Many applications today utilize OpenAI models like ChatGPT through APIs such as:
POST https://api.openai.com/v1/chat/completions
This API call triggers the ChatGPT model to generate responses for a chat. With Lemonade Server, we are replacing the OpenAI endpoint with a local LLM. The new API call becomes:
POST http://localhost:8000/api/v1/chat/completions
This allows the same application to leverage local LLMs instead of relying on OpenAI’s cloud-based models. The guides in this folder show how to connect Lemonade Server to popular applications to enable local LLM execution. To run these examples, you’ll need a Windows PC.
To set up Lemonade Server, check out the Lemonade Server guide for installation instructions and the server spec to learn more about the functionality. For more information about 🍋 Lemonade SDK, see the Lemonade SDK README.
If you encounter any issues or have questions, feel free to:
If you’ve connected Lemonade to a new application, feel free to contribute a guide by following our contribution guide found here or let us know at [email protected].