mlflow.openai

The mlflow.openai module provides an API for logging and loading OpenAI models.

Credential management for OpenAI on Databricks

Warning

Specifying secrets for model serving with MLFLOW_OPENAI_SECRET_SCOPE is deprecated. Use secrets-based environment variables instead.

When this flavor logs a model on Databricks, it saves a YAML file with the following contents as openai.yaml if the MLFLOW_OPENAI_SECRET_SCOPE environment variable is set.

OPENAI_API_BASE: {scope}:openai_api_base
OPENAI_API_KEY: {scope}:openai_api_key
OPENAI_API_KEY_PATH: {scope}:openai_api_key_path
OPENAI_API_TYPE: {scope}:openai_api_type
OPENAI_ORGANIZATION: {scope}:openai_organization

{scope} is the value of the MLFLOW_OPENAI_SECRET_SCOPE environment variable.
The keys are the environment variables that the openai-python package uses to configure the API client.
The values are the references to the secrets that store the values of the environment variables.

When the logged model is served on Databricks, each secret will be resolved and set as the corresponding environment variable. See https://docs.databricks.com/security/secrets/index.html for how to set up secrets on Databricks.

mlflow.openai.autolog(log_input_examples=False, log_model_signatures=False, log_models=False, log_datasets=False, disable=False, exclusive=False, disable_for_unsupported_versions=False, silent=False, registered_model_name=None, extra_tags=None, log_traces=True)[source]

Note

Experimental: This function may change or be removed in a future release without warning.

Note

Autologging is known to be compatible with the following package versions: 1.17.0 <= openai <= 1.51.2. Autologging may not succeed when used with package versions outside of this range.

Enables (or disables) and configures autologging from OpenAI to MLflow. Raises MlflowException if the OpenAI version < 1.0.

Parameters

log_input_examples – If True, input examples from inference data are collected and logged along with Langchain model artifacts during inference. If False, input examples are not logged. Note: Input examples are MLflow model attributes and are only collected if log_models is also True.
log_model_signatures – If True, ModelSignatures describing model inputs and outputs are collected and logged along with OpenAI model artifacts during inference. If False, signatures are not logged. Note: Model signatures are MLflow model attributes and are only collected if log_models is also True.
log_models – If True, OpenAI models are logged as MLflow model artifacts. If False, OpenAI models are not logged. Input examples and model signatures, which are attributes of MLflow models, are also omitted when log_models is False.
log_datasets – If True, dataset information is logged to MLflow Tracking if applicable. If False, dataset information is not logged.
disable – If True, disables the OpenAI autologging integration. If False, enables the OpenAI autologging integration.
exclusive – If True, autologged content is not logged to user-created fluent runs. If False, autologged content is logged to the active fluent run, which may be user-created.
disable_for_unsupported_versions – If True, disable autologging for versions of OpenAI that have not been tested against this version of the MLflow client or are incompatible.
silent – If True, suppress all event logs and warnings from MLflow during OpenAI autologging. If False, show all events and warnings during OpenAI autologging.
registered_model_name – If given, each time a model is trained, it is registered as a new model version of the registered model with this name. The registered model is created if it does not already exist.
extra_tags – A dictionary of extra tags to set on each managed run created by autologging.
log_traces – If True, traces are logged for OpenAI models. If False, no traces are collected during inference. Default to True.

mlflow.openai.get_default_conda_env()[source]

Note

Experimental: This function may change or be removed in a future release without warning.

Returns: The default Conda environment for MLflow Models produced by calls to save_model() and log_model().

mlflow.openai.get_default_pip_requirements()[source]

Note

Experimental: This function may change or be removed in a future release without warning.

Returns: A list of default pip requirements for MLflow Models produced by this flavor. Calls to save_model() and log_model() produce a pip environment that, at minimum, contains these requirements.

mlflow.openai.load_model(model_uri, dst_path=None)[source]

Note

Experimental: This function may change or be removed in a future release without warning.

Load an OpenAI model from a local file or a run.

Parameters

model_uri –
The location, in URI format, of the MLflow model. For example:
- /Users/me/path/to/local/model
- relative/path/to/local/model
- s3://my_bucket/path/to/model
- runs:/<mlflow_run_id>/run-relative/path/to/model
For more information about supported URI schemes, see Referencing Artifacts.
dst_path – The local filesystem path to which to download the model artifact. This directory must already exist. If unspecified, a local output path will be created.

Returns

A dictionary representing the OpenAI model.

mlflow.openai.log_model(model, task, artifact_path, conda_env=None, code_paths=None, registered_model_name=None, signature: mlflow.models.signature.ModelSignature = None, input_example: Union[pandas.core.frame.DataFrame, numpy.ndarray, dict, list, csr_matrix, csc_matrix, str, bytes, tuple] = None, await_registration_for=300, pip_requirements=None, extra_pip_requirements=None, metadata=None, example_no_conversion=None, **kwargs)[source]

Note

Experimental: This function may change or be removed in a future release without warning.

