Python AI SDK reference

Overview

This topic documents how to get started with the Python AI SDK, and links to reference information on all of the supported features.

The Python AI SDK is designed for use with LaunchDarkly’s AI Configs. It is currently in a pre-1.0 release and under active development. You can follow development or contribute on GitHub.

Get started

LaunchDarkly AI SDKs interact with AI Configs. AI Configs are the LaunchDarkly resources that manage model configurations and messages for your generative AI applications.

You can use the Python AI SDK to customize your AI Config based on the context that you provide. This means both the messages and the model evaluation in your generative AI application are specific to each end user, at runtime. You can also use the AI SDKs to record metrics from your AI model generation, including duration and tokens.

Follow these instructions to start using the Python AI SDK in your Python application.

Understand version compatibility

The LaunchDarkly Python AI SDK is compatible with Python 3.8.0 and higher.

Install the SDK

First, install the AI SDK as a dependency in your application using your application’s dependency manager. If you want to depend on a specific version, refer to the SDK releases page to identify the latest version.

Here’s how:

$
pip install launchdarkly-server-sdk
>
pip install launchdarkly-server-sdk-ai

Next, import the LaunchDarkly LDAIClient into your application code:

1
import ldclient
2
from ldclient import Context
3
from ldclient.config import Config
4
from ldai.client import LDAIClient, AIConfig, ModelConfig, LDMessage, ProviderConfig

Initialize the client

After you install and import the AI SDK, create a single, shared instance of LDAIClient. Specify your SDK key here to authorize your application to connect to a particular environment within LaunchDarkly.

Here’s how:

1
ldclient.set_config(Config("sdk-key-123abc"))
2
aiclient = LDAIClient(ldclient.get())

Configure the context

Next, configure the context that will use the AI Config, that is, the context that will encounter generated AI content in your application. The context attributes determine which variation of the AI Config LaunchDarkly serves to the end user, based on the targeting rules in your AI Config. If you are using template variables in the messages in your AI Config’s variations, the context attributes also fill in values for the template variables.

Here’s how:

1
context = Context.builder("context-key-123abc") \
2
    .set("firstName", "Sandy") \
3
    .set("lastName", "Smith") \
4
    .set("email", "sandy@example.com") \
5
    .set("groups", ["Google", "Microsoft"]) \
6
    .build()

Customize an AI Config

Then, use config to customize the AI Config. You need to call config each time you generate content from your AI model.

This function returns the customized messages and model along with a tracker instance for recording metrics. Customization means that any variables you include in the messages when you define the AI Config variation have their values set to the context attributes and variables you pass to config. Then, you can pass the customized messages directly to your AI.

The customization process within the AI SDK is similar to evaluating flags in one of LaunchDarkly’s client-side, server-side, or edge SDKs, in that the SDK completes the customization without a separate network call.

Here’s how:

1
fallback_value = AIConfig(
2
    enabled=True,
3
    model=ModelConfig(
4
        name="my-default-model",
5
        parameters={"temperature": 0.8},
6
    ),
7
    messages=[LDMessage(role="system", content="")],
8
    provider=ProviderConfig(name="my-default-provider"),
9
)
10
11
config, tracker = aiclient.config('ai-config-key-123abc', context, fallback_value, { 'example_custom_variable': 'example_custom_value'})

To learn more, read Customizing AI Configs.

Call provider, Record metrics from AI model generation

Finally, use one of the track_[model]_metrics functions to make a request to your generative AI provider and record metrics from your AI model generation. The Python AI SDK provides specific track_[model]_metrics functions using completions from common AI model families.

Here’s how:

1
# Pass in the result of the OpenAI operation.
2
# When calling the OpenAI operation, use details from config.
3
# For instance, you can pass config.model.name
4
# and config.messages[0].content to your specific OpenAI operation.
5
#
6
# CAUTION: If the call inside of track_openai_metrics throws an exception,
7
# the SDK will re-throw that exception
8
9
messages = [] if config.messages is None else config.messages
10
completion = tracker.track_openai_metrics(
11
    lambda:
12
      openai_client.chat.completions.create(
13
          model=config.model.name,
14
          messages=[message.to_dict() for message in messages],
15
      )
16
)

Alternatively, you can use the SDK’s other track* functions to record these metrics manually. You may need to do this if you are using a model for which the SDK does not provide a convenience track_[model]_metrics function. The track_[model]_metrics functions are expecting a response, so you may also need to do this if your application requires streaming.

Make sure to call config each time you generate content from your AI model:

1
config, tracker = aiclient.config('ai-config-key-123abc', context, fallback_value, { 'example_custom_variable': 'example_custom_value'})
2
3
completion = tracker.track_openai_metrics(...)

To learn more, read Tracking AI metrics.

Supported features

This SDK supports the following features:

• Anonymous contexts
• Context configuration
• Customizing AI Configs
• Private attributes
• Tracking AI metrics