PDF Document Processing RAG Tools

Tools and systems for extracting, parsing, and retrieving information from PDF documents through OCR, layout analysis, and structured data conversion. Does NOT include general chatbots, multi-source document handling beyond PDFs, or chat interfaces built on top of processed PDFs.

There are 65 pdf document processing tools tracked. 2 score above 50 (established tier). The highest-rated is thiswillbeyourgithub/wdoc at 60/100 with 510 stars.

Get all 65 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=rag&subcategory=pdf-document-processing&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	thiswillbeyourgithub/wdoc Summarize and query from a lot of heterogeneous documents. Any LLM provider,...	60	Established	510	Python
2	Arterning/DeepParseX DeepParseX 是一个强大的多模态文档解析与知识管理平台，支持 PDF、Word、Excel、PPT、图片、视频、音频...	51	Established	56	Python
3	NoEdgeAI/pdfdeal A python wrapper for the Doc2X API and comes with native texts processing...	48	Emerging	284	Python
4	laxmimerit/RAGWire Production-grade RAG toolkit — ingest PDFs, DOCX, XLSX into Qdrant with LLM...	44	Emerging	8	Python
5	David-Lolly/ViewRAG 图文并茂的 PDF RAG 系统：支持版式感知分块、图表深度理解与精准视觉溯源。 Multimodal PDF RAG: Features...	42	Emerging	21	Python
6	atpuxiner/docsloader This is a documents loader. (文档解析加载器，rag文档解析，rag知识库构建)	41	Emerging	129	Python
7	3DCF-Labs/doc2dataset 3DCF / doc2dataset: token-efficient document layer with NumGuard numeric...	40	Emerging	56	Rust
8	preprocess-co/rag-document-viewer RAG Document Viewer is an open-source library that generates high-fidelity...	37	Emerging	13	Python
9	zzstoatzz/raggy scraping and querying documents for LLMs	33	Emerging	24	Python
10	ManiAm/RAG-Mail RAG-Mail is a thread-aware email processing system that semantically indexes...	33	Emerging	5	Python
11	e-kotov/rdocdump rdocdump: Dump ‘R’ Package Source, Documentation, and Vignettes into One File	32	Emerging	19	R
12	salameaz/pdf-process-rag A Python-based application that extracts and processes PDF content using a...	31	Emerging	1	Python
13	antoninomariarizzo/rag A Python library for Retrieval-Augmented Generation (RAG) that extracts text...	30	Emerging	2	Python
14	MalayAgr/bookacle bookacle is a RAPTOR-based RAG application to aid in understanding complex...	30	Emerging	2	Python
15	MohammedNasserAhmed/RAGPost RAGPost is an intelligent blog post generator that leverages...	30	Emerging	2	—
16	AKSHAYINDIA05/Document_Comparison_System Implement a Retrieval Augmented Generation (RAG) with a user interface for...	29	Experimental	1	Python
17	natanhp/PythoRAG PythoRAG is a simple, open-source project designed to facilitate...	28	Experimental	3	Python
18	iamarunbrahma/rag-ingest RAG-Ingest: A tool for converting PDFs to markdown and indexing them for...	27	Experimental	13	Python
19	Besthope-Official/predoc Preprocess document service for RAG (Retriveal Augumented Generation)	27	Experimental	2	Python
20	ParthSareen/simple-rag Too many docs? Quickly search over any PDF or Markdown documents	27	Experimental	65	Python
21	SStephanJX/Snowflake-RAG-System Production-ready Snowflake RAG system with type-specific chunking	26	Experimental	3	PLpgSQL
22	liunian-Jay/MU-GOT PDF Parsing Tool: GOT's vLLM acceleration implementation, MinerU for layout...	25	Experimental	65	Python
23	juhaodong/large-file-translator Extract the content while preserving the layout, images, and tables. Perform...	25	Experimental	6	Vue
24	este6an13/checks-ocr Software that applies OCR + RAG to extract bank checks information	23	Experimental	3	Python
25	lolbigtime/Folio Zero-config Swifty RAG toolkit for iOS & macOS — PDF/text loaders, universal...	22	Experimental	1	Swift
26	salim-lakhal/rag-document-pipeline Production RAG pipeline: multi-format document extraction → intelligent...	22	Experimental	—	Python
27	Nexialism-Friday/hwpx-toolkit HWP/HWPX document processing toolkit — extraction, generation, vectorization...	22	Experimental	—	Python
28	slvg01/90.10d_RAG_OnTheFly An app allowing to upload files (ppt, doc, pdf, zip) and RAG on their content	22	Experimental	1	Python
29	Vibhuarvind/Content-Engine-RAG-for-PDF Content Engine is RAG system that analyzes and compares multiple PDF...	22	Experimental	2	Jupyter Notebook
30	FrostWillmott/FinDocBot Modern RAG, designed for semantic search and question-answering over...	21	Experimental	—	Python
