https://github.com/nebeyoumusie/reflection-70b-chat

This GitHub repository integrates Reflection Llama-3.1 70B, the world's top open-source large language model (LLM), in a Streamlit-based user interface. The LLM is trained using a new technique called Reflection-Tuning, which enables it to detect and correct mistakes in its own reasoning.
https://github.com/nebeyoumusie/reflection-70b-chat

langchain llama3 openrouter python streamlit streamlit-webapp

Last synced: 3 months ago
JSON representation

This GitHub repository integrates Reflection Llama-3.1 70B, the world's top open-source large language model (LLM), in a Streamlit-based user interface. The LLM is trained using a new technique called Reflection-Tuning, which enables it to detect and correct mistakes in its own reasoning.

• Host: GitHub
• URL: https://github.com/nebeyoumusie/reflection-70b-chat
• Owner: NebeyouMusie
• License: mit
• Created: 2024-09-09T10:29:09.000Z (4 months ago)
• Default Branch: main
• Last Pushed: 2024-09-28T17:26:08.000Z (3 months ago)
• Last Synced: 2024-10-12T18:01:45.645Z (3 months ago)
• Topics: langchain, llama3, openrouter, python, streamlit, streamlit-webapp
• Language: Python
• Homepage: https://reflection-70b.streamlit.app/
• Size: 31.3 KB
• Stars: 2
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Reflection 70B Chat

![Reflection 70B Chat UI Image](./images/reflection-ui.png)

## Description

- This GitHub repository integrates `Reflection Llama-3.1 70B`, the world's top open-source large language model (LLM), in a Streamlit-based user interface. The LLM is trained using a new technique called Reflection-Tuning, which enables it to detect and correct mistakes in its own reasoning.

## Libraries Used

 - requests

 - streamlit

 - langchain

 - python-dotenv

 - langchain_community

## File and Folder Explanation

1. `lib`: contains configuration and utility code files.

2. `images`: contains UI image.

3. `app.py`: main function that will run the Streamlit UI.

4. `lib/conifg.py`: contains functions to load our environment variables and get our api keys.

5. `lib/utils.py`: contains a function to setup our llm, accept user query and provide response.

## Installation

 1. Prerequisites

    - Git

    - Command line familiarity

 2. Clone the Repository: `git clone https://github.com/NebeyouMusie/Reflection-70B-Chat.git`

 3. Create and Activate Virtual Environment (Recommended)

    - `python -m venv venv`

    - `source venv/bin/activate` for Mac and `venv/bin/activate` for Windows

 4. Navigate to the projects directory `cd ./Reflection-70B-Chat` using your terminal

 5. Install Libraries: `pip install -r requirements.txt`

 6. Enter your `OPENROUTER_API_KEY` in the `example.env` file then change the file to `.env`. You can get your `OPENROUTER_API_KEY` from [here](https://openrouter.ai/settings/keys).

 7. run `streamlit run app.py`

 8. open the link that appears on your terminal in your preferred browser.

## Usage

 - Start by typing your question in the Chat Input located at the bottom of the app.

 - The LLM will provide a response, which will include the action it took to give the answer to the user along with the main response(`output`). 

 - Note that it won't remember previous user interactions (NO MEMORY) as that functionality has not been added.

## Collaboration

- Collaborations are welcomed ❤️

## Acknowledgments

 - I would like to thank [OpenRouter](https://openrouter.ai/)

   

## Contact

 - LinkedIn: [Nebeyou Musie](https://www.linkedin.com/in/nebeyou-musie)

 - Gmail: [email protected]

 - Telegram: [Nebeyou Musie](https://t.me/NebeyouMusie)