Discover the best projects built with LlamaIndex

This repository contains the Hugging Face Agents Course.

[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

AI Observability & Evaluation

Build ChatGPT over your data, all with natural language

The easiest way to use Agentic RAG in any enterprise

Easiest and laziest way for building multi-agent LLMs applications.

The AI-Native Search Database. Best for agent storage, it unifies vector, text, structured, and semi-structured data into a single engine. This all-in-one database makes agents smarter, easier to run, and more stable.

Ollama，CPU，：https://datawhalechina.github.io/handy-ollama/

Deploy your agentic worfklows to production

OpenTelemetry Instrumentation for AI Observability

Large Language Models (LLMs) tutorials & sample scripts, ft. langchain, openai, llamaindex, gpt, chromadb & pinecone

Open source guides/codes for mastering deep learning to deploying deep learning in production in PyTorch, Python, Apptainer, and more.

Repository for the "Building LLMs for Production" book by Towards AI.

ParseBench - A Document Parsing Benchmark for AI Agents

RESTai is an AIaaS (AI as a Service) open-source platform. Supports many public and local LLM suported by Ollama/vLLM/etc. Precise embeddings usage, tuning, analytics etc. Built-in image/audio generation with dynamic loading generators. Live chat deployment. Built-in block based graphical language. Prompt versioning and much more...

LangStream. Event-Driven Developer Platform for Building and Running LLM AI Apps. Powered by Kubernetes and Kafka.

Unlock 650+ MCP servers tools in your favorite agentic framework.

Create a plan from a description in minutes

A LLM RAG system runs on your laptop. ，，。

Build, Improve Performance, and Productionize your AI Application

Code from tutorials presented on the "Code AI with Rok" YouTube channel

This repo is to showcase how you can run a model locally and offline, free of OpenAI dependencies.

Build Agentic AI solutions on AWS, using latest OSS Agentic Frameworks.

This is a repository for the course "From Beginner to LLM Developer" by Towards AI.

Open-source protocol suite standardizing LLM, Vector, Graph, and Embedding infrastructure across LangChain, LlamaIndex, AutoGen, CrewAI, Semantic Kernel, and MCP. 3,330+ conformance tests. One protocol. Any framework. Any provider.

LLM AI

Video understanding and self-verification for AI agents. Turn videos, streams, and agent screen recordings into searchable, timestamped evidence—then use THE LOOP to inspect, fix, and verify the work. MCP, CLI, REST, local-first.

Python SDK for interacting with the MCP Toolbox for Databases.

Ship RAG Solutions Quickly and effortlessly

Pure Rust PDF library for AI/RAG: structure-aware chunking, no ML, no C deps.

Python toolkit for Chinese LLMs, with flexible batch capacity, structured real-time visulization and automated accumulation for streaming, and explicit feedback on vendor-native parameter validation.

Python, LlamaIndex, LangChain, Docker Compose: 15 Property Graph, 4 RDF, 10 Vector, OpenSearch, Elasticsearch, Alfresco DBs. 13 data sources (9 auto-sync), KG auto-building, Ontologies, LLMs, Docling or LlamaParse doc processing, GraphRAG, RAG only, Hybrid Search, AI Chat. TypeScript React, Vue, Angular frontends, FastAPI REST backend, MCP Server.

An agentic AI application that allows you to chat with your papers and gather also information from papers on ArXiv and on PubMed

This project enhances the construction of RAG applications by addressing challenges, improving accessibility, scalability, and managing data and user access. It uses Django, Llamaindex, and Google Drive for effective database management.

Notebooks and Code about Generative Ai, LLMs, MLOPS, NLP, CV and Graph databases

DocMind AI is a powerful, open-source Streamlit application leveraging LlamaIndex, LangGraph, and local Large Language Models (LLMs) via Ollama, LMStudio, llama.cpp, or vLLM for advanced document analysis. Analyze, summarize, and extract insights from a wide array of file formats, securely and privately, all offline.

Open Source, Self-Hosted, AI Search and LLM.txt for your website

Examples of RAG using Llamaindex with local LLMs - Gemma, Mixtral 8x7B, Llama 2, Mistral 7B, Orca 2, Phi-2, Neural 7B

Local llamaindex RAG to assist researchers quickly navigate research papers

Timescale Vector Cookbook. A collection of recipes to build applications with LLMs using PostgreSQL and Timescale Vector.

ChatGPT API Usage using LangChain, LlamaIndex, Guardrails, AutoGPT and more

A collection of personally developed projects contributing towards the advancement of Artificial General Intelligence(AGI)

XRAG: eXamining the Core - Benchmarking Foundational Component Modules in Advanced Retrieval-Augmented Generation

Self-hosted RAG search engine — 34 formats, BM25+hybrid search, multi-LLM (Gemini/OpenAI/Claude/Ollama), FastAPI + Docker, production-ready in 3 min

A collection of LlamaIndex Workflows-powered agents that convert natural language to Cypher queries designed to retrieve information from a Neo4j database to answer the question with included benchmark data.

