Local PDF RAG Systems Vector Databases

Complete RAG implementations for querying PDF documents using local/offline infrastructure (Ollama, FAISS, ChromaDB, etc.). Does NOT include cloud-hosted solutions, non-PDF document types as primary focus, or general RAG frameworks without PDF-specific examples.

There are 27 local pdf rag systems tools tracked. 1 score above 50 (established tier). The highest-rated is VectifyAI/PageIndex at 65/100 with 21,374 stars. 1 of the top 10 are actively maintained.

Get all 27 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=vector-db&subcategory=local-pdf-rag-systems&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	VectifyAI/PageIndex 📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG	65	Established	21,374	Python
2	thearpankumar/GPUaccelerated-multilingual-RAG GPU - vector DB - AI-powered document processing platform for financial...	39	Emerging	2	Python
3	justine-george/ai-markdown-llm-retrieval AI-powered document query system using LangChain, ChromaDB, and OpenAI for...	33	Emerging	6	Python
4	0x5h31d0n/Bajaj-Hackrx A RAG model that takes document input and answers query related pertaining...	25	Experimental	3	Python
5	KayraBulbul/NSW-Crime-RAG-System A RAG application for analysing NSW crime statistics using LangChain, OpenAI...	24	Experimental	1	Python
6	Ashish4144/pageindex Build hierarchical document indexes using LLM reasoning for intuitive...	22	Experimental	—	Python
7	muqadasejaz/PDF-QA-RAG-System A PDF Question-Answering App built with RAG (Retrieval-Augmented...	21	Experimental	6	Python
8	baranozgurtas/Academic-RAG-Assistant End-to-end RAG pipeline for academic PDFs with citation-grounded QA and...	21	Experimental	—	Python
9	keyvar/paperbrace Local-first PDF literature navigator with RAG: index your library, ask...	21	Experimental	—	Python
10	vishalkumar-swe/documind-rag-endee RAG-powered document Q&A system built using Endee Vector Database and FastAPI	21	Experimental	—	Python
11	davidenegri0/LLaMASearchDocs AI-based document search engine based on LLaMa2 by Meta, early development version	19	Experimental	1	Python
12	dulhara79/Research_Assistant_for_PDFs Research Assistant for PDFs is a full-stack prototype that helps you upload,...	19	Experimental	—	JavaScript
13	Akshitha0118/ContextCore-Domain-Aware-RAG-Chatbot RAG-based Question Answering system using LangChain, Groq LLM, and ChromaDB...	15	Experimental	1	Jupyter Notebook
14	zmwzmo11130/neuraldocs Demo RAG API (FastAPI, OpenAI, ChromaDB, Docker) automatically generated...	15	Experimental	—	Python
15	SakuraPuare/Delphi 可离线部署的本地知识库系统 — 导入代码仓库、技术文档、音视频，基于 RAG 的智能问答	14	Experimental	—	Python
16	gregorydearing/AI-Handbook-Generator AI-powered system that generates comprehensive handbooks from PDF documents...	14	Experimental	1	Python
17	SKcoder6344/insurance-rag-endee RAG-based Insurance Policy Q&A using Endee Vector DB + OpenAI GPT \| FastAPI \| Docker	14	Experimental	1	Python
18	Purnachander-Konda/RAG-Based-PDF-Assistant RAG-based Research Paper Assistant - Upload PDFs and ask questions using...	13	Experimental	—	Python
19	Namanpaliyal/KardiaFlow 🚀 Build and deploy a lightweight RAG demo using FastAPI, Chroma, and Ollama...	13	Experimental	—	HTML
20	22CB006/AI-Knowledge-Copilot Production-grade RAG system for querying PDFs and web content with semantic...	13	Experimental	—	Python
21	ai-prasanth/sample-claude-rag-system AI-powered PDF Q&A system using RAG with Claude API, Qdrant, and...	13	Experimental	—	Python
22	Hassi34/document-portal A FastAPI-powered application to analyze, compare, and chat with documents...	13	Experimental	—	Jupyter Notebook
23	24f2000058/pdf_knowledge_tool Enterprise-ready, local-first RAG system that converts complex PDFs into...	13	Experimental	—	Python
24	IvayloP0709/langchain-pdf-rag Retrieval-Augmented Generation (RAG) system for PDF documents using...	13	Experimental	—	Python
25	Queen-esther01/RAG-Langchain RAG-powered PDF Q&A app built with LangChain, OpenAI GPT-4o, ChromaDB and...	13	Experimental	—	Python
26	coderRobust/fullstack-rag-app A fullstack RAG-based Document Q\&A system that allows authenticated users...	12	Experimental	3	Python
27	armanjscript/Fusion-RAG A powerful web-based application designed to answer questions based on the...	10	Experimental	1	Python

Comparisons in this category

PageIndex and pageindex (65 vs 22)