h4cker/ai_research/LangChain

LangChain Resources

This section includes several resources and examples of using LangChain.

Langchain Smith and Cookbook

• Langchain Smith: a unified developer platform for building, testing, and monitoring LLM applications.
• Chat Langchain: Ask me anything about LangChain's Python documentation!
• Langchain Cookbook

LangChain Framework

• LangChain: the original 🐍
• LangChain.js: the js brother ✨
• Concepts: Langchain concepts doc
• Twitter account: follow to get fresh updates
• Youtube Channel
• Discord: discussion
• Langchain Blog: The Official Langchain blog
• LangChainHub: collection of all artifacts useful for working with LangChain primitives such as prompts, chains and agents
• LangServe: LangServe helps developers deploy LangChain runnables and chains as a REST API.

Ports to other languages

List of non-official ports of LangChain to other languages.

• Langchain Go: Golang Langchain
• LangchainRb: Ruby Langchain
• BoxCars: Ruby gem, Building applications with composability using Boxcars with LLM's. Inspired by LangChain.
• LangTorch: Building composable LLM applications with Java / JVM. Inspired by LangChain.
• LangChain4j: LangChain for Java
• LangChainJSDotNet: Use the official LangChain.js library in .NET
• LangChainDart: Build powerful LLM-based Dart/Flutter applications.

Tools

Low-code

• Flowise: Drag & drop UI to build your customized LLM flow using LangchainJS
• Langflow: LangFlow is a UI for LangChain

Services

• GPTCache: A Library for Creating Semantic Cache for LLM Queries
• Gorilla: An API store for LLMs
• LlamaHub: a library of data loaders for LLMs made by the community
• EVAL: Elastic Versatile Agent with Langchain. will execute all your requests.
• Auto-evaluator: a lightweight evaluation tool for question-answering using Langchain
• Langchain visualizer: visualization and debugging tool for LangChain workflows
• LLM Strategy: implementing the Strategy Pattern using LLMs
• datasetGPT: A command-line interface to generate textual and conversational datasets with LLMs.
• spellbook-forge: Make your LLM prompts executable and version controlled.
• Auto Evaluator: Langchain auto evaluator
• Jina: Langchain Apps on Production with Jina
• Gradio Tools: Gradio 🤝 LLM Agents
• steamship-langchain: adapters for Steamship, enabling LangChain developers to rapidly deploy their apps on Steamship 🐍
• LangForge: A Toolkit for Creating and Deploying LangChain Apps
• BentoChain: LangChain Deployment on BentoML
• LangCorn: Serving LangChain apps automagically with FastApi
• Langchain Service: Opinionated Langchain setup with Qdrant vector store and Kong gateway
• Lanarky: 🚢 Ship production-ready LLM projects with FastAPI
• Dify: One API for plugins and datasets, one interface for prompt engineering and visual operation, all for creating powerful AI applications.
• LangchainJS Worker: LangchainJS worker on cloudflare
• Chainlit: Build Python LLM apps in minutes ⚡️
• Psychic: Universal APIs for unstructured data. Sync documents from SaaS tools to a SQL or vector database, where they can be easily queried by AI applications like ChatGPT.
• Zep: Zep: A long-term memory store for LLM / Chatbot applications
• Langchain Decorators: a layer on the top op LangChain that provides syntactic sugar 🍭 for writing custom langchain prompts and chains
• FastAPI + Chroma: An Example Plugin for ChatGPT, Utilizing FastAPI, LangChain and Chroma
• AilingBot: Quickly integrate applications built on Langchain into IM such as Slack, WeChat Work, Feishu, DingTalk.
• Llama2 Embedding Server: Llama2 Embeddings FastAPI Service using LangChain

