Ingestion RAG Tools

There are 50 ingestion tools tracked. The highest-rated is veyliss/ai-localbase at 48/100 with 133 stars.

Get all 50 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=rag&subcategory=ingestion&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	veyliss/ai-localbase 一个本地优先的AI知识库系统（RAG），用于把本地文档接入辅导搜索与大模型对话流程。目前支持md、txt、pdf（文本）类型	48	Emerging	133	Go
2	Cloud2BR-MSFTLearningHub/RAG-ChatBot-Implementation This repository contains example of a RAG chat bot with a basic architecture...	45	Emerging	3	Bicep
3	LakshmiSravyaVedantham/RAG-Based-Chatbot-with-Streamlit Chat with any document (PDF, CSV, DOCX) using RAG — LangChain + Streamlit + OpenAI	39	Emerging	1	Python
4	yifanfeng97/Hyper-Extract Transform unstructured text into structured knowledge with LLMs. Graphs,...	30	Emerging	6	Python
5	Tendo33/markio a powerful document processing service that seamlessly converts a wide range...	28	Experimental	—	Python
6	LLMSystems/file2md file2md is a versatile tool for converting multiple file formats to Markdown.	28	Experimental	5	Python
7	brolyroly007/docschat RAG chat system: ingest documents, embed in ChromaDB, and chat with any LLM	25	Experimental	1	Python
8	trenknerpeter/mdspin Document to Markdown converter for AI workflows — try it at https://mdspin.app	24	Experimental	—	TypeScript
9	tushar10sh/NimbusPDF Private, self-hosted PDF reader with an offline-capable AI assistant. 🔒 100%...	24	Experimental	2	Rust
10	however-yir/ai-demo Spring AI demo backend with chat, tool calling, multimodal input, PDF RAG,...	23	Experimental	1	Java
11	lakshgk/distill Python library that converts Word, Excel, PowerPoint, PDF, and Google Docs...	23	Experimental	1	Python
12	harshbhanushali26/hArI AI-powered PDF & CSV analysis assistant using Groq LLM, ChromaDB, and RAG...	22	Experimental	—	Python
13	PatienceQi/sge_lightrag SGE: Structure-Guided Extraction for GraphRAG — faithful graph construction...	22	Experimental	—	Python
14	mulkatz/mulder Config-driven Document Intelligence Platform on GCP. PDFs → Knowledge Graph,...	22	Experimental	—	TypeScript
15	VesperArch/rag-ingestion-benchmark Benchmark: GopherDoc (Go) vs LangChain (Python) — 340× throughput, 3.3× less...	22	Experimental	—	Shell
16	Nufeen/pdf-rag Local RAG over pdf collection	22	Experimental	—	Python
17	vericontext/parsemux Document parser orchestrator — auto-routes to the optimal OSS parser. CLI,...	22	Experimental	—	Python
18	Cdharth-07/AI-Powered-Travel-Language-Companion-App A multimodal AI travel companion built with Streamlit. Features an LLM...	22	Experimental	—	Python
19	nithinrajkore/PDF-DataAnalyzer RAG-based PDF QA app using Google Gemini, LangChain, FAISS, and Streamlit —...	22	Experimental	—	Python
20	Sanya003/Scribe I read your PDFs so you don’t have to. 👀	21	Experimental	—	Python
21	a2Fsa2k/eigen ms edge pdf viewer but simply superior	19	Experimental	3	JavaScript
22	CHIRABRATA/vagacore VagaCore — Context-aware NLP engine for extracting structured, time-aware...	19	Experimental	12	HTML
23	sniperx-19/rag-chatbot Chat with multiple PDFs locally	19	Experimental	1	Python
24	shivaacodes/document-rag-service FastAPI RAG microservice for document ingestion and contextual content...	19	Experimental	—	Python
25	jmatias2411/RAG 🧠 Consulta tus PDFs con IA local usando LangChain, Ollama y Streamlit. Sube...	19	Experimental	—	Python
26	DhruvShah510/ai-meeting-assistant AI-powered meeting assistant that summarizes transcripts, extracts action...	19	Experimental	—	Python
27	drewid74/ai_skills AI skills and workflow templates for Claude Code, Copilot, Gemini, any AI...	18	Experimental	8	—
28	ashwyan/Privacy-First-Local-RAG-Pipeline A local AI tool using Ollama (Llama 3) to analyze PDF documents and generate...	17	Experimental	1	Jupyter Notebook
29	leosantos2003/Sabia-QA-System-on-Scientific-Articles Question-Answer RAG-based system with Sabiá on scientific articles in PDF format.	17	Experimental	—	Python
30	sam-k0/ExamGen Generate exam questions based on slides, notes or other PDFs. Answer and...	17	Experimental	—	Python
31	reezuleanu/pdf_deconstructor Decompose a PDF file based on its headers for RAG ingestion.	17	Experimental	—	Python
32	DevPedroGomes/voice_rag Voice RAG — Upload PDFs and ask questions with voice-powered answers....	16	Experimental	—	TypeScript
33	Ashwathama2024/manual-diagnostic-ai Offline AI diagnostic assistant for marine/industrial equipment — Upload PDF...	16	Experimental	—	Python
34	MsheesAI/CortexDocs A smart PDF summarization tool built with AI to convert large documents into...	16	Experimental	2	Python
35	am2998/RAG-cli Local-first RAG CLI that ingests documents, stores embeddings in Qdrant, and...	15	Experimental	—	Python
36	AnshumanMahanta/Cyra-Analytics Cyra Analytics is RAG-based CSV Analyzer for automated dataset profiling and...	15	Experimental	—	Python
37	seantlee88/ai-operations-copilot AI document assistant that summarizes estimates, extracts costs, timelines,...	14	Experimental	—	Python
38	wahhabriaz/rag-chat-pro RAG chatbot for PDF Q&A with switchable AI providers and Streamlit UI	14	Experimental	—	Python
39	Rehman110-F/docmind Full-stack RAG application — chat with your PDF documents using Google...	14	Experimental	—	JavaScript
40	willweimike/RAGAgent Agentic PDF RAG with LangGraph & Ollama	14	Experimental	—	Python
41	N3M3515069/rag-knowledge-assistant A RAG-based Q&A assistant that answers questions from uploaded PDFs using...	14	Experimental	—	Python
42	Yashwanth-23/Omnisense Local multimodal RAG AI assistant where you can chat with PDFs, images, and...	14	Experimental	—	Python
43	Anshuljain-bit/pdf-chatbot Agentic PDF and document-image chatbot with grounded RAG, citations,...	14	Experimental	—	Python
44	rohanpatil2905/Personal-AI-Assistant AI-Powered PDF assistant using RAG + Gemini API	14	Experimental	—	Python
45	mayurk224/mindfolio Mindfolio is an AI-powered knowledge management system and "Second Brain"...	14	Experimental	—	JavaScript
46	deBUGger404/navexa-docs Navexa Docs — documentation site for the Navexa PDF/document processing...	13	Experimental	—	JavaScript
47	Hema4640/AI-Document-Assistant AI-powered PDF Question Answering System using RAG, LangChain, and ChromaDB	13	Experimental	—	Python
48	aseseri/agent-society-user-simulation LLM-based User Simulation Agent for the AgentSociety Challenge. Features...	13	Experimental	—	Python
49	MekdelawitGebre/student-notes-rag RAG application that lets students upload PDF notes and ask questions using...	13	Experimental	—	Python
50	EtheXReal/basiclaw-rag RAG demo that turns the Hong Kong Basic Law PDF into a FAISS + Redis...	13	Experimental	2	Python