31	yotaken/docuggez Automatic project documentator	21	Experimental	—	Python
32	JochiRaider/sievio Sievio turns GitHub, local repos, and web PDFs into clean JSONL for LLM...	21	Experimental	2	Python
33	JuliaGenAI/DocsScraper.jl Efficient RAG knowledge pack creator from online Julia documentation	21	Experimental	14	Julia
34	Clearedge-AI/clearedge Build a RAG preprocessing pipeline	21	Experimental	13	Jupyter Notebook
35	S0lkar/IntGathering-x-RAG--BlazingDocs RAG-based tool for document batch querying.	19	Experimental	—	Python
36	silas-rickards/PDF-LLM-RAG A RAG pipeline specialized for local pdfs.	18	Experimental	1	Python
37	sfkunal/librarian Librarian is a RAG-assisted LLM application that allows any user to query...	17	Experimental	1	JavaScript
38	A-Najjar/rag-factory Modular RAG system with Factory Pattern - Load PDF/Word docs, configure...	17	Experimental	—	Python
39	husaynirfan1/PullData RAG with response in what you need. Output directly with supported format...	17	Experimental	—	Python
40	solomonjie/rag-processor RAG index pipeline, from raw data clean to index. each step communicate via...	14	Experimental	1	Python
41	alrafiabdullah/doc_rag Document RAG with HuggingFace Token	14	Experimental	—	Python
42	yagmur-kurtbas/pdf-rag-pipeline A RAG pipeline for PDF question answering using LangChain, ChromaDB and Groq...	14	Experimental	—	Python
43	ahmad-albasha/DataForg PDF to JSON pipeline with intelligent bilingual chunking (AR/EN) and a fully...	14	Experimental	—	Python
44	ritheesh-dev/Local-PDF-RAG-System Privacy-first local PDF RAG system using FAISS + Ollama — fully offline,...	14	Experimental	—	Python
45	avocatt/ocr-rag-highlighted-viewer OCR + RAG document viewer with highlighted search results	14	Experimental	—	JavaScript
46	2dogsandanerd/rag_pdf_audit Tool to compare pdf extraction methods	14	Experimental	3	Python
47	fllin1/mawa RAG workflow (Mistral OCR + Gemini) for complex regulatory PDFs....	14	Experimental	1	Python
48	julicq/PDF-RAG-Query RAG model for PDF database	13	Experimental	—	Python
49	shivkhurana/technical-docs-rag-pipeline Enterprise-grade RAG (Retrieval Augmented Generation) pipeline using...	13	Experimental	—	—
50	will695672804/graphrag-engineering-pdfs 🔍 Extract entities and build knowledge graphs from large engineering PDFs,...	13	Experimental	—	Python
51	andersborgabiro/RagQueryDocuments RAG application that makes it easy to search in multiple documents	13	Experimental	—	Python
52	ashwyan/local-llm-pdf-analyzer A local AI tool using Ollama (Llama 3) to analyze PDF documents and generate...	13	Experimental	—	Jupyter Notebook
53	Qinnovation123/papers PDF embedding workflow	13	Experimental	—	Python
54	adrianizmi/Simple-RAG Minimalist RAG system built from scratch using Python, local embeddings, and...	13	Experimental	—	Python
55	mshojaei77/DataSpeakGPT Read files and images and retrieve data for LLM	13	Experimental	14	Python
56	zenmakhlouf/arabic-rag-pipeline A single-file RAG pipeline for Arabic PDF lectures with two-stage retrieval,...	13	Experimental	—	Python
57	nkarast/ask-my-pdf A RAG application using local LLM to answer questions given a PDF.	12	Experimental	1	Jupyter Notebook
58	siddharth-nandagopal/billionaires-rag-query Billionaires RAG Query uses LLMs and a RAG framework to analyze the world's...	11	Experimental	—	Python
59	bazilicum/pdf-query This project processes and retrieves information from PDF file or PDF...	11	Experimental	—	Python
60	zhangshi0512/DevTools A lightweight Python-based Software Package for daily use	11	Experimental	1	Python
61	AlinaBaber/Document-Analysis-Identification-with-RAG-Vector-Database-and-Mistral-LLM This Document Analysis pipeline is a comprehensive document analysis system,...	11	Experimental	3	Python
62	pvmodayil/ragyphi An entire RAG (Retrieval-Augmented Generation) pipeline library designed to...	11	Experimental	4	Python
63	swax10/anaya Anaya is a Content Engine that specializes in analyzing and comparing...	11	Experimental	3	Python
64	SuchitG04/multi_doc_rag RAG application to query multiple docs. Built to query 10K reports of companies.	10	Experimental	2	Jupyter Notebook
65	ITSAIDI/RAGify RAGify is a Retrieval-Augmented Generation (RAG) application designed to...	10	Experimental	2	Jupyter Notebook

Comparisons in this category

rag and PythoRAG (30 vs 28) pdf-process-rag and PythoRAG (31 vs 28) pdf-process-rag and rag (31 vs 30)