RAG & retrieval pipelines
5,258 agents · most starred first
RAG & retrieval pipelines, page 35 of 53
CRDFAgent is a modular Python framework for multi-step question answering, combining clarification, routing, decomposition, retrieval, and aggregation to deliver accurate, reproducible answers for complex tasks like financial document QA.
🧠 A personal multimodal RAG chatbot that remembers you — encrypted document Q&A with persistent memory, citations, and automatic provider fail-over. FastAPI + Next.js 15.
Build a robust, production-ready RAG system with effective data preparation, anonymization, and LLM integration. Explore best practices and metrics. 🐙📦
Star Wars: Legion rules and unit data translated into pure JSON and Markdown. Built specifically to help AI agents and developers accurately parse Legion 2.5 gameplay mechanics.
streamlit region:us
gradio agent-demo-track agent smolagents convex vectara nebius region:us
gradio mcp-in-action-track-enterprise mcp agent rag llm bayesian-optimization embeddings
gradio region:us
streamlit region:us
streamlit region:us
gradio region:us
streamlit region:us
streamlit region:us
gradio region:us
gradio region:us
gradio region:us
streamlit region:us
docker region:us
streamlit region:us
gradio region:us
gradio region:us
streamlit region:us
streamlit region:us
gradio region:us
streamlit region:us
streamlit region:us
streamlit region:us
streamlit region:us
static region:us
gradio region:us
gradio region:us
region:us
gradio region:us
streamlit region:us
gradio region:us
static region:us
streamlit region:us
docker region:us
gradio region:us
gradio region:us
docker region:us
gradio region:us
static region:us
gradio region:us
gradio region:us
docker openenv incident-ops benchmark enterprise region:us
safetensors gguf qwen3 rag chunking text-segmentation
A Retrieval-Augmented Generation (RAG) system for Kenyan legal, parliamentary, and news intelligence. NIRU: Neural Intelligence Retrieval Unit
An app built using langchain and streamlit which allows to chat with multiple PDFs and can be run locally with GPUs.
An application that allows you to interact with your PDF's⚓
Build a Production RAG System with Python, LangChain, and ChromaDB Build ShopBot from scratch — a production RAG assistant that answers from retrieved evidence, not training memory. Ten chapters, one complete system.
This project creates an intelligent product information chatbot that can answer questions about laptops sold by a company. It demonstrates the power of LLMs in creating interactive, context-aware agents that can retrieve and present information naturally.
StudyAgents:五人协作开发的多 Agent 可信知识问答与专项复习系统(Vue 3 / FastAPI / LangGraph / PostgreSQL + pgvector)
Develop a production-grade, cyclic Retrieval-Augmented Generation (RAG) system leveraging LangGraph, Google Cloud Platform (GCP), and Groq for accelerated inference. This system intelligently distinguishes between technical 'True Data' and random 'Noisy Data' through semantic re-ranking and history-aware planning, ensuring accurate and contextually
Agentic Medical RAG: Agentic memory-augmented retrieval and evidence grounding for medical question-answering tasks
Drift-free query routing for multi-collection RAG.
Agentic RAG learning project — Pydantic AI agent + FastAPI + Next.js + pgvector.
docker region:us
Multimodal chatbot project using five LLM-based approaches including RAG, PEFT, and prompt engineering, built on the BioASQ dataset for biomedical QA.
This project is an AI-driven chatbot trained on theoretical Computer Science subjects like DBMS, CN, OS, Blockchain and OOP. The bot answers questions based on content fed through pre-embedded PDFs using ChromaDB. The project offers both a command-line interface (CLI) and a user interface (UI) built using Streamlit.
30 production-focused examples: covering RAG patterns, hybrid search, routing, agentic RAG, knowledge graphs, multimodal RAG, and debugging.
Server with an AI agent powered by an LLM, with tools for internet search, Wikipedia, and RAG database access.
An enterprise-grade, retrieval-augmented generation (RAG) chatbot CLI & FastAPI backend using BGE embeddings, ChromaDB, and LLM for e-commerce customer support.
DrawingIQ - turns an archive of engineering drawings into a knowledge base you can ask questions, with an agent that cites every drawing behind its answer.
We did it even with only 8 hours deadline.
Retrieval-Augmented Generation. A production-shaped reference stack for grounded chat over your own documents — FastAPI + LangChain agents, Qdrant vector search, and a Next.js 15 frontend with a deterministic calculator tool wired in.