Agents

• Private GPT: Interact privately with your documents using the power of GPT, 100% privately, no data leaks
• CollosalAI Chat: implement LLM with RLHF, powered by the Colossal-AI project
• AgentGPT: AI Agents with Langchain & OpenAI (Vercel / Nextjs)
• Local GPT: Inspired on Private GPT with the GPT4ALL model replaced with the Vicuna-7B model and using the InstructorEmbeddings instead of LlamaEmbeddings
• GPT Researcher: GPT Researcher is an autonomous agent designed for comprehensive online research on a variety of tasks.
• ThinkGPT: Agent techniques to augment your LLM and push it beyond its limits
• Camel-AutoGPT: role-playing approach for LLMs and auto-agents like BabyAGI & AutoGPT
• RasaGPT: RasaGPT is the first headless LLM chatbot platform built on top of Rasa and Langchain.
• SkyAGI: Emerging human-behavior simulation capability in LLM agents
• PyCodeAGI: A small AGI experiment to generate a Python app given what app the user wants to build
• BabyAGI UI: Make it easier to run and develop with babyagi in a web app, like a ChatGPT
• SuperAgent: Deploy LLM Agents to production
• Voyager: An Open-Ended Embodied Agent with Large Language Models
• ix: Autonomous GPT-4 agent platform
• DuetGPT: A conversational semi-autonomous developer assistant, AI pair programming without the copypasta.
• Multi-Modal LangChain agents in Production: Deploy LangChain Agents and connect them to Telegram
• DemoGPT: DemoGPT enables you to create quick demos by just using prompt. It applies ToT approach on Langchain documentation tree.
• SuperAGI: SuperAGI - A dev-first open source autonomous AI agent framework
• Autonomous HR Chatbot: An autonomous agent that can answer HR related queries autonomously using the tools it has on hand
• BlockAGI: BlockAGI conducts iterative, domain-specific research, and outputs detailed narrative reports to showcase its findings
• waggledance.ai: An opinionated, concurrent system of AI Agents. It implements Plan-Validate-Solve with data and tools for general goal-solving.

Templates

• AI: Vercel template to build AI-powered applications with React, Svelte, and Vue, fist class support for LangChain
• create-t3-turbo-ai: t3 based, Langchain-friendly boilerplate for building type-safe, full-stack, LLM-powered web apps with Nextjs and Prisma
• LangChain.js LLM Template: LangChain LLM template that allows you to train your own custom AI LLM model.
• Streamlit Template: template for how to deploy a LangChain on Streamlit
• Codespaces Template: a Codespaces template for getting up-and-running with LangChain in seconds!
• Gradio Template: template for how to deploy a LangChain on Gradio
• AI Getting Started: A Javascript AI getting started stack for weekend projects, including image/text models, vector stores, auth, and deployment configs
• Embedchain: Framework to easily create LLM powered bots over any dataset.

Platforms

• Modal: End-to-end stack for cloud/ML compute
• Metal: Metal is a managed service that allows you to build AI products without the hassle of managing infrastructure
• Graphsignal: Observability for AI agents and LLM-powered applications. Trace, monitor and debug LangChain in production.
• Mona: Live monitoring for your OpenAI usage
• Openllmetry: Open-source observability for your LLM application, based on OpenTelemetry

Open Source Projects

Knowledge Management

• Quiver: Dump your brain into your GenerativeAI Vault
• DocsGPT: GPT-powered chat for documentation search & assistance.
• Chaindesk: The no-code platform for semantic search and documents retrieval
• Knowledge GPT: Accurate answers and instant citations for your documents.
• Knowledge: Knowledge is a tool for saving, searching, accessing, and exploring all of your favorite websites, documents and files.
• Anything LLM: A full-stack application that turns any documents into an intelligent chatbot with a sleek UI and easier way to manage your workspaces.
• DocNavigator: AI-powered chatbot builder that is designed to improve the user experience on product documentation/support websites
• ChatFiles: Upload your document and then chat with it. Powered by GPT / Embedding / TS / NextJS.
• DataChad: A streamlit app that let's you chat with any data source. Supporting both OpenAI and local mode with GPT4All.
• Second Brain AI Agent: A streamlit app automaticall dialog with your second brain notes using OpenAI and ChromaDB locally.
• examor: A website application that allows you to take exams based on your knowledge notes. Let you really remember what you have learned and written.

