Document Intelligence RAG Embedding Tools

Tools for uploading, searching, and conversationally querying documents (PDFs, files, etc.) using embeddings and semantic search to extract insights and answers. Does NOT include code documentation generation, code search, or cross-document fact-checking systems.

There are 52 document intelligence rag tools tracked. The highest-rated is maxent-ai/ocrpy at 42/100 with 224 stars and 167 monthly downloads.

Get all 52 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=embeddings&subcategory=document-intelligence-rag&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	maxent-ai/ocrpy OCR, Archive, Index and Search: Implementation agnostic OCR framework.	42	Emerging	224	Jupyter Notebook
2	haven-jeon/LegalQA Korean LegalQA using SentenceKoBART	38	Emerging	97	Python
3	ametnes/nesis Your AI Powered Enterprise Knowledge Partner. Designed to be used at scale...	36	Emerging	55	Python
4	foxminchan/LawKnowledge A legal knowledge search and Q&A application based on Vietnam's Legal Code...	33	Emerging	118	TypeScript
5	utachicodes/PyDocEnhancer An AI-powered Python plugin to enhance documentation with summaries, code...	33	Emerging	2	Python
6	ryanlane/document-manager Local-first document archive assistant for semantic search and RAG using...	33	Emerging	2	Python
7	intel/document-automation Document Automation Reference Kit	31	Emerging	16	Python
8	machinelearningZH/document-research-tool Perform intelligent research over document collections using hybrid search and LLMs.	31	Emerging	12	Python
9	joe32140/tei-qdrant-cache Docker Compose stack for scalable TEI embeddings (multi-GPU) fronted by a...	27	Experimental	4	Python
10	Schematise-Lex-Data-Analysis/lex-liberalis A fork of Semantra for Indian court judgments	27	Experimental	3	Python
11	rahulapjs/QueryDoc QueryDoc is a full-stack RAG application that enables secure,...	25	Experimental	2	TypeScript
12	kchanda24/hackathon-backend Enterprise Content Management MVP with semantic search capabilities. Upload...	24	Experimental	1	Python
13	FellowTraveler/ngest Python script for ingesting various files into a semantic graph. For text,...	24	Experimental	40	Python
14	mcplusa/elastic-ingest-http This is an Elasticsearch Ingest Pipeline Processor that calls an HTTP(s)...	23	Experimental	6	Java
15	Leg0shii/smart-documents A web application that enables users to upload documents and utilize AI...	23	Experimental	2	Python
16	josego85/pdf-content-search 🔍 AI-powered PDF search with OCR support for scanned documents, local AI via...	23	Experimental	1	PHP
17	HarshilMaks/InsightDocs AI Document Intelligence System for deep analysis and semantic querying of...	23	Experimental	1	Python
18	moonlitrevery/DodocLens Inteligência documental com IA local (OCR + busca semântica) para PDFs e...	23	Experimental	1	—
19	lookingforvirus/fastapi_auto_routes ⚡ Generate dynamic CRUD and Auth routes effortlessly with FastAPI Auto...	22	Experimental	—	Python
20	gracee3/qdrant-bge-stack Local deployment stack for Qdrant vector search with vLLM-served BAAI...	22	Experimental	—	Python
21	arcnem-ai/arcnem-vision An AI-powered platform for document ingestion, processing, and similarity search	22	Experimental	—	TypeScript
22	sapientpants/doctrans Privacy-first document translation powered by local AI (Ollama). Upload PDF,...	22	Experimental	—	Elixir
23	xhulianokoci/DocCompareAI ASP.NET Core API for comparing Word documents with AI — text diff, OpenAI...	20	Experimental	1	C#
24	danilagoleen/vetka-ingest-engine Ingestion/indexing core for agent systems: scanning, extraction, dependency...	20	Experimental	1	Python
25	VedantKothari01/DocInsight AI-powered document originality and plagiarism risk detection system...	20	Experimental	1	Python