Kyros — The Memory OS for AI Agents Give your AI agents secure, self-correcting, persistent memory in 3 lines of code. Three memory types (episodic, semantic, procedural) with built-in forgetting curves, cryptographic integrity, and automatic contradiction resolution. Model-agnostic REST API with Python and TypeScript SDKs.

From data to vector database effortlessly

(LLM)code，github、、code，pythonLLM、

A MCP server connecting to managed indexes on LlamaCloud

linkedin-jobs-RAG

OWASP Foundation web repository

This sample shows how to quickly get started with LlamaIndex.ai on Azure

Javascript SDK for interacting with the MCP Toolbox for Databases.

AI Engineering Specially Topics- Agentic AI & GenAI Explanation

Ready-to-run examples showing NoPII PII protection with OpenAI, Anthropic, LangChain, LlamaIndex, and more

Agentic AI-driven Quantitative Alpha Builder. Streamline alpha generation with autonomous research navigation and backtesting.

Trust your gut on git

GenAI Experimentation

GPTStonks is a financial chatbot powered by LLMs and enhanced with data frameworks. It provides natural language conversation capabilities for financial topics, making it an ideal choice for a wide range of financial applications.

Agentic RAG to help you build a startup

LlamaCloud nodes for n8n

This project is a comprehensive recruitment and interview assistance system developed based on large models and agents, leveraging the langgraph and llamaindex agent frameworks. It aims to enhance job search efficiency and interview performance by automating and intelligentizing the entire interview process. it is China Software Cup A3 competition

A virtual agent for your virtual books

Building and deploying a document Q&A application on the Hugging Face cloud using Docker.

Examples and guides for building Gen AI applications on the watsonx platform.

Maximem Synap is the memory layer that makes AI agents remember. 92% LongMemEval, 93.2% on LOCOMO. Works natively with LangChain, LlamaIndex, CrewAI, Google ADK, AutoGen, OpenAI Agents, Semantic Kernel, Haystack, and Pydantic AI.

Designed for offline use, this RAG application template offers a starting point for building your own local RAG pipeline, independent of online APIs and cloud-based LLM services like OpenAI.

LLM Chatbot w/ Retrieval Augmented Generation using Llamaindex. It demonstrates how to impl. chunking, indexing, and source citation.

Convert Confluence MIME exports (.doc) to clean Markdown

A framework for hosting and scaling AI agents.

Diagnose the performance of your RAG

Enterprise-ready Document Analysis with Large Language Models

An AI-powered equity research analyst demo using Large Language Models to analyze 10-K filings of renowned NYSE listed companies.

Tailored cloud solutions based on use case, cost, and preferences using natural language with Agentic AI to research, design, price, diagram, and report an optimized result.

RE:0RAG。LangChain、LangGraph、LangSmith、PydanticAI。

The Smart Marketing Assistant is an innovative project that leverages AI agents to automate tasks within an Instagram marketing workflow. This project aims to streamline and optimize various marketing activities, providing users with a powerful tool to enhance their social media strategies.

Fluent CLI is an advanced command-line interface designed to interact seamlessly with multiple workflow systems like FlowiseAI, Langflow, Make, and Zapier. Tailored for developers and IT professionals, Fluent CLI facilitates robust automation, simplifies complex interactions, and enhances productivity through a powerful and command suite

Learn how to talk to Django as any human should -- e.g. Semantic Search and Text-to-SQL.

Open-source deep research for AI agents: 40 channels, 10+ Chinese sources.

Runnable examples for AI agent identity & compliance — certificate issuance, scope enforcement, and integrations for LangChain, CrewAI, Next.js & more.

Match your resume with a job, effortlessly

Multimodal RAG ingests PDFs and generates combined text and image outputs by retrieving and grounding relevant information from the documents.

BigBertha is an architecture design that demonstrates how automated LLMOps (Large Language Models Operations) can be achieved on any Kubernetes cluster using open source container-native technologies

Simple, High Quality, Open Source RAG solution for chatting with your documents

Advanced Coding AI Assistant that uses a Gradio interface to stream coding related responses. ChatRAG supports local and API inference and pulls context from GitHub Repos and local files.

Smart log analysis and debugging assistant for backend developers

A RAG system designed to process documents with multimodal content. It can generate factual, context-aware answers to user queries, based on the documents texts, tables, figures,...

Open-source, LLM-ready SERP and web scraping service

Edge Vector search engine with Vulkan GPU acceleration, hierarchical indexing (HRM2), and native LangChain integration. Gaussian splat-based architecture for similarity search on resource-constrained devices.

Client-side retrieval firewall for RAG systems — blocks prompt injection and secret leaks, re-ranks stale or untrusted content, and keeps all data inside your environment.