Other / Chatbots

• DB GPT: Interact your data and environment using the local GPT, no data leaks, 100% privately, 100% security
• AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
• Paper QA: LLM Chain for answering questions from documents with citations
• Chat Langchain: locally hosted chatbot specifically focused on question answering over the LangChain documentation
• Langchain Chat: another Next.js frontend for LangChain Chat.
• Book GPT: drop a book, start asking question.
• Chat LangchainJS: NextJS version of Chat Langchain
• Doc Search: converse with book - Built with GPT-3
• Fact Checker: fact-checking LLM outputs with langchain
• MM ReAct: Multi Modal ReAct Design
• QABot: Query local or remote files or databases with natural language queries powered by langchain and openai
• GPT Automator: Your voice-controlled Mac assistant.
• Teams LangchainJS: Demonstration of LangChainJS with Teams / Bot Framework bots
• ChatGPT: ChatGPT & langchain example for node.js & Docker
• FlowGPT: Generate diagram with AI
• langchain-text-summarizer: A sample streamlit application summarizing text using LangChain
• Langchain Chat Websocket: About LangChain LLM chat with streaming response over websockets
• langchain_yt_tools: Langchain tools to search/extract/transcribe text transcripts of Youtube videos
• SmartPilot: A Python program leveraging OpenAI's language models to generate, analyze, and select the best answer to a given question
• Howdol: a helpful chatbot that can answer questions
• MrsStax: QA Slack Bot
• ThoughtSource⚡: A framework for the science of machine thinking
• ChatGPT Langchain: ChatGPT clone using langchain on Huggingface
• Chat Math Techniques: langchain chat with math techniques on Huggingface
• Notion QA: Notion Question-Answering Bot
• QNimGPT: Play Nim against an IBM Quantum Computer simulator or OpenAI GPT-3.5
• ChatPDF: ChatGPT + Enterprise data with Azure OpenAI
• Chat with Scanned Documents: A demo chatting with documents scanned with Dynamic Web TWAIN.
• snowChat ❄️: Chat with you're snowflake database
• Airtable-QnA: 🌟 a question-answering tool for your Airtable content
• WingmanAI: tool for interacting with real-time transcription of both system and microphone audio
• TutorGPT: Dynamic few-shot metaprompting for the task of tutoring.
• Cheshire Cat: Custom AGI boT with ready-to-use chat integration and plugins development platform.
• Got Chaat Bot: Repo for creating GoT Chatbots (ex: talk with Tyrion Lannister)
• Dialoqbase: web application that allows you to create custom chatbots with your own knowledge base
• CSV-AI 🧠: CSV-AI is the ultimate app powered by LangChain that allows you to unlock hidden insights in your CSV files.
• MindGeniusAI: Auto generate MindMap with ChatGPT
• Robby-Chatbot: AI chatbot 🤖 for chat with CSV, PDF, TXT files 📄 and YTB videos 🎥 | using Langchain🦜 | OpenAI | Streamlit ⚡.
• AI Chatbot: A full-featured, hackable Next.js AI chatbot built by Vercel Labs
• Instrukt: A fully-fledged AI environment in the terminal. Build, test and instruct agents.
• OpenChat: LLMs custom-chatbots console ⚡.
• Twitter Agent: Scrape tweets, summarize them and chat with them in an interactive terminal.
• GPT Migrate: Easily migrate your codebase from one framework or language to another.
• Code Interpreter API: About Open source implementation of the ChatGPT Code Interpreter
• Recommender: Create captivating email marketing campaigns tailored to your business needs
• Autonomous HR Chatbot An autonomous HR agent that can answer user queries using tools
• Lobe Chat An open-source, extensible (Function Calling), high-performance chatbot framework
• Funcchain: write prompts, pythonic
• PersonalityChatbot: Langchain chatbot for chat with personality using Langchain🦜 | LangSmith | MongoDB.

Learn

Notebooks

• Langchain Tutorials: overview and tutorial of the LangChain Library
• LangChain Chinese Getting Started Guide: Chinese LangChain Tutorial for Beginners
• Flan5 LLM: PDF QA using LangChain for chain of thought and multi-task instructions, Flan5 on HuggingFace
• LangChain Handbook: Pinecone / James Briggs' LangChain handbook
• Query the YouTube video transcripts: Query the YouTube video transcripts, returning timestamps as sources to legitimize the answers
• llm-lobbyist: Large Language Models as Corporate Lobbyists
• Langchain Semantic Search: Search and indexing your own Google Drive Files using GPT3, LangChain, and Python
• GPT Political Compass
• llm-grovers-search-party: Leveraging Qiskit, OpenAI and LangChain to demonstrate Grover's algorithm
• TextWorld ReAct Agent
• LangChain <> Wolfram Alpha
• BYO Knowledge Graph
• Large Language Models Course

