Document Data Extraction LLM Tools

Tools for extracting, parsing, and converting structured data from unstructured documents (PDFs, images, invoices, etc.) using OCR and LLMs. Does NOT include general document summarization, web scraping, or downstream analytics applications.

There are 71 document data extraction tools tracked. 9 score above 50 (established tier). The highest-rated is NanoNets/docstrange at 60/100 with 1,379 stars. 2 of the top 10 are actively maintained.

Get all 71 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=llm-tools&subcategory=document-data-extraction&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Tool	Score	Tier	Stars	Language
1	NanoNets/docstrange Extract and convert data from any document, images, pdfs, word doc, ppt or...	60	Established	1,379	Python
2	th1nhhdk/local_ai_ocr An local, offline (after initial setup), portable OCR software that can...	58	Established	713	Python
3	Dicklesworthstone/llm_aided_ocr Enhances Tesseract OCR output using LLMs (local or API) for error...	58	Established	2,885	Python
4	emcf/thepipe Get clean data from tricky documents, powered by vision-language models ⚡	56	Established	1,524	Python
5	langstruct-ai/langstruct Extract structured data from any content using LLMs.	55	Established	118	Python
6	hashangit/Extract2MD Extract2MD is a powerful and versatile AI-enabled client-side JavaScript...	52	Established	105	JavaScript
7	CatchTheTornado/text-extract-api Document (PDF, Word, PPTX ...) extraction and parse API using state of the...	51	Established	2,989	Python
8	CambioML/uniflow LLM-based text extraction from unstructured data like PDFs, Words and HTMLs....	50	Established	234	Python
9	Xyntopia/pydoxtools Effortlessly extract information from unstructured data with this library,...	50	Established	87	Python
10	Capevace/data-wizard Extract structured data from PDFs, Word docs and images. Embeddable directly...	49	Emerging	68	JavaScript
11	enoch3712/ExtractThinker ExtractThinker is a Document Intelligence library for LLMs, offering...	48	Emerging	1,492	Python
12	langchain-ai/langchain-extract 🦜⛏️ Did you say you like data?	45	Emerging	1,190	Rich Text Format
13	QuivrHQ/MegaParse File Parser optimised for LLM Ingestion with no loss 🧠 Parse PDFs, Docx,...	44	Emerging	7,347	Python
14	arshad-yaseen/ocr-llm ⚡️ Fast, ultra-accurate text extraction from any image or PDF—including...	43	Emerging	39	TypeScript
15	junhoyeo/BetterOCR 🔍 Better text detection by combining multiple OCR engines (EasyOCR,...	42	Emerging	622	Python
16	LM-150A/docflash ⚡ AI-powered content intelligence with structured data extraction....	41	Emerging	10	HTML
17	Traves-Theberge/webform-cli A CLI tool for extracting unstructured data from websites using customizable...	39	Emerging	6	TypeScript
18	heripo-lab/heripo-engine TypeScript library for extracting structured data from archaeological...	39	Emerging	4	TypeScript
19	Lazzzer/structurizer Structurizer is a web application that helps you extract structured data...	38	Emerging	33	TypeScript
20	ShengjieJin/pdftrim-for-llm An open-source Zotero plugin for vibe reading and LLM-assisted paper...	37	Emerging	4	TypeScript
21	kennethleungty/LangExtract-Gemma-Structured-Extraction Using LangExtract and Gemma 3 for structured information extraction from...	37	Emerging	32	Python
22	lias-laboratory/cidoccrm-llm-extractor A tool for automating CIDOC CRM knowledge graph population using Large...	34	Emerging	9	Python
23	mohanbing/st_doc_ext This repository contains the code for the information extraction app that...	34	Emerging	7	Python
24	phanxuanquang/XCan-AI Extract the text, style, format, and layout from any images, even...	34	Emerging	21	TypeScript
25	messeb/py-openai-receipt-extractor Extracts structured data from receipts via OpenAI API	33	Emerging	2	Python
26	jamesmcroft/azure-document-intelligence-markdown-to-openai-data-extraction-sample This sample demonstrates how to use Document Intelligence's Layout model to...	33	Emerging	31	Jupyter Notebook
27	jamesmcroft/ai-document-data-extraction-evaluation This project demonstrates how to evaluate the use of LLMs and SLMs for...	33	Emerging	5	C#
28	isaiah76/Reviewer extracts text from pdfs and powerpoint documents and summarizes it into key...	32	Emerging	3	Python
29	sabber-slt/NetExtract NetExtract: Efficiently extract core content from any webpage and convert it...	32	Emerging	32	TypeScript
30	CambioML/any-parser Accurate, private and configurable document retrieval LLM	31	Emerging	131	Python
31	pranavgupta2603/SplitwiseGPTVision SplitwiseGPT Vision: Streamline bill splitting with AI-driven image...	30	Emerging	8	Python
32	AFLucas-UOM/Accurate-Name-Extraction 2026 IEEE Conference on Artificial Intelligence (CAI26) · A modular computer...	29	Experimental	3	Jupyter Notebook
33	mike-grant/intelliextract Extract structured data from your unstructured data	26	Experimental	1	TypeScript
34	Ja-yy/Invoice-extractor Streamlit app leveraging OpenAI's LLM for accurate invoice extraction,...	24	Experimental	4	Python