Log an OpenAI model as an MLflow artifact for the current run.

Parameters

model – The OpenAI model name or reference instance, e.g., openai.Model.retrieve("gpt-4o-mini").
task – The task the model is performing, e.g., openai.chat.completions or 'chat.completions'.
artifact_path – Run-relative artifact path.
conda_env –
Either a dictionary representation of a Conda environment or the path to a conda environment yaml file. If provided, this describes the environment this model should be run in. At a minimum, it should specify the dependencies contained in get_default_conda_env(). If None, a conda environment with pip requirements inferred by mlflow.models.infer_pip_requirements() is added to the model. If the requirement inference fails, it falls back to using get_default_pip_requirements(). pip requirements from conda_env are written to a pip requirements.txt file and the full conda environment is written to conda.yaml. The following is an example dictionary representation of a conda environment:
```
{
    "name": "mlflow-env",
    "channels": ["conda-forge"],
    "dependencies": [
        "python=3.8.15",
        {
            "pip": [
                "openai==x.y.z"
            ],
        },
    ],
}
```
code_paths –
A list of local filesystem paths to Python file dependencies (or directories containing file dependencies). These files are prepended to the system path when the model is loaded. Files declared as dependencies for a given model should have relative imports declared from a common root path if multiple files are defined with import dependencies between them to avoid import errors when loading the model.

For a detailed explanation of code_paths functionality, recommended usage patterns and limitations, see the code_paths usage guide.
registered_model_name – If given, create a model version under registered_model_name, also creating a registered model if one with the given name does not exist.
signature –
ModelSignature describes model input and output Schema. The model signature can be inferred from datasets with valid model input (e.g. the training dataset with target column omitted) and valid model output (e.g. model predictions generated on the training dataset), for example:
```
from mlflow.models import infer_signature

train = df.drop_column("target_label")
predictions = ...  # compute model predictions
signature = infer_signature(train, predictions)
```
input_example – one or several instances of valid model input. The input example is used as a hint of what data to feed the model. It will be converted to a Pandas DataFrame and then serialized to json using the Pandas split-oriented format, or a numpy array where the example will be serialized to json by converting it to a list. Bytes are base64-encoded. When the signature parameter is None, the input example is used to infer a model signature.
await_registration_for – Number of seconds to wait for the model version to finish being created and is in READY status. By default, the function waits for five minutes. Specify 0 or None to skip waiting.
pip_requirements – Either an iterable of pip requirement strings (e.g. ["openai", "-r requirements.txt", "-c constraints.txt"]) or the string path to a pip requirements file on the local filesystem (e.g. "requirements.txt"). If provided, this describes the environment this model should be run in. If None, a default list of requirements is inferred by mlflow.models.infer_pip_requirements() from the current software environment. If the requirement inference fails, it falls back to using get_default_pip_requirements(). Both requirements and constraints are automatically parsed and written to requirements.txt and constraints.txt files, respectively, and stored as part of the model. Requirements are also written to the pip section of the model’s conda environment (conda.yaml) file.
extra_pip_requirements –
Either an iterable of pip requirement strings (e.g. ["pandas", "-r requirements.txt", "-c constraints.txt"]) or the string path to a pip requirements file on the local filesystem (e.g. "requirements.txt"). If provided, this describes additional pip requirements that are appended to a default set of pip requirements generated automatically based on the user’s current software environment. Both requirements and constraints are automatically parsed and written to requirements.txt and constraints.txt files, respectively, and stored as part of the model. Requirements are also written to the pip section of the model’s conda environment (conda.yaml) file.
Warning

The following arguments can’t be specified at the same time:
- conda_env
- pip_requirements
- extra_pip_requirements
This example demonstrates how to specify pip requirements using pip_requirements and extra_pip_requirements.
metadata – Custom metadata dictionary passed to the model and stored in the MLmodel file.
example_no_conversion – This parameter is deprecated and will be removed in a future release. It’s no longer used and can be safely removed. Input examples are not converted anymore.
kwargs – Keyword arguments specific to the OpenAI task, such as the messages (see Supported messages formats for OpenAI chat completion task for more details on this parameter) or top_p value to use for chat completion.

Returns

A ModelInfo instance that contains the metadata of the logged model.

import mlflow
import openai

# Chat
with mlflow.start_run():
    info = mlflow.openai.log_model(
        model="gpt-4o-mini",
        task=openai.chat.completions,
        messages=[{"role": "user", "content": "Tell me a joke about {animal}."}],
        artifact_path="model",
    )
    model = mlflow.pyfunc.load_model(info.model_uri)
    df = pd.DataFrame({"animal": ["cats", "dogs"]})
    print(model.predict(df))

# Embeddings
with mlflow.start_run():
    info = mlflow.openai.log_model(
        model="text-embedding-ada-002",
        task=openai.embeddings,
        artifact_path="embeddings",
    )
    model = mlflow.pyfunc.load_model(info.model_uri)
    print(model.predict(["hello", "world"]))

mlflow.openai.save_model(model, task, path, conda_env=None, code_paths=None, mlflow_model=None, signature: mlflow.models.signature.ModelSignature = None, input_example: Union[pandas.core.frame.DataFrame, numpy.ndarray, dict, list, csr_matrix, csc_matrix, str, bytes, tuple] = None, pip_requirements=None, extra_pip_requirements=None, metadata=None, example_no_conversion=None, **kwargs)[source]

Note

Experimental: This function may change or be removed in a future release without warning.

