gkamradt/langchain-tutorials — explained in plain English
Analysis updated 2026-06-24
Follow a guided cookbook notebook covering 7 core LangChain concepts and 9 practical use cases with runnable code and matching YouTube videos
Build a question-answering chatbot over your own documents using LangChain patterns from the tutorial notebooks
Browse community project examples organised by difficulty and category to find a working starting point for your own AI app
| gkamradt/langchain-tutorials | microsoft/tinytroupe | open-mmlab/mmagic | |
|---|---|---|---|
| Stars | 7,435 | 7,440 | 7,426 |
| Language | Jupyter Notebook | Jupyter Notebook | Jupyter Notebook |
| Setup difficulty | easy | moderate | moderate |
| Complexity | 2/5 | 3/5 | 4/5 |
| Audience | developer | researcher | researcher |
Figures from each repo's GitHub metadata at analysis time.
Most notebooks require an OpenAI or other LLM API key to run the code examples.
This repository is a collection of tutorials and code examples for LangChain, a library that helps developers build applications powered by large language models. LangChain provides building blocks for tasks like asking questions over your own documents, summarizing text, extracting structured data from unstructured sources, and building chatbot-style interfaces. This repository is aimed at developers who want to learn how to use LangChain through practical examples rather than just reading the official documentation. The recommended learning path in the README starts with two cookbook notebooks. The first covers seven core concepts in LangChain, and the second covers nine practical use cases. Each notebook has a matching YouTube video. There are also links to prompt engineering resources for those who are new to writing effective instructions for AI models. Beyond the cookbooks, the repository includes a gallery of community-submitted projects organized by difficulty level (beginner, intermediate, and advanced) and by category. The categories covered include summarization, question answering over documents, data extraction, evaluation of AI outputs, chatbots, and AI agents. Most entries in the gallery link to separate repositories with the full code for each project. The tutorials use Jupyter Notebooks, which are files that combine code, explanatory text, and output in a single document that can be run interactively in the browser through tools like Google Colab. The README includes a link to a beginner video explaining how to use notebooks if that format is unfamiliar. The repository is maintained by Greg Kamradt and accepts contributions via pull request. It accompanies a YouTube channel and email newsletter focused on practical applications of AI tools for developers.
A curated collection of Jupyter Notebook tutorials for learning LangChain, covering document Q&A, summarization, data extraction, AI agents, and chatbots, with YouTube walkthroughs and a community project gallery.
Mainly Jupyter Notebook. The stack also includes Python, LangChain, Jupyter Notebook.
Setup difficulty is rated easy, with roughly 30min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.