LLM-LangChain

This repository contains my explorations and practice with Large Language Models (LLMs) like OpenAI and Gemini, using the LangChain framework. The main focus is to integrate and experiment with LLMs, showcasing various use cases, tools, and capabilities.

Contents

• LangChain.ipynb: A Jupyter Notebook demonstrating the usage of LLMs via the LangChain framework, including examples with OpenAI and Gemini.

Features

• LLM Integration: Using LangChain to integrate with various LLMs, such as OpenAI and Gemini.
• Prompt Engineering: Crafting prompts for different use cases.
• Chain Logic: Creating chains that process and analyze text with LangChain tools.
• Model Comparison: Side-by-side comparison of LLM responses for different tasks.

Requirements

To run the notebook, you will need the following dependencies:

• langchain
• openai
• gemini (if available via API)
• jupyterlab or notebook

Install the dependencies using pip:

pip install langchain openai jupyterlab

Usage

1. Clone the repository:

   git clone https://github.com/sameertak/LLM-LangChain.git

2. Navigate into the directory:

   cd LLM-LangChain

3. Launch the Jupyter Notebook:

   jupyter notebook Langchain.ipynb

4. Run the cells to see how different LLMs behave with various tasks and prompts using LangChain.

License

This project is licensed under the MIT License. Feel free to use, modify, and distribute the code as needed.

Contributing

If you would like to contribute to this project or have ideas for improvements, feel free to open an issue or submit a pull request.

Acknowledgments

• LangChain: For providing an excellent framework to work with LLMs.
• OpenAI: For providing the API and models used in this notebook.
• Gemini: For being part of the LLM exploration in this notebook.