Create mlflow.deployments.openai

[prithvikannan]

🛠 DevTools 🛠

Install mlflow from this PR

pip install git+https://github.com/mlflow/mlflow.git@refs/pull/10473/merge

Checkout with GitHub CLI

gh pr checkout 10473

Related Issues/PRs

#xxx

What changes are proposed in this pull request?

Introduce a new module mlflow.deployments.openai, which can be used to call OpenAI (and Azure OpenAI) API. This module will handle retry logic and error handling automatically, without any OpenAI dependency.

from mlflow.deployments import get_deploy_client
client = get_deploy_client("openai")
client.predict(
    endpoint="gpt-4",
    inputs={
        "messages": [
            {"role": "user", "content": "Hello!"},
        ],
    },
)

How is this PR tested?

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

Manual e2e test

OpenAI

> import os
> os.environ["OPENAI_API_KEY"] = "my-openai-key"
> from mlflow.deployments import get_deploy_client
> client = get_deploy_client("openai")
> resp = client.predict(
>     endpoint="gpt-4",
>     inputs={
>         "messages": [
>             {"role": "user", "content": "Hello!"},
>         ],
>     },
> )
> print(resp)
{
  "id": "chatcmpl-8PfclAtfydDOTm6wPcyNfj9iWs669",
  "object": "chat.completion",
  "created": 1701128895,
  "model": "gpt-4-0613",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Sure, please provide your prompt so I can assist you."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}

Azure OpenAI

> import os
> os.environ["OPENAI_API_KEY"] = "my-key"
> os.environ["OPENAI_API_TYPE"] = "azure"
> os.environ["OPENAI_API_VERSION"] = "2023-05-15"
> os.environ["OPENAI_API_BASE"] = "https://my-baze.openai.azure.com/"
> os.environ["OPENAI_DEPLOYMENT_NAME"] = "gpt-35-turbo-16k"
> from mlflow.deployments import get_deploy_client
> client = get_deploy_client("openai")
> resp = client.predict(
>     endpoint="gpt-4",
>     inputs={
>         "messages": [
>             {"role": "user", "content": "Hello!"},
>         ],
>     },
> )
> print(resp)
{
  "id": "chatcmpl-8PfeKjZXEfbL7eWl5BpAVWOoZuXJT",
  "object": "chat.completion",
  "created": 1701128992,
  "model": "gpt-35-turbo-16k",
  "choices": [
    {
      "index": 0,
      "finish_reason": "stop",
      "message": {
        "role": "assistant",
        "content": "Sure, please provide me with your prompt and I'll be happy to help you with it."
      }
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 19,
    "total_tokens": 28
  }
}

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.

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/docs: MLflow documentation pages
• area/examples: Example code
• area/gateway: AI Gateway service, Gateway client APIs, third-party Gateway integrations
• 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

[github-actions]

Documentation preview for 67947dc will be available here when this CircleCI job completes successfully.

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/7197859184.

[prithvikannan]

moving this file out of mlflow/openai so that we can use the utils without running the imports from mlflow/openai/__init__.py

[harupy]

LGTM

[dbczumar]

LGTM! Can we add docs in a follow-up PR?