A self-hosted RAG assistant using local LLM that combines document Q&A with citations and natural language to SQL database access - running entirely on local infrastructure
This is a basic RAG chatbot and report generator made using LangChain, Streamlit, FAISS, Cohere's embed-english-v3.0 and Cohere's command-r
A prototype of RAG-based AI chatbot using LangChain, LLMs (OpenAI/HuggingFace), and Chroma vector database.
A dynamic chatbot serving tailored food recommendations and similar recipes.
RAPTOR introduces a novel approach to retrieval-augmented language models by constructing a recursive tree structure from documents. This allows for more efficient and context-aware information retrieval across large texts, addressing common limitations in traditional language models.
RAG Chatbot deployed to GCP with gpt-3.5 and Mistral-7B language models and gte-base-en-v1.5 with FAISS for vector search.
Production-ready RAG for codebases using AST parsing, hybrid search, and LLMs with precise file & line citations.
On-device RAG on Android — notes app with local embeddings, vector search, and agentic tool calling. Fully offline, Gemma 4 + LiteRT-LM
QVS-RAG
A chat bot which makes use of multiple RAG collections/metadata field filtering, and multiple LLMs for model orchestration
Ask questions about your PDFs, grounded in what's actually in them. FastAPI + Postgres/pgvector RAG API with background document ingestion, source-cited answers, and pluggable LLM/embedding providers.
Local, offline AI PDF assistant for private document Q&A and summarization using LLaMA 3 via Ollama.
Production-grade federal law RAG with multi-source retrieval (U.S. Code, CFR, Case Law), LangGraph orchestration, hybrid search, conflict detection, and Prometheus observability. Regression-tested by Rag-eval.
Self-correcting agentic RAG over 2k arXiv CS papers: Neo4j · Qdrant · LangGraph
Production-ready multi-agent PDF RAG system with LangGraph, FastAPI, React, reflection/retry, citations, evaluation, and LLM cost observability.
transformers gguf bible rag question-answering qwen3.5
Self-hosted RAG event assistant (Llama 3.3 70B via Ollama, LangChain, FAISS, Gradio) - built as a 2-person sprint, deployed to production for a corporate client
gradio region:us
A Retrieval-Augmented Generation chatbot that impersonates Claude Shannon, the father of Information Theory. It ingests his biographies and papers, retrieves with hybrid BM25 + FAISS, reranks via cross-encoder, and answers in his voice (English/Persian).
A Retrieval-Augmented Generation (RAG) system for Kenyan legal, parliamentary, and news intelligence. NIRU: Neural Intelligence Retrieval Unit
A RAG web application that delivers answers using hybrid document retrieval, reranking, and local LLMs.
Ask MSU-IIT's scanned documents anything: page-level vision OCR, hybrid search with reranking, and a streaming chat agent that cites the page. Django, LangGraph, pgvector, React.
飞书知识库 RAG Agent:增量同步 · 父子切块混合检索 · JWT 多用户隔离 · 微调图表专家(FastAPI + LangGraph + Milvus)
Sandbox for comparing Agentic & RAG frameworks
A production-ready Retrieval-Augmented Generation (RAG) pipeline optimized for scalability, accuracy, and enterprise deployment.
LangGraph support triage across HackerRank, Claude, and Visa corpora. Hybrid BM25+dense RAG, citation critic, eval CLI, production observability.
Interactive 3D RAG lab. Ask questions on your PDFs, Markdown, and text and get source-cited, grounded answers. Explore retrieval and embeddings in 3D. Built with FastAPI, React, Three.js, ChromaDB. Keys stay in your browser.
AI summaries, follow-up chat, and a cited research copilot for any Discourse forum — a Chrome side-panel extension. Bring your own AI provider.
streamlit region:us
A production-grade RAG AI Agent built with FastAPI, LangChain, Qdrant, and OpenRouter. Features full PDF ingestion, deduplication, and context-aware chat.
Multi RAG File System using Groq, Huggingface, Llama Index, Langchain
Local RepoGPT using Ollama + FAISS (RAG) + FastAPI Web UI. CPU-friendly AI assistant for querying code repositories.
Vision-grounded RAG agent for financial documents, built on a self-finetuned ColPali and LangGraph.
A lightweight AI agent that answers natural language questions about APIs using their official documentation. It leverages vector embeddings and Retrieval-Augmented Generation (RAG) for accurate, context-aware responses.