aura-mocks-openai-api plugin

Description

The aura-mocks-openai-api plugin contains the services used by aura-gateway-api to work without real OpenAI services.

Find more information in the Github repository:
https://github.com/Telefonica/aura-mocks-server/tree/master/src/plugins/aura-mocks-openai-api

Currently, the plugin mocks the following services:

• Create Completion

This is part of aura-mocks-server project.

aura-mocks-openai-api API

Endpoints description

Currently, the mock for OpenAI has the following endpoints implemented:

Create chat completions

The endpoint /openai/deployments/:deployment_id/chat/completions is used to create a new chat completion. It is a POST request that receives the following query parameters:

The response can be modified using the content field of the request body.

Using a specific response

The content field of the request body can be used to return a specific response:

{
    "messages": [
        {
            "role": "user",
            "content": "error_400_content_filter"
        }
    ]
}

Using retries profile

The content field of the request body can be used to return responses based on a profile. The retries profile allows to return different responses for each retry. Example:

{
    "messages": [
        {
            "role": "user",
            "content": "user2|retries:status-500&status-200"
        }
    ]
}

In the example above, the retries profile will return the first response with status 500 and then the second response with status 200.

Defined responses

The following table shows the different mock responses that can be used:

The “error_429_exceeded_quota” and “error_429_rate_limit_reached” responses will have the “Retry-After” header set to 5 seconds.