- langchain - ⚡ Building applications with LLMs through composability ⚡
- llama_index - LlamaIndex (formerly GPT Index) is a data framework for your LLM applications
- crewAI - Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
- embedchain - Embedchain is an Open Source RAG Framework that makes it easy to create and deploy AI apps. -
- FlagEmbedding - Dense Retrieval and Retrieval-augmented -
- TaskingAI - Dense Retrieval and Retrieval-augmented LLMs -
- fastRAG - Efficient Retrieval Augmentation and Generation Framework -
- llmware - Providing enterprise-grade LLM-based development framework, tools, and fine-tuned models. -
- llm-applications - A comprehensive guide to building RAG-based LLM applications for production. -
- DB-GPT - An open-source AI native data app development framework with AWEL(Agentic Workflow Expression Language) and agents. Revolutionizing Database Interactions with Private LLM Technology -
- langroid - Harness LLMs with Multi-Agent Programming -
- pandas-ai - Chat with your data (SQL, CSV, pandas, polars, noSQL, etc). PandasAI makes data analysis conversational using LLMs (GPT 3.5 / 4, Anthropic, VertexAI) and RAG. -
- canopy - Retrieval Augmented Generation (RAG) framework and context engine powered by Pinecone -
- autollm - Ship RAG based LLM web apps in seconds. -
‼️ it can set up a fastAPI server quickly, - GraphRAG - A modular graph-based Retrieval-Augmented Generation (RAG) system. A data pipeline and transformation suite that is designed to extract meaningful, structured data from unstructured text using the power of LLMs. -
- DSPy - DSPy: The framework for programming—not prompting—foundation models . -
- Haystack - an end-to-end LLM framework that allows you to build applications powered by LLMs, Transformer models, vector search and more. -
- Dify - an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production. -
- quivr - Your GenAI Second Brain 🧠 A personal productivity assistant (RAG) ⚡️🤖 Chat with your docs (PDF, CSV, ...) & apps using Langchain, GPT 3.5 / 4 turbo, Private, Anthropic, VertexAI, Ollama, LLMs, that you can share with users ! - Ship RAG based LLM web apps in seconds. -
- Langchain-Chatchat - 基于 ChatGLM 等大语言模型与 Langchain 等应用框架实现，开源、可离线部署的 RAG 与 Agent 应用项目。. -
- Chatbot UI - The open-source AI chat app for everyone. -
- Jan - Jan is an open-source alternative to ChatGPT that runs 100% offline on your computer. Multiple engine support (llama.cpp, TensorRT-LLM). -
- fastGPT - FastGPT is a knowledge-based platform built on the LLM, offers out-of-the-box data processing and model invocation capabilities, allows for workflow orchestration through Flow visualization! -
- LangChain-ChatGLM-Webui - 基于LangChain和ChatGLM-6B等系列LLM的针对本地知识库的自动问答 -
- anything-llm - Open-source multi-user ChatGPT for all LLMs, embedders, and vector databases. Unlimited documents, messages, and users in one privacy-focused app. -
- QAnything - Question and Answer based on Anything.
- danswer - Ask Questions in natural language and get Answers backed by private sources. Connects to tools like Slack, GitHub, Confluence, etc. -
- RAGFlow - an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding. -
- Bisheng - an open LLM devops platform for next generation AI applications.. -
- khoj - A copilot to search and chat (using RAG) with your knowledge base (pdf, markdown, org). Use powerful, online (e.g gpt4) or private, offline (e.g mistral) LLMs. -
- rags - Build ChatGPT over your data, all with natural language -
- Verba - Retrieval Augmented Generation (RAG) chatbot powered by Weaviate -
- SuperMemory - Build your own second brain with supermemory. It's a ChatGPT for your bookmarks. Import tweets or save websites and content using the chrome extension (the extension on webstore is not updated, please use the one in the repo) -
- llm-app - LLM App templates for RAG, knowledge mining, and stream analytics. Ready to run with Docker,⚡in sync with your data sources. -
- casibase - ⚡️Open-source AI LangChain-like RAG (Retrieval-Augmented Generation) knowledge database with web UI and Enterprise SSO⚡️ -
- trt-llm-rag-windows - A developer reference project for creating Retrieval Augmented Generation (RAG) chatbots on Windows using TensorRT-LLM -
- GPT-RAG - GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences. -
- rag-demystified - An LLM-powered advanced RAG pipeline built from scratch -
- LARS - An application for running LLMs locally on your device, with your documents, facilitating detailed citations in generated responses. -
- SemanticFinder - frontend-only live semantic search with transformers.js. -
- MindSearch - an open-source AI Search Engine Framework with Perplexity.ai Pro performance. -
- Anthropic Quickstarts - a collection of projects designed to help developers quickly get started with building deployable applications using the Anthropic API. -
- NotebookLlama - An Open Source version of NotebookLM. -
- Botpress - Botpress is the standard developer stack to build, run, and improve conversational AI applications. Powered by natural language understanding, a messaging API, and a fully featured studio, Botpress allows developers and conversation designers around the globe to build remarkable chatbots without compromise. -
- AutoGroq - groundbreaking tool that revolutionizes the way users interact with AI assistants. By dynamically generating tailored teams of AI agents based on your project requirements. -
💥 💥
- micro-agent - An AI agent that writes (actually useful) code for you: JavaScript maily -
💥 💥
- llama-agentic-system - This repo allows you to run Llama 3.1 as a system capable of performing "agentic" tasks -
- Controllable Agent for Complex RAG - n advanced Retrieval-Augmented Generation (RAG) solution designed to tackle complex questions that simple semantic similarity-based retrieval cannot solve. -
- privateGPT - Interact with your documents using the power of GPT, 100% privately, no data leaks
- localGPT - Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.
