Skip to content

ChatLocalAI

LocalAI Setup

LocalAI is a drop-in replacement REST API that’s compatible with OpenAI API specifications for local inferencing. It allows you to run LLMs (and not only) locally or on-prem with consumer grade hardware, supporting multiple model families that are compatible with the ggml format.

To use ChatLocalAI within Akilibot, follow the steps below:

  1. bash
  2. cd LocalAI
  3. bash # copy your models to models/ cp your-model.bin models/

For example:

Download one of the models from gpt4all.io

# Download gpt4all-j to models/
wget https://gpt4all.io/models/ggml-gpt4all-j.bin -O models/ggml-gpt4all-j

In the /models folder, you should be able to see the downloaded model in there:

Refer here for list of supported models.

  1. bash docker compose up -d --pull always
  2. Now API is accessible at localhost:8080
# Test API
curl http://localhost:8080/v1/models
# {"object":"list","data":[{"id":"ggml-gpt4all-j.bin","object":"model"}]}

Akilibot Setup

Drag and drop a new ChatLocalAI component to canvas:

Fill in the fields:

  • Base Path: The base url from LocalAI such as http://localhost:8080/v1
  • Model Name: The model you want to use. Note that it must be inside /models folder of LocalAI directory. For instance: ggml-gpt4all-j.bin

Info

If LocalAI is not reachable from the public internet, expose it via a secure URL or tunnel that the platform can reach. Do not use localhost addresses — the platform cannot resolve them.

That's it! For more information, refer to LocalAI docs.