26	mry0tt4/DocGenie AI-powered documentation platform that automatically generates, categorizes,...	20	Experimental	1	JavaScript
27	Tonemon/StaxRead Self-hosted semantic search over your own documents. Your own self-hosted...	19	Experimental	—	Python
28	LeonKiptoo/document-intelligence-engine A document intelligence system that enables semantic question answering over...	19	Experimental	—	Python
29	ashankgupta/docai DocAI is a Go-based toolkit that enables intelligent interaction with your...	19	Experimental	—	Go
30	ivan-markov-666/rag-jag Self-hosted AI-powered document search system. Upload PDF, DOCX, TXT, and...	19	Experimental	—	TypeScript
31	harshsrivastava05/Document-Analyzer An AI-powered document analysis platform that transforms uploaded files into...	17	Experimental	2	Python
32	HemalDholakiya12/PDFChat A web app that allows users to upload PDFs and interact with them through a...	17	Experimental	2	JavaScript
33	ventz/pdf-semantic-keyword-analysis High-performance PDF Semantic keyword analysis tool using AI for intelligent...	16	Experimental	1	Python
34	akbar-ops/sistema-de-analisis-de-documentos-juridicos 📄 Analyze, classify, and search legal documents with advanced NLP techniques...	16	Experimental	—	Python
35	cosmanBrenden/DocumentMuncher DocumentMuncher is a locally running document seach engine that allows you...	15	Experimental	—	Python
36	SSK-14/GitDoc-AI GitDoc is your ultimate GitHub Documentation Explorer! It's your trusty...	15	Experimental	2	Python
37	KaramelBytes/docloom-cli AI‑augmented document analysis and lightweight retrieval (Go) with...	15	Experimental	—	Go
38	KaavyaGala546/DocuMind-AI DocuMind-AI is an AI-powered document assistant that allows users to upload...	15	Experimental	1	Python
39	Irshad-11/PDF-INSIGHTS Smart PDF Analyzer with OCR and Semantic Search	14	Experimental	—	JavaScript
40	mamoon-17/DocuQuery DocuQuery — a minimal RAG demo: upload PDFs, generate local embeddings,...	14	Experimental	—	TypeScript
41	maharishiayurveda/DocQuify Extract insights from research papers with DocQuify. Upload PDFs and ask...	14	Experimental	—	TypeScript
42	NathanMaine/rah-qdrant-integration Community add-on for RA-H OS that replaces sqlite-vec with Qdrant for vector...	14	Experimental	—	Python
43	Helixo613/docforensics Cross-document contradiction and agreement detection for PDF collections...	14	Experimental	—	Python
44	Naturestudyperinatologist466/fojin Aggregate and search over 9,200 Buddhist texts in multiple languages with...	14	Experimental	—	—
45	JacobPolloreno/OfficeAnswers Get to the real work by using neural information retrieval for company information.	12	Experimental	3	Python
46	dyannadle/AI-Powered-Search-Over-Noation An AI-powered document search engine that connects to Notion and Google...	11	Experimental	—	Java
47	tstephx/book-ingestion-python Book ingestion pipeline for processing PDF/EPUB into searchable chapters...	11	Experimental	—	Python
48	devinitive-team/mirage 🏜️ Mirage: Universal, relevance search over PDF documents at any scale....	11	Experimental	—	TypeScript
49	KishoreMuruganantham/HackRx-6.0-Intelligent-Query-Retrieval LLM-powered system for intelligent query–retrieval from large documents in...	11	Experimental	—	Python
50	gururaser/qdrant-data-processor A high-performance data ingestion pipeline in Go for processing Amazon...	11	Experimental	—	Go
51	kstv364/intellidoc Hackathon project - Intellidoc - ECM MVP with semantic search capabilities....	11	Experimental	—	Python
52	bivex/qdrant_streamlit_generator_via_groq 🔍 QDRANT + STREAMLIT + GROQ = VECTOR SEARCH UI. Explore embeddings....	11	Experimental	—	Python