Introduction

In order to know which models you can have access to through Paradigm, a dedicated endpoint is available for you to get the list of available models.

Prerequisites

In order to use the embedding endpoint, here are the prerequisites:

• Having a Paradigm API key: if you do not have one, go to your Paradigm profile and generate a new API key.

Usage methods

There are several ways to call the endpoint:

1. With the OpenAI python client (recommended)
2. With the python requests package: to avoid the OpenAI layer
3. Through a curl request: to do a quick check or a first test

OpenAI python client

Setup

Here is a code snippet setting up the OpenAI python client:

from openai import OpenAI as OpenAICompatibleClient
import os

# Get API key from environment
api_key = os.getenv("PARADIGM_API_KEY")
# Our base url
base_url = "https://paradigm.lighton.ai/api/v2"

# Configure the OpenAI client
client = OpenAICompatibleClient(api_key=api_key, base_url=base_url)

Here the Paradigm API key is set up in an environment variable, but you could very well forward it through a argument parsing method with argparse.

Usage

To get the list of , you can use the client.models.list() method with an available model in Paradigm.
An example is described below:

models_response = client.models.list()

The given response would then follow the OpenAI format:

SyncPage[Model](
    data=[
        Model(
            id=None, 
            created=None, 
            object='model', 
            owned_by=None, 
            name='alfred-40b-1123', 
            model_type='Large Language Model', 
            deployment_type='SageMaker', 
            enabled=True, 
            technical_name='alfred-40b-1123'
        )
    ], 
    object='list'
)

Python requests package

You can also avoid using the OpenAI python class and directly send request to the API endpoint through the requests package.

import requests
import os

# Get API key from environment
api_key = os.getenv("PARADIGM_API_KEY")

response = requests.request(
    method="GET",
    url="https://paradigm.lighton.ai/api/v2/models",
    headers={
        'accept': "application/json",
        'Authorization': f"Bearer {api_key}"
    }
)

print(response.json())

You would then get a JSON answer as a dictionnary:

{
    'object': 'list', 
    'data': [
        {
            'object': 'model', 
            'name': 'alfred-40b-1123', 
            'model_type': 'Large Language Model', 
            'deployment_type': 'SageMaker', 
            'enabled': True, 
            'technical_name': 'alfred-40b-1123'
        }
    ]
}

cURL request

If you would prefer sending a request to Paradigm with a simple cURL command, here is an example:

curl --request GET \
  --url https://paradigm.lighton.ai/api/v2/models \
  --header 'Authorization: Bearer <YOUR_API_KEY>'