Skip to content

Clone of ChatGPT to get same functionality using open source LLMs offline, locally.

License

Notifications You must be signed in to change notification settings

Bbs1412/LocalGPT

Repository files navigation

✨ LocalGPT

  • Clone of ChatGPT to get same functionality using open source LLMs offline, locally.
  • Gives interface to interact with LLMs installed locally via Ollama and Streamlit.

Index:

Project Details:

Aim:

To provide an interface to interact with LLMs installed locally, offline, and to save the threads and models used for later use.

Features:

  • Runs Locally with Streamlit
  • Any model from Ollama can be used
  • Supports Streaming Responses with Live Preview
  • Support attachments like Images for vision models like LLama Vision and LLava
  • Supports Threads (Chat Archives)
  • Can rename, create and delete threads
  • Threads are listed as per last used
  • Remembers the last model used with thread, which is auto-loaded next time
  • Can switch between models within same thread
  • Running models can be checked and stopped

Tech Stack:

  • Python
  • Streamlit
  • Ollama

Screenshots:

  • Home Page: Home Page
  • Sample Prompt: Sample Prompt
  • Running Models: Running Models
  • Image support: Vision Model Support

Steps to run:

  1. Clone the repository:

    git clone https://github.com/Bbs1412/LocalGPT
  2. Navigate to the project directory:

    cd LocalGPT
  3. Install the required packages:

    pip install -r requirements.txt
  4. Run the app:

    streamlit run app.py
  5. Open the link in the browser:

    http://localhost:8501

Contributions:

Any contributions or suggestions are welcome!

License:

Code-License

  • This project is licensed under the MIT License
  • See the LICENSE file for details.
  • You can use the code with proper credits to the author.

Contact:

About

Clone of ChatGPT to get same functionality using open source LLMs offline, locally.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages