chore: import upstream snapshot with attribution

docs/api_reference/source/python_api/exceptions/mlflow.exceptions.rst

@@ -0,0 +1,15 @@
+:orphan:
+
+mlflow.exceptions
+=================
+
+.. exception:: mlflow.exceptions.MlflowException(message, error_code=1, **kwargs)
+
+    Generic exception thrown when an MLflow operation fails
+
+.. automodule:: mlflow.exceptions
+    :members:
+    :undoc-members:
+    :show-inheritance:
+    :exclude-members:
+        MlflowException

docs/api_reference/source/python_api/index.rst

@@ -0,0 +1,33 @@
+.. _python-api:
+
+Python API
+==========
+
+The MLflow Python API is organized into the following modules. The most common functions are
+exposed in the :py:mod:`mlflow` module, so we recommend starting there.
+
+.. toctree::
+  :glob:
+  :maxdepth: 1
+
+  *
+
+
+See also the :ref:`index of all functions and classes<genindex>`.
+
+Log Levels
+----------
+
+MLflow Python APIs log information during execution using the Python Logging API. You can 
+configure the log level for MLflow logs using the following code snippet. Learn more about Python
+log levels at the
+`Python language logging guide <https://docs.python.org/3/howto/logging.html>`_.
+
+.. code-block:: python
+
+    import logging
+
+    logger = logging.getLogger("mlflow")
+
+    # Set log level to debugging
+    logger.setLevel(logging.DEBUG)

docs/api_reference/source/python_api/mlflow.ag2.rst

@@ -0,0 +1,7 @@
+mlflow.ag2
+==========
+
+.. automodule:: mlflow.ag2
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.agno.rst

@@ -0,0 +1,7 @@
+mlflow.agno
+==================
+
+.. automodule:: mlflow.agno
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.anthropic.rst

@@ -0,0 +1,7 @@
+mlflow.anthropic
+================
+
+.. automodule:: mlflow.anthropic
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.artifacts.rst

@@ -0,0 +1,7 @@
+mlflow.artifacts
+================
+
+.. automodule:: mlflow.artifacts
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.autogen.rst

@@ -0,0 +1,7 @@
+mlflow.autogen
+==============
+
+.. automodule:: mlflow.autogen
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.bedrock.rst

@@ -0,0 +1,7 @@
+mlflow.bedrock
+==============
+
+.. automodule:: mlflow.bedrock
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.catboost.rst

@@ -0,0 +1,7 @@
+mlflow.catboost
+===============
+
+.. automodule:: mlflow.catboost
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.client.rst

@@ -0,0 +1,9 @@
+.. _mlflow.tracking:
+
+mlflow.client
+===============
+
+.. automodule:: mlflow.client
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.config.rst

@@ -0,0 +1,7 @@
+mlflow.config
+==============
+
+.. automodule:: mlflow.config
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.crewai.rst

@@ -0,0 +1,7 @@
+mlflow.crewai
+==============
+
+.. automodule:: mlflow.crewai
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.data.rst

@@ -0,0 +1,169 @@
+mlflow.data
+============
+
+The ``mlflow.data`` module helps you record your model training and evaluation datasets to
+runs with MLflow Tracking, as well as retrieve dataset information from runs. It provides the
+following important interfaces:
+
+* :py:class:`Dataset <mlflow.data.dataset.Dataset>`: Represents a dataset used in model training or
+  evaluation, including features, targets, predictions, and metadata such as the dataset's name, digest (hash)
+  schema, profile, and source. You can log this metadata to a run in MLflow Tracking using
+  the :py:func:`mlflow.log_input()` API. ``mlflow.data`` provides APIs for constructing
+  :py:class:`Datasets <mlflow.data.dataset.Dataset>` from a variety of Python data objects, including
+  Pandas DataFrames (:py:func:`mlflow.data.from_pandas()`), NumPy arrays
+  (:py:func:`mlflow.data.from_numpy()`), Spark DataFrames (:py:func:`mlflow.data.from_spark()`
+  / :py:func:`mlflow.data.load_delta()`), Polars DataFrames (:py:func:`mlflow.data.from_polars()`), and more.
+
+* :py:func:`DatasetSource <mlflow.data.dataset_source.DatasetSource>`: Represents the source of a
+  dataset. For example, this may be a directory of files stored in S3, a Delta Table, or a web URL.
+  Each :py:class:`Dataset <mlflow.data.dataset.Dataset>` references the source from which it was
+  derived. A :py:class:`Dataset <mlflow.data.dataset.Dataset>`'s features and targets may differ
+  from the source if transformations and filtering were applied. You can get the
+  :py:func:`DatasetSource <mlflow.data.dataset_source.DatasetSource>` of a dataset logged to a
+  run in MLflow Tracking using the :py:func:`mlflow.data.get_source()` API.
+
+The following example demonstrates how to use ``mlflow.data`` to log a training dataset to a run,
+retrieve information about the dataset from the run, and load the dataset's source.
+
+.. code-block:: python
+
+    import mlflow.data
+    import pandas as pd
+    from mlflow.data.pandas_dataset import PandasDataset
+
+    # Construct a Pandas DataFrame using iris flower data from a web URL
+    dataset_source_url = "http://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-red.csv"
+    df = pd.read_csv(dataset_source_url)
+    # Construct an MLflow PandasDataset from the Pandas DataFrame, and specify the web URL
+    # as the source
+    dataset: PandasDataset = mlflow.data.from_pandas(df, source=dataset_source_url)
+
+    with mlflow.start_run():
+        # Log the dataset to the MLflow Run. Specify the "training" context to indicate that the
+        # dataset is used for model training
+        mlflow.log_input(dataset, context="training")
+
+    # Retrieve the run, including dataset information
+    run = mlflow.get_run(mlflow.last_active_run().info.run_id)
+    dataset_info = run.inputs.dataset_inputs[0].dataset
+    print(f"Dataset name: {dataset_info.name}")
+    print(f"Dataset digest: {dataset_info.digest}")
+    print(f"Dataset profile: {dataset_info.profile}")
+    print(f"Dataset schema: {dataset_info.schema}")
+
+    # Load the dataset's source, which downloads the content from the source URL to the local
+    # filesystem
+    dataset_source = mlflow.data.get_source(dataset_info)
+    dataset_source.load()
+
+.. autoclass:: mlflow.data.dataset.Dataset
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. autoclass:: mlflow.data.dataset_source.DatasetSource
+    :members:
+    :undoc-members:
+    :show-inheritance:
+    :exclude-members: from_json
+
+    .. method:: from_json(cls, source_json: str) -> DatasetSource
+
+.. autofunction:: mlflow.data.get_source
+
+
+pandas
+~~~~~~
+
+.. autofunction:: mlflow.data.from_pandas
+
+.. autoclass:: mlflow.data.pandas_dataset.PandasDataset()
+    :members:
+    :undoc-members:
+    :exclude-members: to_pyfunc, to_evaluation_dataset
+
+
+NumPy
+~~~~~
+
+.. autofunction:: mlflow.data.from_numpy
+
+.. autoclass:: mlflow.data.numpy_dataset.NumpyDataset()
+    :members:
+    :undoc-members:
+    :exclude-members: to_pyfunc, to_evaluation_dataset
+
+
+Spark
+~~~~~
+
+.. autofunction:: mlflow.data.load_delta
+
+.. autofunction:: mlflow.data.from_spark
+
+.. autoclass:: mlflow.data.spark_dataset.SparkDataset()
+    :members:
+    :undoc-members:
+    :exclude-members: to_pyfunc, to_evaluation_dataset
+
+
+Hugging Face 
+~~~~~~~~~~~~
+
+.. autofunction:: mlflow.data.huggingface_dataset.from_huggingface
+
+.. autoclass:: mlflow.data.huggingface_dataset.HuggingFaceDataset()
+    :members:
+    :undoc-members:
+    :exclude-members: to_pyfunc
+
+
+TensorFlow 
+~~~~~~~~~~~~
+
+.. autofunction:: mlflow.data.tensorflow_dataset.from_tensorflow
+
+.. autoclass:: mlflow.data.tensorflow_dataset.TensorFlowDataset()
+    :members:
+    :undoc-members:
+    :exclude-members: to_pyfunc, 
+
+.. autoclass:: mlflow.data.evaluation_dataset.EvaluationDataset()
+    :members:
+    :undoc-members:
+
+
+polars
+~~~~~~
+
+.. autofunction:: mlflow.data.from_polars
+
+.. autoclass:: mlflow.data.polars_dataset.PolarsDataset()
+    :members:
+    :undoc-members:
+    :exclude-members: to_pyfunc, to_evaluation_dataset
+
+
+Dataset Sources 
+~~~~~~~~~~~~~~~~
+
+.. autoclass:: mlflow.data.filesystem_dataset_source.FileSystemDatasetSource()
+    :members:
+    :undoc-members:
+
+.. autoclass:: mlflow.data.http_dataset_source.HTTPDatasetSource()
+    :members:
+    :undoc-members:
+    
+.. autoclass:: mlflow.data.huggingface_dataset_source.HuggingFaceDatasetSource()
+    :members:
+    :undoc-members:
+    :exclude-members:
+
+.. autoclass:: mlflow.data.delta_dataset_source.DeltaDatasetSource()
+    :members:
+    :undoc-members:
+
+.. autoclass:: mlflow.data.spark_dataset_source.SparkDatasetSource()
+    :members:
+    :undoc-members:

docs/api_reference/source/python_api/mlflow.deployments.rst

@@ -0,0 +1,12 @@
+mlflow.deployments
+==================
+
+.. automodule:: mlflow.deployments
+    :members:
+    :undoc-members:
+    :exclude-members: PredictionsResponse
+
+.. autoclass:: mlflow.deployments.PredictionsResponse
+    :members:
+    :undoc-members:
+    :exclude-members: from_json

docs/api_reference/source/python_api/mlflow.dspy.rst

@@ -0,0 +1,7 @@
+mlflow.dspy
+==================
+
+.. automodule:: mlflow.dspy
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.entities.rst

@@ -0,0 +1,15 @@
+mlflow.entities
+===============
+
+.. automodule:: mlflow.entities
+    :members:
+    :undoc-members:
+
+.. automodule:: mlflow.entities.model_registry
+    :members:
+    :undoc-members:
+    :exclude-members: Prompt
+
+.. automodule:: mlflow.store.entities
+    :members:
+    :undoc-members:

docs/api_reference/source/python_api/mlflow.environment_variables.rst

@@ -0,0 +1,6 @@
+mlflow.environment_variables
+============================
+
+.. automodule:: mlflow.environment_variables
+    :members:
+    :undoc-members:

docs/api_reference/source/python_api/mlflow.gateway.rst

@@ -0,0 +1,14 @@
+mlflow.gateway
+==============
+
+.. automodule:: mlflow.gateway
+    :members:
+    :undoc-members:
+
+.. automodule:: mlflow.gateway.base_models
+    :members: ConfigModel
+
+.. automodule:: mlflow.gateway.config
+    :members:
+    :undoc-members:
+    :exclude-members: model_computed_fields

docs/api_reference/source/python_api/mlflow.gemini.rst

@@ -0,0 +1,7 @@
+mlflow.gemini
+==============
+
+.. automodule:: mlflow.gemini
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.genai.rst

@@ -0,0 +1,73 @@
+mlflow.genai
+============
+
+.. automodule:: mlflow.genai
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. automodule:: mlflow.genai.scorers
+    :members:
+    :undoc-members:
+    :show-inheritance:
+    :exclude-members: Scorer
+
+.. automodule:: mlflow.genai.scorers.deepeval
+    :members:
+    :undoc-members:
+    :show-inheritance:
+    :exclude-members: DeepEvalScorer
+
+.. automodule:: mlflow.genai.scorers.ragas
+    :members:
+    :undoc-members:
+    :show-inheritance:
+    :exclude-members: RagasScorer
+
+.. automodule:: mlflow.genai.scorers.phoenix
+    :members:
+    :undoc-members:
+    :show-inheritance:
+    :exclude-members: PhoenixScorer
+
+.. automodule:: mlflow.genai.scorers.trulens
+    :members:
+    :undoc-members:
+    :show-inheritance:
+    :exclude-members: TruLensScorer, TruLensAgentScorer
+
+.. automodule:: mlflow.genai.scorers.guardrails
+    :members:
+    :undoc-members:
+    :show-inheritance:
+    :exclude-members: GuardrailsScorer
+
+.. automodule:: mlflow.genai.datasets
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. automodule:: mlflow.genai.label_schemas
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. automodule:: mlflow.genai.review_queues
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. automodule:: mlflow.genai.optimize
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. automodule:: mlflow.genai.judges
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. automodule:: mlflow.genai.agent_server
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.groq.rst

@@ -0,0 +1,7 @@
+mlflow.groq
+================
+
+.. automodule:: mlflow.groq
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.h2o.rst

@@ -0,0 +1,7 @@
+mlflow.h2o
+==========
+
+.. automodule:: mlflow.h2o
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.haystack.rst

@@ -0,0 +1,7 @@
+mlflow.haystack
+==================
+
+.. automodule:: mlflow.haystack
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.johnsnowlabs.rst

@@ -0,0 +1,7 @@
+mlflow.johnsnowlabs
+===================
+
+.. automodule:: mlflow.johnsnowlabs
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.keras.rst

@@ -0,0 +1,22 @@
+mlflow.keras
+==================
+
+.. automodule:: mlflow.keras.autolog
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. automodule:: mlflow.keras.callback
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. automodule:: mlflow.keras.load
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. automodule:: mlflow.keras.save
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.langchain.rst

@@ -0,0 +1,13 @@
+mlflow.langchain
+==================
+
+.. automodule:: mlflow.langchain
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. autoclass:: mlflow.langchain.chat_agent_langgraph.ChatAgentState
+
+.. autoclass:: mlflow.langchain.chat_agent_langgraph.ChatAgentToolNode
+
+.. autoclass:: mlflow.langchain.output_parsers.ChatAgentOutputParser

docs/api_reference/source/python_api/mlflow.lightgbm.rst

@@ -0,0 +1,7 @@
+mlflow.lightgbm
+===============
+
+.. automodule:: mlflow.lightgbm
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.litellm.rst

@@ -0,0 +1,7 @@
+mlflow.litellm
+==============
+
+.. automodule:: mlflow.litellm
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.llama_index.rst

@@ -0,0 +1,7 @@
+mlflow.llama_index
+==================
+
+.. automodule:: mlflow.llama_index
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.metrics.rst

