompanying PDF, built with Agentic Star.

🚀 An object-oriented CLI engine built in Python that automatically scans backends, parses endpoints via regex, and compiles production-ready Markdown and HTML API documentation.

Intelligent API documentation platform combining Python AST parsing, LLM-powered code analysis, PostgreSQL, WebSockets, and a Next.js dashboard to automate API documentation generation and real-time synchronization.

Interactive Streamlit app using Gemini API and PyPDF to parse documents and answer contextual questions.

Document parser orchestrator — auto-routes to the optimal OSS parser. CLI, API, MCP, Web UI.

AI-powered CT-200 PDF parser with semantic search, document version comparison, SQLite storage and FastAPI REST API.

A production-grade FastAPI backend for PDF document ingestion, parsing and structured data extraction. Async-first design, modular services, REST API, designed and built for document intelligence, legal-tech, cloud-native deployments and AI/LLM backend readiness.

AI-powered Resume Parser API transforms unstructured resume documents into structured, actionable data. Perfect for ATS, HR platforms, and recruitment software

An Intelligent Document Processing (IDP) system that parses unstructured PDFs and document images (invoices, receipts, contracts) into schema-validated JSON structures using **Pydantic V2**, **PyPDF**, and Vision LLM APIs (**Groq** / **OpenAI**).

A Python-based Retrieval-Augmented Generation (RAG) chatbot using NVIDIA API, vector embeddings, and document parsing for domain-specific question answering.

A conversational RAG FastAPI backend leveraging Google Gemini API and PyPDF2 to parse PDF documents and answer contextual queries with maintained session history.

FastAPI + React multi-tenant RAG API. Document upload, async parsing/chunking, Qdrant vector search, and LLM-powered Q&A with source attribution.

Python SDK for the beliq e-invoice API: generate, validate, parse, and convert EN 16931 documents.

A typed Python client for the WhatsApp Cloud API's Groups API: documented limits enforced before the call, idempotent group creation, aggregation-aware webhook parsing, and a dry-run transport that records what it would have sent

Versioned document-to-QA pipeline: parses a manual into a structured tree, tracks changes across versions, and flags AI-generated test cases as stale when source text changes.

Document extraction API for Vietnamese PDFs, Word, Excel, and scanned images — native text parsing with PaddleOCR VLM model, normalized to Markdown or structured JSON via LLM.

A production-grade Django REST Framework backend application designed for document ingestion, text extraction (digital text parsing and OCR for scanned documents), asynchronous processing with Celery/Redis, and structured AI summarization using the Gemini API.

Software that uses RAG pipeline to generate question's answers relevant to the document parsed into it and includes Ingestion, Chunking, Embedding and Vector Storage, uses GEMINI model for answers.

This repository features a FastAPI application that integrates with LangChain components and the Groq API. It accepts uploaded PDF documents, parses their text contents, and generates structured, formatted summaries or reports.

Built a multi-agent AI system using LangGraph and LLMs to analyze legal documents and detect compliance risks. Developed document parsing pipeline (PDF, DOCX, URLs) and structured report generation with scoring. Integrated multiple LLM APIs and designed scalable backend using FastAPI.

An AI-powered educational tool for processing and analysing Cambridge A-Level past examination papers. Integrates document parsing with the Gemini API to generate structured answers, topic breakdowns, and revision aids.

A RAG pipeline that turns Business Requirements Documents into a queryable knowledge base — parsing, enrichment, chunking, vector embedding, and indexing — then lets you interact with that knowledge via your own LLM API key.

High-performance, privacy-preserving local document intelligence engine to parse PDFs, DOCX, HTML, and images into structured Markdown, JSON, HTML, or CSV with CLI, Python API, and streaming REST API.

Analyze resumes against job descriptions using ATS scoring, keyword matching, skill-gap detection, and OCR-based document parsing. Supports PDF/DOCX resumes with a Flask web interface, REST API, and CLI for automated resume analysis.

A PDF document parser and comparison tool using Python, PyMuPDF, and FastAPI. The application reconstructs document hierarchies, extracts section content, compares different manual versions, and generates structured JSON outputs with REST API support for version comparison.

An explainable Pharmaceutical RAG application built with Streamlit, Gemini API, LangChain, and ChromaDB that visualizes every stage of the RAG pipeline—from document parsing and chunking to embeddings, vector search, retrieval, prompt construction, and answer generation with detailed metrics and domain-specific validation.