- ChatFiles - Document Chatbot
- pdfGPT - PDF GPT allows you to chat with the contents of your PDF file by using GPT capabilities. The most effective open source solution to turn your pdf files in a chatbot!
- chatd - Chat with your documents using local AI -
- IncarnaMind - Connect and chat with your multiple documents (pdf and txt) through GPT 3.5, GPT-4 Turbo, Claude and Local Open-Source LLMs
- ArXivChatGuru - Use ArXiv ChatGuru to talk to research papers. This app uses LangChain, OpenAI, Streamlit, and Redis as a vector database/semantic cache. -
- h2ogpt - Private chat with local GPT with document, images, video, etc. -
- qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Qdrant is also available as a fully managed Qdrant Cloud ⛅ including a free tier. -
- vanna - 🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using RAG 🔄. -
- txtai - 💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows -
- infinity - The AI-native database built for LLM applications, providing incredibly fast vector and full-text search -
- postgresml - The GPU-powered AI application database. -
- lancedb - Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps! -
- sparrow - Data extraction with ML and LLM -
- fastembed - Fast, Accurate, Lightweight Python library to make State of the Art Embedding -
- self-rag - SELF-RAG: Learning to Retrieve, Generate and Critique through Self-reflection -
- instructor - Your Gateway to Structured Outputs with OpenAI
- swirl-search - Swirl is open source software that simultaneously searches multiple content sources and returns AI ranked results. -
- kernel-memory - Index and query any data using LLM and natural language, tracking sources and showing citations. -
- AutoRAG - a tool for finding optimal RAG pipeline for “your data.” 🔮 -
- promptfoo - Test your prompts, agents, and RAGs. Use LLM evals to improve your app's quality and catch problems. -
- YiVal - Your Automatic Prompt Engineering Assistant for GenAI Applications -
- LLM Comparator - LLM Comparator is an interactive data visualization tool for evaluating and analyzing LLM responses side-by-side, developed by the PAIR team. -
- Ragas - a framework that helps you evaluate your Retrieval Augmented Generation (RAG) pipelines. -
- Athina - Athina is an Observability and Experimentation platform for AI teams, Python SDK for running evaluations on LLM generated responses. -
- OmniParse - OmniParse is a platform that ingests and parses any unstructured data into structured, actionable data optimized for GenAI (LLM) applications. Whether you are working with documents, tables, images, videos, audio files, or web pages, OmniParse prepares your data to be clean, structured, and ready for AI applications such as RAG, fine-tuning, and more
- Open Parse) - Easily chunks complex documents the same way a human would, including Semantic Processing.
- Unstructured - open-source components for ingesting and pre-processing images and text documents, such as PDFs, HTML, Word docs, and many more.
- ExtractThinker - Library to extract data from files and documents agnostically using LLMs. extract_thinker provides ORM-style interaction between files and LLMs, allowing for flexible and powerful document extraction workflows. -
- nlm-ingestor - This repo provides the service code for llmsherpa API to parse PDF, HTML, DOCX, PPTX. -
- python-readability - Given an HTML document, extract and clean up the main body text and title. -
- llm_aided_ocr - The LLM-Aided OCR Project is an advanced system designed to significantly enhance the quality of Optical Character Recognition (OCR) output. By leveraging cutting-edge natural language processing techniques and large language models (LLMs), this project transforms raw OCR text into highly accurate, well-formatted, and readable documents.. -
- Datachain - a modern Pythonic data-frame library designed for artificial intelligence. It is made to organize your unstructured data into datasets and wrangle it at scale on your local machine. -
- Jina Reader-LM - take noisy HTML and parse it into clean and usable Markdown for training and reasoning.
