https://github.com/bklieger-groq/gradio-groq-basics
Building Blocks for Multi-Modal Gradio Powered by Groq Apps
https://github.com/bklieger-groq/gradio-groq-basics
Last synced: 8 months ago
JSON representation
Building Blocks for Multi-Modal Gradio Powered by Groq Apps
- Host: GitHub
- URL: https://github.com/bklieger-groq/gradio-groq-basics
- Owner: bklieger-groq
- License: mit
- Created: 2024-10-18T02:06:56.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2024-11-05T20:56:51.000Z (about 1 year ago)
- Last Synced: 2025-03-30T06:07:49.533Z (8 months ago)
- Language: Python
- Size: 37.1 KB
- Stars: 108
- Watchers: 2
- Forks: 19
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Building Blocks for Multi-Modal Apps Powered by Gradio and Groq
[Video Demo](https://github.com/user-attachments/assets/0ab0f71a-4b0a-4d58-ae79-02573aa8a21d)
This repository includes an application showing how to build fast multi-modal apps on Gradio powered by Groq. Specifically, it uses Whisper and Llama-3.2-vision to enable voice to text to LLM response, image to text, and traditional chat.
### Quickstart
To run the Gradio app, follow these instructions:
~~~
python3 -m venv venv
~~~
~~~
source venv/bin/activate
~~~
~~~
pip3 install -r requirements.txt
~~~
~~~
export GROQ_API_KEY=gsk...
~~~
~~~
python3 app.py
~~~
And your app will be hosted at http://127.0.0.1:7860!