OpenAI API Playground

The reason why I developed this online application is because I enjoy researching various new LLMs, including open source and closed source online. However, after deploying the server, I often have to test it. I searched online for a long time but couldn't find a good one, so I wrote one myself with streamlit. You can play any API server that compatible with OpenAI API, hoping to help friends with similar needs.

Try it on streamlit cloud: https://openai-api-playground.streamlit.app/

Feature List:

• Set API server URL and KEY
• List all models on the server and informations
• Specify a model and set its parameters
• Support for stream or non-stream mode
• Test the connection latency of the API server
• Test the token generation speed of the model with concurrency
• View the complete session state content of Streamlit
• Support multimodal model, including images, audio or video
• Conduct Q&A interactions using uploaded text files as a knowledge base
• Support for online content search for reference

Usage Instructions:

1. Download the Repository:

   git clone https://github.com/hanckjt/openai_api_playground.git
   cd openai_api_playground

2. Install the requirements:

   pip install -r requirements.txt

3. Run the Script:

Linux:

   chmod +x run.sh
   ./run.sh

Windows:

   run.bat