Configure another AI Provider

COMING SOON

This page describes how to configure a generic AI Provider for use with the AI Review Assistant.

If you are using ChatGPT, Claude.ai or Ollama, you can directly consult our dedicated guides.

If any of the headers, body content or query parameters require a secret, use the $API_KEY placeholder, and fill the actual value in the API Key section.

Request section

Section	Instructions
API URL	Enter the REST API address for your AI Provider. This has to be the endpoint for a chat (message based) completion
API Key	Enter your API key
Headers	Add all the key-value Http Headers for your AI Provider. For example, a Basic Authorization or a version controlling header.
Query Parameters	Add all key-value pairs that you would find after the `?` in the url (`?key1=value1&key2=value2`)
Request Body	Add all members for the JSON content. For example, the model, a stop sequence, a maximum number of tokens…

Response Section

Section

Instructions

Success Query

Enter the JSON query to retrieve the content of the chat message completion. For example, if the JSON response from the API is

{
  "content": [
    {
      "text": "Hi! My name is Claude.",
      "type": "text"
    }
  ]
}

Then the query will be content[0].text

Error Query

Enter the query to retrieve the error message when an error occurs. This is not strictly necessary, but it will help users when an error pops up.

Test and Save

Click on the Test button and verify that you receive a confirmation message that everything is configured properly.

Click on the Save button.

If you have trouble in configuring our AI Review Assistant, we are happy to help! 🎉