Videos Playlists

• LangChain Series by Sam Witteveen
• LangChain Tutorials Playlist
• LangChain James Briggs' Playlist
• Greg Kamradt Playlist

Other LLM Frameworks

• Transformers Agents: Provides a natural language API on top of transformers
• LlamaIndex: provides a central interface to connect your LLM's with external data.
• Botpress: The building blocks for building chatbots
• Haystack: NLP framework to interact with your data using Transformer models and LLMs
• Semantic Kernel: Microsoft C# SDK to integrate cutting-edge LLM technology quickly and easily into your apps
• Promptify: Prompt Engineering | Use GPT or other prompt based models to get structured output.
• PromptSource: About Toolkit for creating, sharing and using natural language prompts.
• Agent-LLM: An Artificial Intelligence Automation Platform.
• LLM Agents: Build agents which are controlled by LLMs
• MiniChain: A tiny library for coding with large language models.
• Griptape: Python framework for AI workflows and pipelines with chain of thought reasoning, external tools, and memory.
• llm-chain: is a powerful rust crate for building chains in LLMs allowing you to summarise text and complete complex tasks.
• PromptFlow: Create executable flowcharts that link LLMs (Large Language Models), Prompts, Python functions, and conditional logic together.
• OpenLM: a drop-in OpenAI-compatible library that can call LLMs from any other hosted inference API. Also Typescript
• Dust: Design and Deploy Large Language Model Apps
• e2b: Open-source platform for building & deploying virtual developers’ agents
• SuperAGI: A dev-first open source autonomous AI agent framework.
• SmartGPT: A program that provides LLMs with the ability to complete complex tasks using plugins.
• TermGPT: Giving LLMs like GPT-4 the ability to plan and execute terminal commands
• ReLLM: Regular Expressions for Language Model Completions.
• OpenDAN: open source Personal AI OS , which consolidates various AI modules in one place for your personal use.
• OpenLLM: An open platform for operating large language models (LLMs) in production. Fine-tune, serve, deploy, and monitor any LLMs with ease using OpenLLM.
• FlagAI: FlagAI (Fast LArge-scale General AI models) is a fast, easy-to-use and extensible toolkit for large-scale model.
• AI.JSX: The AI Application Framework for Javascript
• Outlines: Generative Model Programming (Python)
• AI Utils: TypeScript-first library for building AI apps, chatbots, and agents.
• MetaGPT: The Multi-Agent Meta Programming Framework: Given one line Requirement, return PRD, Design, Tasks, Repo and CI
• Hyv: Probably the easiest way to use any AI Model in Node.js and create complex interactions with ease.
• Autochain: Build lightweight, extensible, and testable LLM Agents with AutoChain.
• TypeChat: TypeChat is a library that makes it easy to build natural language interfaces using types.
• Marvin: ✨ Build AI interfaces that spark joy
• LMQL: A programming language for large language models.
• LLMFlow: Simple, Explicit and Transparent LLM Apps
• Ax: A comprehensive AI framework for TypeScript
• TextAI: 💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows.
• AgentFlow: About Complex LLM Workflows from Simple JSON.
• Outlines: Fast and reliable neural text generation.
• SimpleAIChat: Python package for easily interfacing with chat apps, with robust features and minimal code complexity.
• LLFn: A light-weight framework for creating applications using LLMs
• LLMStack: No code platform for building LLM-powered applications with custom data.
• Lagent: A lightweight framework for building LLM-based agents
• Embedbase: The native Software 3.0 stack for building AI-powered applications.
• Rivet: An IDE for creating complex AI agents and prompt chaining, and embedding it in your application.
• Promptfoo: Test your prompts. Evaluate and compare LLM outputs, catch regressions, and improve prompt quality.
• RestGPT: An LLM-based autonomous agent controlling real-world applications via RESTful APIs
• LangStream: Framework for building and running event-driven LLM applications using no-code and Python (including LangChain-based) agents.
• Magentic: Seamlessly integrate LLMs as Python functions
• Autogen: Enable Next-Gen Large Language Model Applications.
• AgentVerse Provides a flexible framework that simplifies the process of building custom multi-agent environments for LLMs
• Flappy: Production-Ready LLM Agent SDK for Every Developer ![Github Repo stars]
• MemGPT: Teaching LLMs memory management for unbounded context