This repository contains a collection of Jupyter notebooks that demonstrate different use cases and patterns using LangChain. The goal is to build a hands-on, evolving knowledge base to understand how to combine LLMs with tools like vector stores, custom prompts, document loaders, and more.

langchain-jupyter-notebook/
│
├── data/
│   ├── chroma-db/       # Persisted vector database
│   ├── external/        # Raw markdown or text files for processing
│   └── docs/            # Optional: documentation or supporting files
│
├── notebooks/
│   └── 01_simple_splitter.ipynb  # First example notebook
│
└── src/                # Custom Python modules and helpers

Each notebook explores a different feature or capability of LangChain:

• Chunking and splitting documents
• Creating and querying vector databases
• Using custom prompt templates
• Integrating local LLMs via Ollama
• ...and more coming soon

✅ The notebooks are written to be clear, modular, and beginner-friendly. Feel free to clone, run, and adapt them.

To run the notebooks, you’ll need:

• Python 3.10+
• Jupyter Notebook or JupyterLab
• LangChain, Chroma, Ollama, and other dependencies listed in requirements.txt (to be added)

Want to share your own LangChain pattern, fix something, or improve an existing notebook? Contributions are more than welcome!

• Fork this repo
• Add your notebook or improvement
• Open a pull request with a clear explanation

If you have questions, ideas, or just want to connect — feel free to reach out or open an issue.

Let's build a great collection of LangChain recipes together!