Deterministic desktop app for extracting SEC 10-K/10-Q PDFs into traceable, KPI-ready financial data with explainable diagnostics.
-
Updated
Jan 7, 2026 - Python
#
document-parsing
Here are 350 public repositories matching this topic...
An AI-driven FinTech platform that transforms complex, opaque insurance policies into clear, actionable consumer insights using AI.
react javascript nlp firebase ai fintech firebase-auth firebase-database gemini-api vite sequence-animation insuretech framer-motion glassmorphism document-parsing generative-ai spline3d
-
Updated
Apr 25, 2026 - JavaScript
Turn professional profile documents (LinkedIn PDFs, resumes) into structured AI-queryable profiles.
-
Updated
Mar 16, 2026 - TypeScript
End-to-end RAG pipeline built with Next.js, Supabase pgvector, and Gemini AI for intelligent document Q&A and source citations.
-
Updated
Sep 20, 2026 - TypeScript
Engineering-first guide to commercial lease abstraction & PropTech automation — parsing, extraction, escalation logic, and downstream sync, with runnable Python. https://www.leaseautomation.org
property-management real-estate python ocr static-site proptech eleventy commercial-real-estate pydantic document-parsing lease-management lease-abstraction
-
Updated
Jul 15, 2026 - JavaScript
Hybrid AI document layout parser: images and PDFs to structured Markdown and rebuilt PDF using PaddleOCR-VL and PP-StructureV3.
python markdown pdf ocr computer-vision vlm document-layout paddleocr document-ai document-parsing paddleocr-vl pp-structurev3
-
Updated
Jun 19, 2026 - Python
Firecrawl AnyDoc: Blazing Fast 4ms Document Parsing! Fast Rust library converting office documents (PPTX, DOCX, CSV, PDF, RTF) to clean GFM Markdown and local Ollama LLM synthesis.
-
Updated
Aug 6, 2026 - Python
CleanSlate Protocol (CSP) — AI-native document standardization layer for AI agents. Transform any document into structured, verifiable, semantically-rich format for LLM pipelines.
markdown csp protocol pdf-parser browser-native privacy-first rag ai-agent llm document-parsing langchain llamaindex ai-data-standard
-
Updated
Mar 4, 2026 - TypeScript
Code examples for the CrowdSorcerer API — web research, entity enrichment, document parsing, and more
-
Updated
Apr 8, 2026 - TypeScript
Read PDFs, scans and screenshots into structured content — headings, lists and tables in reading order — on-device with Apple's Vision framework.
-
Updated
Aug 10, 2026 - Swift
Google Colab to parse a Multipage Document using Amazon Textract asynchronously
ocr amazon-web-services textract amazon-s3 ocr-text-reader visual-question-answering document-ai document-parsing
-
Updated
Feb 25, 2025 - Jupyter Notebook
Extracts structured legal information from scanned and digital PDF documents using OCR and exports the results as JSON.
-
Updated
Jun 6, 2026 - Jupyter Notebook
Schema-driven document -> structured JSON. Anthropic / OpenAI / local Ollama, plus a no-API-key demo mode. Invoices, contracts, emails -> clean data.
python json-schema openai data-extraction structured-data document-processing structured-output llm document-parsing anthropic ollama invoice-extraction
-
Updated
Sep 21, 2026 - Python
Portable local PaddleOCR WebUI for macOS and Linux
-
Updated
Aug 3, 2026 - Python
A document parser using Cloud LLMs like gemini, openai etc
-
Updated
Jan 13, 2025 - HTML
A high-precision, agentic RAG system for contract review, legal research, and automated citation mapping.
-
Updated
Feb 12, 2026 - Python
Intelligent document parsing system utilizing agentic AI workflows.
-
Updated
May 11, 2026 - Python
本地优先的多模态视觉 MCP —— 为无视觉 LLM（DeepSeek、GLM 等）提供可自定义端点的看图 / OCR / 文档解析能力。
python docker ocr computer-vision mcp vision ai-agents multimodal document-parsing ollama mcp-server agent-skills
-
Updated
Aug 31, 2026 - Python
Add this topic to your repo
To associate your repository with the document-parsing topic, visit your repo's landing page and select "manage topics."