- Introducing Contextual Retrieval (blog post) - Anthropic shows how to semantically chunk documents, which dramatically improves performance while only costing $1/million chunks due to caching.
- thepi.pe - Python package that can extract clean markdown from PDFs, URLs, slides, videos, and more, ready for any LLM. -
- Montessori-Instruct - Official repository for Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning. -
- Marly - Marly allows your agents to extract tables & text from your PDFs, Powerpoints, etc in a structured format making it easy for them to take subsequent actions (database call, API call, creating a chart etc). -
- Docling - Reads popular document formats (PDF, DOCX, PPTX, Images, HTML, AsciiDoc, Markdown) and exports to Markdown and JSON -
- DocOwl - mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding -
- markitdown - Python tool for converting files and office documents to Markdown. -
- mistral-finetune - mistral-finetune is a light-weight codebase that enables memory-efficient and performant finetuning of Mistral's models.... -
- LLaMA-Factory - A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024). -
- axolotl - a tool designed to streamline the fine-tuning of various AI models, offering support for multiple configurations and architectures.. -
- LlamaDuo - This project showcases an LLMOps pipeline that fine-tunes a small-size LLM model to prepare for the outage of the service LLM. -
- chatgpt-retrieval-plugin - The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.
- RAGxplorer - Open-source tool to visualise your RAG 🔮 -
- deep-chat - a fully customizable AI chat component that can be injected into your website with minimal to no effort. -
- Ollama-Laravel - a Laravel package providing seamless integration with the Ollama API.. -
- fabric - an open-source framework for augmenting humans using AI. It provides a modular framework for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere. -
- n8n - Free and source-available fair-code licensed workflow automation tool. Easily automate tasks across different services. -
- Langtrace - an open-source, Open Telemetry based end-to-end observability tool for LLM applications, providing real-time tracing, evaluations and metrics for popular LLMs, LLM frameworks, vectorDBs and more.. Integrate using Typescript, Python. -
- tokencost - Helps calculate the USD cost of using major Large Language Model (LLMs) APIs by calculating the estimated cost of prompts and completions. -
- quality-prompts - Use and evaluate prompting techniques quickly. -
- Laminar - Open-Source observability, analytics, evals and prompt chains for complex LLM apps. -
- mistral.rs - a fast LLM inference platform supporting inference on a variety of devices, quantization, and easy-to-use application with an Open-AI API compatible HTTP server and Python bindings. -
- MInference - To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filling on an A100 while maintaining accuracy. -
- LiteLLM - Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs). -
- LitServe - an easy-to-use, flexible serving engine for AI models built on FastAPI. Features like batching, streaming, and GPU autoscaling eliminate the need to rebuild a FastAPI server per model. -
- SGLang - a fast-serving framework for large language models and vision language models. -
- MiniCPM-V - a series of end-side multimodal LLMs (MLLMs) designed for vision-language understanding. Models take image and text as inputs and provide high-quality text outputs.-
- DeepSeek-Coder-V2 - an open-source Mixture-of-Experts (MoE) code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks. -
- Trol - Traversal of Layers for Large Language and Vision Models. -
- FunAudioLLM - This project hosts two exciting applications leveraging advanced audio understand and speech generation models to bring your audio experiences to life:
CosyVoiceandSenseVoice- - MobileLLM - MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024. -
- awesome-whisper - Awesome list for Whisper — an open-source AI-powered speech recognition system developed by OpenAI. -
- SmolLM - A series of smol LLMs: 135M, 360M and 1.7B. We release base and Instruct models as well as the training corpus and some WebGPU demos. blazingly fast and remarkably powerful
- CogVideo - Text-to-video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
- MiniCPM-V - MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone
- Flux - the latest promising open-source AI image generation tool. It is capable of running on consumer-grade laptops. -
- Sana - 🖼️ an efficient image generation model that can create high-quality 1024x1024 images in under a second on a laptop GPU. -
- Awesome-LLM-RAG - This repo aims to record advanced papers of Retrieval Agumented Generation (RAG) in LLMs.
- Building RAG-based LLM Applications for Production
- A-Guide-to-Retrieval-Augmented-LLM
- 一文详谈20多种RAG优化方法
- funNLP - NLP民工的乐园: 几乎最全的中文NLP资源库, 在入门到熟悉NLP的过程中，用到了很多github上的包，遂整理了一下，分享在这里。
- AGI-survey - Awesome AGI Survey. Must-read papers on Artificial General Intelligence.
- rag-resources - A collection of curated RAG (Retrieval Augmented Generation) resources.
- RAG-Survey
- Awesome-LLM-RAG-Application - the resources about the application based on LLM with RAG pattern