Local AI
Set up local models with LocalAI (LLama, GPT4All, Vicuna, Falcon, etc.)
Preparationβ
Go to https://github.com/go-skynet/LocalAI and follow their instruction to run a model on your device.
For example, here is the command to setup LocalAI with Docker:
Note that we added the --cors true
parameter to the command to make sure the local server is accessible from the browser. AIChatOne will send requests to the local model directly from the browser.
Configuration
We're using the gemma:2b
model in this example.
API Key is required but ignored, so you can input any string.
Issue | Resolution |
CORS related issues CORS | Make sure your server configuration allows the endpoint to be accessible from the browser. Open the Network tab in the browser console to see more details. |
Long waiting time | In the first request, your model can take a long time to respond. Check the terminal log of the Docker process to see if anything goes wrong. |
API Key Missing | AIChatOne does not support API key authentication for custom model yet. Please reconfigurate your custom model to remove API key requirement. |
Last updated