@@ -0,0 +1,224 @@
+mlflow.metrics
+==============
+
+The ``mlflow.metrics`` module helps you quantitatively and qualitatively measure your models. 
+
+.. autoclass:: mlflow.metrics.EvaluationMetric
+
+These :py:class:`EvaluationMetric <mlflow.metrics.EvaluationMetric>` are used by the :py:func:`mlflow.evaluate()` API, either computed automatically depending on the ``model_type`` or specified via the ``extra_metrics`` parameter.
+
+The following code demonstrates how to use :py:func:`mlflow.evaluate()` with an  :py:class:`EvaluationMetric <mlflow.metrics.EvaluationMetric>`.
+
+.. code-block:: python
+
+    import mlflow
+    from mlflow.metrics.genai import EvaluationExample, answer_similarity
+
+    eval_df = pd.DataFrame(
+        {
+            "inputs": [
+                "What is MLflow?",
+            ],
+            "ground_truth": [
+                "MLflow is the largest open source AI engineering platform for agents, LLM applications, and ML models. It was developed by Databricks, a company that specializes in data and AI solutions. MLflow is designed to address the challenges that data scientists and AI engineers face when developing, evaluating, and deploying AI applications.",
+            ],
+        }
+    )
+
+    example = EvaluationExample(
+        input="What is MLflow?",
+        output="MLflow is the largest open source AI engineering platform "
+        "for agents, LLM applications, and ML models, including tracing, "
+        "evaluation, prompt management, experiment tracking, and deployment.",
+        score=4,
+        justification="The definition effectively explains what MLflow is "
+        "its purpose, and its developer. It could be more concise for a 5-score.",
+        grading_context={
+            "ground_truth": "MLflow is the largest open source AI engineering "
+            "platform for agents, LLM applications, and ML models. It was "
+            "developed by Databricks, a company that specializes in data and "
+            "AI solutions. MLflow is designed to address the challenges that "
+            "data scientists and AI engineers face when developing, evaluating, "
+            "and deploying AI applications."
+        },
+    )
+    answer_similarity_metric = answer_similarity(examples=[example])
+    results = mlflow.evaluate(
+        logged_model.model_uri,
+        eval_df,
+        targets="ground_truth",
+        model_type="question-answering",
+        extra_metrics=[answer_similarity_metric],
+    )
+
+Information about how an :py:class:`EvaluationMetric <mlflow.metrics.EvaluationMetric>` is calculated, such as the grading prompt used is available via the ``metric_details`` property.
+
+.. code-block:: python
+
+    import mlflow
+    from mlflow.metrics.genai import relevance
+
+    my_relevance_metric = relevance()
+    print(my_relevance_metric.metric_details)
+
+Evaluation results are stored as :py:class:`MetricValue <mlflow.metrics.MetricValue>`. Aggregate results are logged to the MLflow run as metrics, while per-example results are logged to the MLflow run as artifacts in the form of an evaluation table.
+
+.. autoclass:: mlflow.metrics.MetricValue
+
+We provide the following builtin factory functions to create :py:class:`EvaluationMetric <mlflow.metrics.EvaluationMetric>` for evaluating models. These metrics are computed automatically depending on the ``model_type``. For more information on the ``model_type`` parameter, see :py:func:`mlflow.evaluate()` API.
+
+Regressor Metrics
+-----------------
+
+.. autofunction:: mlflow.metrics.mae
+
+.. autofunction:: mlflow.metrics.mape
+
+.. autofunction:: mlflow.metrics.max_error
+
+.. autofunction:: mlflow.metrics.mse
+
+.. autofunction:: mlflow.metrics.rmse
+
+.. autofunction:: mlflow.metrics.r2_score
+
+Classifier Metrics
+------------------
+
+.. autofunction:: mlflow.metrics.precision_score
+
+.. autofunction:: mlflow.metrics.recall_score
+
+.. autofunction:: mlflow.metrics.f1_score
+
+Text Metrics
+------------
+
+.. autofunction:: mlflow.metrics.ari_grade_level
+
+.. autofunction:: mlflow.metrics.flesch_kincaid_grade_level
+
+Question Answering Metrics
+---------------------------
+
+Includes all of the above **Text Metrics** as well as the following:
+
+.. autofunction:: mlflow.metrics.exact_match
+
+.. autofunction:: mlflow.metrics.rouge1
+
+.. autofunction:: mlflow.metrics.rouge2
+
+.. autofunction:: mlflow.metrics.rougeL
+
+.. autofunction:: mlflow.metrics.rougeLsum
+
+.. autofunction:: mlflow.metrics.toxicity
+
+.. autofunction:: mlflow.metrics.token_count
+
+.. autofunction:: mlflow.metrics.latency
+
+.. autofunction:: mlflow.metrics.bleu
+
+Retriever Metrics
+-----------------
+
+The following metrics are built-in metrics for the ``'retriever'`` model type, meaning they will be 
+automatically calculated with a default ``retriever_k`` value of 3. 
+
+To evaluate document retrieval models, it is recommended to use a dataset with the following 
+columns:
+
+- Input queries
+- Retrieved relevant doc IDs
+- Ground-truth doc IDs