35	wmahfoudh/crabocr PDF and image to-text converter with XFA forms support. It extract embedded...	24	Experimental	3	Rust
36	QuartzUnit/docpick Lightweight OCR + Local LLM → Schema-based Structured JSON Extraction	22	Experimental	—	Python
37	Randika00/VisionGPT-Extractor An AI-powered tool designed to extract structured data from documents,...	22	Experimental	—	Python
38	lecuong1502/NanoOCR NanoOCR — Internal document OCR system powered by GLM-OCR, with a FastAPI...	22	Experimental	—	TypeScript
39	lisstasy/Receipt_Scanner Advanced receipt OCR and analysis using PaddleOCR, GPT-3.5-turbo, Plotly,...	22	Experimental	28	Jupyter Notebook
40	Nguyendu9096/langcore-api Provide production-ready HTTP API for structured document extraction using...	22	Experimental	—	Python
41	jaimvizalla01/aiwhisperer 📄 Optimize your large documents for AI analysis by converting and splitting...	21	Experimental	—	Python
42	SH-Nihil-Mukkesh-25/fractaAI FractaAI is a Streamlit-based application for exploring and visualizing text...	21	Experimental	—	Python
43	isobarbaric/SnapTrack a receipt CLI	21	Experimental	3	Python
44	Tek233/Document-Processing-with-OCR An agent for document processing using OCR	21	Experimental	—	Jupyter Notebook
45	voidpenguin-28/Textractor-ExtraExtensions Several useful Textractor extensions, which are not available by default in...	21	Experimental	13	C++
46	Jishnnu/InvoiceAI-Document-Parser Simple Streamlit application that parses the data from Invoice images and...	20	Experimental	8	Jupyter Notebook
47	amit-timalsina/document_classification All in one package for Document (image, pdf) Classification. Unified...	20	Experimental	6	Python
48	ilyassuelen/InsightAI InsightAI: Python-based document processing platform with chunking,...	19	Experimental	—	TypeScript
49	RPramodh/LLM-based-Invoice-Extractor This repository hosts the source code for an Invoice Extractor application...	19	Experimental	3	Python
50	mu373/vertex-ai-ocr Convert scanned book images to Markdown with Gemini	18	Experimental	1	Jupyter Notebook
51	PMTheTechGuy/document-entity-extractor AI-powered document extractor for names, emails, and organizations. License: MIT	18	Experimental	1	Python
52	xiangjianxiaohuangyu/paper-extract-app AI-powered desktop tool for extracting structured information from academic...	16	Experimental	4	TypeScript
53	agxp/docpulse Async document intelligence API — upload any PDF/DOCX/image + a JSON Schema,...	15	Experimental	2	Go
54	leadershop/marksheet-information-extraction-api 🎓 Extract and validate data from academic marksheets using AI for accurate...	14	Experimental	—	Python
55	cucumberian/__ai_draft-parser structured data extraction from drafts	14	Experimental	—	TypeScript
56	andyed/fascist-language-analyzer langchain+langextract gemini-api breakdown of Project2025 text by Umberto...	14	Experimental	1	HTML
57	abdulmanafsahito/Vision-OCR A general OCR and image-understanding web app. Upload an image, write a...	13	Experimental	—	JavaScript
58	haritha8503/langextract 🌐 Extract languages from text seamlessly using LangExtract. Simplify...	13	Experimental	—	—
59	junotb/omniparse-ai-stack Document & image parsing full-stack demo. OCR, VLM, document layout...	13	Experimental	—	TypeScript
60	HTLinh0604/invoice_ai_automation This project transforms messy invoice images into a structured, searchable...	13	Experimental	2	Python
61	r0b0tan/document-ai-demo Full-stack demo for AI-assisted document analysis. Upload a document and let...	13	Experimental	—	JavaScript
62	tahangz/Multimodal_OCR_LLM This project is a user-friendly web application that allows you to upload...	13	Experimental	7	Python
63	Tahsine/warmup-ernie-paddleocr Demonstration of the AI pipeline for the conversion of structured documents:...	12	Experimental	1	Jupyter Notebook
64	giruu/TesserXtract.AI This Flask application empowers users to seamlessly upload image files like...	12	Experimental	7	Python
65	rririanto/unstructured-demo-streamlit Extract your docs (CSV, PDF, JSON, HTML, DOCS, Sheets and more) for your own...	12	Experimental	8	Python
66	suddeb/langextract My experiment with langextract - a Python library for extracting structured...	11	Experimental	2	HTML
67	thinktecture-labs/llm-extract-structured-information-langchain-kor Very simple sample that extracts JSON based on a schema from human text input.	11	Experimental	—	HTML
68	joery0x3b800001/Intelligent-Document-Verification-System The application uses state-of-the-art NLP models for summarization and...	11	Experimental	—	HTML
69	Bang-tv259/LLM_Ngrok_Flask OCR (Optical Character Recognition) on images and expose the functionality...	10	Experimental	2	Jupyter Notebook
70	ngtrdai/extractor Extractor is a powerful tool that leverages the capabilities of Langchain to...	10	Experimental	2	Vue
71	fri3erg/DataDig-AIExtractor App used to extract structured data from documents photos or pdfs via custom...	10	Experimental	1	Python