Add tracing to OpenAI autologging

[gabrielfu]

🛠 DevTools 🛠

Install mlflow from this PR

pip install git+https://github.com/mlflow/mlflow.git@refs/pull/12267/merge

Checkout with GitHub CLI

gh pr checkout 12267

Related Issues/PRs

#xxx

What changes are proposed in this pull request?

Add tracing to OpenAI autologging

How is this PR tested?

• Existing unit/integration tests
• New unit/integration tests
• Manual tests

Code:

import mlflow
import openai

mlflow.openai.autolog(
    log_input_examples=True,
    log_model_signatures=True,
    log_models=True,
    log_datasets=True,
)
mlflow.set_experiment("openai_new_example")

client = openai.OpenAI(
    api_key=...,
)
messages = [{"role": "user", "content": "Say 'hello world!'"}]
output = client.chat.completions.create(
    model="gpt-3.5-turbo",
    messages=messages,
    temperature=0.0,
)

Successful call:

Failed call (e.g., setting temperature=5.0):

Does this PR require documentation update?

• No. You can skip the rest of this section.
• Yes. I've updated:
  • Examples
  • API references
  • Instructions

Release Notes

Is this a user-facing change?

• No. You can skip the rest of this section.
• Yes. Give a description of this change to be included in the release notes for MLflow users.

Add tracing to OpenAI autologging

What component(s), interfaces, languages, and integrations does this PR affect?

Components

• area/artifacts: Artifact stores and artifact logging
• area/build: Build and test infrastructure for MLflow
• area/deployments: MLflow Deployments client APIs, server, and third-party Deployments integrations
• area/docs: MLflow documentation pages
• area/examples: Example code
• area/model-registry: Model Registry service, APIs, and the fluent client calls for Model Registry
• area/models: MLmodel format, model serialization/deserialization, flavors
• area/recipes: Recipes, Recipe APIs, Recipe configs, Recipe Templates
• area/projects: MLproject format, project running backends
• area/scoring: MLflow Model server, model deployment tools, Spark UDFs
• area/server-infra: MLflow Tracking server backend
• area/tracking: Tracking Service, tracking client APIs, autologging

Interface

• area/uiux: Front-end, user experience, plotting, JavaScript, JavaScript dev server
• area/docker: Docker use across MLflow's components, such as MLflow Projects and MLflow Models
• area/sqlalchemy: Use of SQLAlchemy in the Tracking Service or Model Registry
• area/windows: Windows support

Language

• language/r: R APIs and clients
• language/java: Java APIs and clients
• language/new: Proposals for new client languages

Integrations

• integrations/azure: Azure and Azure ML integrations
• integrations/sagemaker: SageMaker integrations
• integrations/databricks: Databricks integrations

How should the PR be classified in the release notes? Choose one:

• rn/none - No description will be included. The PR will be mentioned only by the PR number in the "Small Bugfixes and Documentation Updates" section
• rn/breaking-change - The PR will be mentioned in the "Breaking Changes" section
• rn/feature - A new user-facing feature worth mentioning in the release notes
• rn/bug-fix - A user-facing bug fix worth mentioning in the release notes
• rn/documentation - A user-facing documentation change worth mentioning in the release notes

Should this PR be included in the next patch release?

Yes should be selected for bug fixes, documentation updates, and other small changes. No should be selected for new features and larger changes. If you're unsure about the release classification of this PR, leave this unchecked to let the maintainers decide.

What is a minor/patch release?

• Minor release: a release that increments the second part of the version number (e.g., 1.2.0 -> 1.3.0).
  Bug fixes, doc updates and new features usually go into minor releases.
• Patch release: a release that increments the third part of the version number (e.g., 1.2.0 -> 1.2.1).
  Bug fixes and doc updates usually go into patch releases.

• Yes (this PR will be cherry-picked and included in the next patch release)
• No (this PR will be included in the next minor release)

[gabrielfu]

this lets us test error behaviours. openai will throw a openai.BadRequestError when a 400 response is returned

[gabrielfu]

Hi @harupy , would you be able to review this? :)

[harupy]

Can we add log_traces to mlflow.openai.auotlog as a flag to disable/enable trace logging? langchain autolog has the same flag.

[gabrielfu]

sure, added!

[harupy]

Sorry for the late review, thanks for the PR!

[gabrielfu]

no worries :)

[github-actions]

Documentation preview for 40b3a46 will be available when this CircleCI job
completes successfully.

• Top page
• Changed pages

More info

• Ignore this comment if this PR does not change the documentation.
• It takes a few minutes for the preview to be available.
• The preview is updated when a new commit is pushed to this PR.
• This comment was created by https://github.com/mlflow/mlflow/actions/runs/9656436307.

[harupy]

Suggested change

	log_traces: If ``True``, traces are logged for OpenAI models by using
	MlflowLangchainTracer as a callback during inference. If ``False``, no traces are
	collected during inference. Default to ``True``.
	log_traces: If ``True``, traces are logged for OpenAI models. If ``False``, no traces are
	collected during inference. Default to ``True``.

[gabrielfu]

fixed

[harupy]

Manually ran examples/openai/autologging/instantiated_client.py on my machine. It looks great!

[harupy]

LGTM!