Save an OpenAI model to a path on the local file system.

Parameters

model – The OpenAI model name.
task – The task the model is performing, e.g., openai.chat.completions or 'chat.completions'.
path – Local path where the model is to be saved.
conda_env –
Either a dictionary representation of a Conda environment or the path to a conda environment yaml file. If provided, this describes the environment this model should be run in. At a minimum, it should specify the dependencies contained in get_default_conda_env(). If None, a conda environment with pip requirements inferred by mlflow.models.infer_pip_requirements() is added to the model. If the requirement inference fails, it falls back to using get_default_pip_requirements(). pip requirements from conda_env are written to a pip requirements.txt file and the full conda environment is written to conda.yaml. The following is an example dictionary representation of a conda environment:
```
{
    "name": "mlflow-env",
    "channels": ["conda-forge"],
    "dependencies": [
        "python=3.8.15",
        {
            "pip": [
                "openai==x.y.z"
            ],
        },
    ],
}
```
code_paths –
A list of local filesystem paths to Python file dependencies (or directories containing file dependencies). These files are prepended to the system path when the model is loaded. Files declared as dependencies for a given model should have relative imports declared from a common root path if multiple files are defined with import dependencies between them to avoid import errors when loading the model.

For a detailed explanation of code_paths functionality, recommended usage patterns and limitations, see the code_paths usage guide.
mlflow_model – mlflow.models.Model this flavor is being added to.
signature –
ModelSignature describes model input and output Schema. The model signature can be inferred from datasets with valid model input (e.g. the training dataset with target column omitted) and valid model output (e.g. model predictions generated on the training dataset), for example:
```
from mlflow.models import infer_signature

train = df.drop_column("target_label")
predictions = ...  # compute model predictions
signature = infer_signature(train, predictions)
```
input_example – one or several instances of valid model input. The input example is used as a hint of what data to feed the model. It will be converted to a Pandas DataFrame and then serialized to json using the Pandas split-oriented format, or a numpy array where the example will be serialized to json by converting it to a list. Bytes are base64-encoded. When the signature parameter is None, the input example is used to infer a model signature.
pip_requirements – Either an iterable of pip requirement strings (e.g. ["openai", "-r requirements.txt", "-c constraints.txt"]) or the string path to a pip requirements file on the local filesystem (e.g. "requirements.txt"). If provided, this describes the environment this model should be run in. If None, a default list of requirements is inferred by mlflow.models.infer_pip_requirements() from the current software environment. If the requirement inference fails, it falls back to using get_default_pip_requirements(). Both requirements and constraints are automatically parsed and written to requirements.txt and constraints.txt files, respectively, and stored as part of the model. Requirements are also written to the pip section of the model’s conda environment (conda.yaml) file.
extra_pip_requirements –
Either an iterable of pip requirement strings (e.g. ["pandas", "-r requirements.txt", "-c constraints.txt"]) or the string path to a pip requirements file on the local filesystem (e.g. "requirements.txt"). If provided, this describes additional pip requirements that are appended to a default set of pip requirements generated automatically based on the user’s current software environment. Both requirements and constraints are automatically parsed and written to requirements.txt and constraints.txt files, respectively, and stored as part of the model. Requirements are also written to the pip section of the model’s conda environment (conda.yaml) file.
Warning

The following arguments can’t be specified at the same time:
- conda_env
- pip_requirements
- extra_pip_requirements
This example demonstrates how to specify pip requirements using pip_requirements and extra_pip_requirements.
metadata – Custom metadata dictionary passed to the model and stored in the MLmodel file.
example_no_conversion – This parameter is deprecated and will be removed in a future release. It’s no longer used and can be safely removed. Input examples are not converted anymore.
kwargs – Keyword arguments specific to the OpenAI task, such as the messages (see Supported messages formats for OpenAI chat completion task for more details on this parameter) or top_p value to use for chat completion.

import mlflow
import openai

# Chat
mlflow.openai.save_model(
    model="gpt-4o-mini",
    task=openai.chat.completions,
    messages=[{"role": "user", "content": "Tell me a joke."}],
    path="model",
)

# Completions
mlflow.openai.save_model(
    model="text-davinci-002",
    task=openai.completions,
    prompt="{text}. The general sentiment of the text is",
    path="model",
)

# Embeddings
mlflow.openai.save_model(
    model="text-embedding-ada-002",
    task=openai.embeddings,
    path="model",
)