Quickstart example

First, you pip install the Adaptive SDK.

pip install adaptive_sdk

Instantiate the Adaptive client.

from adaptive_sdk import Adaptive

client = Adaptive(
    base_url="ADAPTIVE_URL",
    api_key="ADAPTIVE_API_KEY"
)

An Adaptive Engine use case is a user-defined workspace where you group together resources such as models, interaction logs and metrics for monitoring and evaluation.

You first create a Customer Support Assistant use case that to service your customer support operations.

use_case = client.use_cases.create(
    key="customer_support_assistant"
)

You deploy the Llama 3.1 70B instruction-tuned model and attach it to the use case, so your customer support agents can start using it. This is a capable base model that can provide satisfactory performance initially. Learn more about other supported models.

# configure default client use case
# SDK methods will target the customer support use case going forward, unless specifically overriden
client = client.set_default_use_case(use_case.key)

model = client.models.attach(
    model="llama-3.3-70b-instruct",
)

You can now integrate the Adaptive SDK in your customer support application, and start making inference requests. The Adaptive Chat API is also compatible with the OpenAI Python library, so there is no need to refactor application code if you were previously using it.

chat_response = client.chat.create(
    model=model.key,
    messages=[
        {
            "role": "system",
            "content": "You are a helpful customer support assistant."
        },
        {
            "role": "user",
            "content": "I was blocked out of my account, I don't know why."
        }
    ]
)
print(chat_response.choices[0].message.content)

Output:

Have you tried recovering your password?

Pairs of messages, completion resulting from chat requests are automatically logged and saved on Adaptive.

Your customer support agent who is using the model as an assistant finds the model’s completion appropriate, and accepts it to be sent to the customer.

To log and aggregate this feedback, you register a new Acceptance feedback key, link it to your use case, and log the agent’s feedback against the completion_id.

feedback_key = client.feedback.register_key(
    key="acceptance",
    kind="bool",
    scoring_type="higher_is_better",
)
_ = client.feedback.link(feedback_key.key)

completion_id = chat_response.choices[0].completion_id

feedback = client.feedback.log_metric(
    completion_id=completion_id,
    feedback_key=feedback_key.key,
    value=True,
)

Learn more about feedback types and logging in Adaptive.

After running your customer support operations with the help of Adaptive Engine, you have accumulated feedback from your human agents in production. To align a model to the preferences of your human agents, you adapt a smaller 8B model on the feedback you logged. This tunes the smaller model using reinforcement learning methods, learning from the successes and failures of the larger, more capable model.

job = client.training.jobs.create(
    model="llama-3.1-8b-instruct",
    config={
        "output_name":"llama-3.1-8b-customer-support",
        "training_config": {
            "training_objective": {"metric_key": feedback_key.key}
        }
    }
)

The job trains and saves a new, improved model that you can immediatelly deploy for better results! Learn more in Adapt a model.