Australian Tax Office (ATO) chatbot using LlamaIndex RAG and OpenAI. Features automated documentation processing with ZenML pipelines, Qdrant vector storage, and Streamlit interface. Built for accurate tax information retrieval and natural language query processing.

Debug your RAG pipeline without leaving the terminal. Real-time chunking visualization, batch testing, quality metrics, and one-click export to LangChain/LlamaIndex.

RAG-enabled multi-agentic system for medical diagnosis and assistance

DataRobot Agentic Workflow Templates

Reliable research infrastructure for AI agents. Evidence-backed web search with citations, confidence scores, and Clarity anti-hallucination. MCP server, REST API, Python SDK.

This repository contains code for how to store and query your own data using OpenAI Embeddings and Supabase using JavaScript.

Measuring RAG solutions throughput and latency

An AI-powered platform that uses an agentic workflow to automatically generate Project Requirement Documents (PRDs).

RAG-Ingest: A tool for converting PDFs to markdown and indexing them for enhanced Retrieval Augmented Generation (RAG) capabilities.

Information extraction from unstructured text to build a knowledge graph using techniques from traditional NLP to pre-trained transformers and LLMs for NER and Linking, and Relation Extraction.

Zoom Note Taker Agent for Notion, built with LlamaIndex

Intuitive RAG system on top of LllamaIndex

A RAG implementation on Llama Index using Qdrant vector stores as storage. Take some pdfs, store them in the db, use LLM to inference.

LlamaIndex Powered RAG for PDF, TXT and DOCX files with Tesseract OCR support, Semantic chunking, Document citations with direct page display, Advanced Caching and Duplicate Detection with Redis Vector DB

A sample app for the Retrieval-Augmented Generation pattern using LlamaIndex.ts, running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences using your own data.

Production-ready Agentic AI ChatBot using Llamaindex and Groq-Llama 3.3

A large model app. Integrating various capabilities. Highly scalable, Highly compatible.

API to load and query documents using RAG

A RAG system is just the beginning of harnessing the power of LLM. The next step is creating an intelligent Agent. In Agentic RAG the Agent makes use of available tools, strategies and LLM to generate response in a specialized way. Unlike a simple RAG, an Agent can dynamically choose between tools, routing strategy, etc.

This project aims to compare different Retrieval-Augmented Generation (RAG) frameworks in terms of speed and performance.

EduBot is a powerful RAG (Retrieval-Augmented Generation) chatbot that utilizes the latest SOTA models to provide a seamless and interactive learning experience.

Learn how to build agents that can reason over their own documents

LLM Agent that performs sentiment analysis of drawings and natural language using a combination of Google Gemini Vision model and GPT-4 Turbo with LlamaIndex.

Multimodal document QA: vision + retrieval over PDFs (LLaVA + LlamaIndex)

TurtleSim A* Path Planning with Meta LLaMA-3.1-405B-Instruct model powered by NVIDIA / LlamaIndex Agent

Serverless RAG application with LlamaIndex and code interperter on Azure Container Apps

Trust metadata for AI agents — a stamp costs ~15 tokens, re-verifying costs 15,000. Agents stamp what they verify; the next agent runs 'akf check' and builds on it. pip install akf

Enterprise AI-Enhanced Development Platform with GraphRAG, LlamaIndex, Multi-Tenant Architecture, and Advanced Security & Compliance. Transform your development workflow with persistent memory, intelligent automation, and 99.9% uptime.

Build a RAG preprocessing pipeline

Production-grade architecture patterns, decision frameworks, and best practices for building reliable AI agents. Framework-agnostic reference for engineers.

Knowledge-Sharing Hub using RAG Q&A techniques with LLMs (Llama2 and ChatGPT)

A production-ready RAG (Retrieval Augmented Generation) system for chatting with your documents

Automate Your GitHub Flows with MCP!

This repo contains code related to development of LLM based projects with Langchain and LLamaIndex. It uses RAG, Function calling, agents and tools as of now for interaction with data.

This project demonstrates how GenAI can potentially be leveraged in financial and investment advisory services to provide personalized and tailored recommendations and strategies.

RAG-API: A production-ready Retrieval Augmented Generation API leveraging LLMs, vector databases, and hybrid search for accurate, context-aware responses with citation support.

Local-first evaluation framework for RAG systems and AI Agents. 18+ metrics, CLI + SDK, framework-agnostic. The pytest of AI evaluation.

Browse with the power of Gemini URL Context!

Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2.0, 1040 tests, F1 96.0% with 0% false positives. Docker, GitHub Action, LangChain/LlamaIndex/CrewAI integrations.

Examples of RAG using Llamaindex with local LLMs in Linux - Gemma, Mixtral 8x7B, Llama 2, Mistral 7B, Orca 2, Phi-2, Neural 7B

A collection of Python SDKs that enable developers to build and deploy agents to the UiPath Cloud Platform using different agent frameworks