+
+Alternatively, you can also provide a function through the ``model`` parameter to represent 
+your retrieval model. The function should take a Pandas DataFrame containing input queries and 
+ground-truth relevant doc IDs, and return a DataFrame with a column of retrieved relevant doc IDs.
+
+A "doc ID" is a string or integer that uniquely identifies a document. Each row of the retrieved and
+ground-truth doc ID columns should consist of a list or numpy array of doc IDs.
+
+Parameters:
+
+- ``targets``: A string specifying the column name of the ground-truth relevant doc IDs
+- ``predictions``: A string specifying the column name of the retrieved relevant doc IDs in either 
+  the static dataset or the Dataframe returned by the ``model`` function
+- ``retriever_k``: A positive integer specifying the number of retrieved docs IDs to consider for 
+  each input query. ``retriever_k`` defaults to 3. You can change ``retriever_k`` by using the 
+  :py:func:`mlflow.evaluate` API:
+
+    1. .. code-block:: python
+
+        # with a model and using `evaluator_config`
+        mlflow.evaluate(
+            model=retriever_function,
+            data=data,
+            targets="ground_truth",
+            model_type="retriever",
+            evaluators="default",
+            evaluator_config={"retriever_k": 5}
+        )
+    2. .. code-block:: python
+
+        # with a static dataset and using `extra_metrics`
+        mlflow.evaluate(
+            data=data,
+            predictions="predictions_param",
+            targets="targets_param",
+            model_type="retriever",
+            extra_metrics = [
+                mlflow.metrics.precision_at_k(5),
+                mlflow.metrics.precision_at_k(6),
+                mlflow.metrics.recall_at_k(5),
+                mlflow.metrics.ndcg_at_k(5)
+            ]   
+        )
+    
+    NOTE: In the 2nd method, it is recommended to omit the ``model_type`` as well, or else 
+    ``precision@3`` and ``recall@3`` will be  calculated in  addition to ``precision@5``, 
+    ``precision@6``, ``recall@5``, and ``ndcg_at_k@5``.
+
+.. autofunction:: mlflow.metrics.precision_at_k
+
+.. autofunction:: mlflow.metrics.recall_at_k
+
+.. autofunction:: mlflow.metrics.ndcg_at_k
+
+Users create their own :py:class:`EvaluationMetric <mlflow.metrics.EvaluationMetric>` using the :py:func:`make_metric <mlflow.metrics.make_metric>` factory function
+
+.. autofunction:: mlflow.metrics.make_metric
+
+.. automodule:: mlflow.metrics
+    :members:
+    :undoc-members:
+    :show-inheritance:
+    :exclude-members: MetricValue, EvaluationMetric, make_metric, EvaluationExample, ari_grade_level, flesch_kincaid_grade_level, exact_match, rouge1, rouge2, rougeL, rougeLsum, toxicity, answer_similarity, answer_correctness, faithfulness, answer_relevance, mae, mape, max_error, mse, rmse, r2_score, precision_score, recall_score, f1_score, token_count, latency, precision_at_k, recall_at_k, ndcg_at_k, bleu
+
+Generative AI Metrics
+---------------------
+
+We also provide generative AI ("genai") :py:class:`EvaluationMetric <mlflow.metrics.EvaluationMetric>`\s for evaluating text models. These metrics use an LLM to evaluate the quality of a model's output text. Note that your use of a third party LLM service (e.g., OpenAI) for evaluation may be subject to and governed by the LLM service's terms of use. The following factory functions help you customize the intelligent metric to your use case.
+
+.. automodule:: mlflow.metrics.genai
+    :members:
+    :undoc-members:
+    :show-inheritance:
+    :exclude-members: EvaluationExample, make_genai_metric
+
+You can also create your own generative AI :py:class:`EvaluationMetric <mlflow.metrics.EvaluationMetric>`\s using the :py:func:`make_genai_metric <mlflow.metrics.genai.make_genai_metric>` factory function.
+
+.. autofunction:: mlflow.metrics.genai.make_genai_metric
+
+When using generative AI :py:class:`EvaluationMetric <mlflow.metrics.EvaluationMetric>`\s, it is important to pass in an :py:class:`EvaluationExample <mlflow.metrics.genai.EvaluationExample>`
+
+.. autoclass:: mlflow.metrics.genai.EvaluationExample
+
+Users must set the appropriate environment variables for the LLM service they are using for 
+evaluation. For example, if you are using OpenAI's API, you must set the ``OPENAI_API_KEY`` 
+environment variable. If using Azure OpenAI, you must also set the ``OPENAI_API_TYPE``, 
+``OPENAI_API_VERSION``, ``OPENAI_API_BASE``, and ``OPENAI_DEPLOYMENT_NAME`` environment variables. 
+See `Azure OpenAI documentation <https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/switching-endpoints>`_
+Users do not need to set these environment variables if they are using a gateway route.

docs/api_reference/source/python_api/mlflow.mistral.rst

@@ -0,0 +1,7 @@
+mlflow.mistral
+==============
+
+.. automodule:: mlflow.mistral
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.models.rst

@@ -0,0 +1,11 @@
+mlflow.models
+==============
+
+.. automodule:: mlflow.models
+    :members:
+    :undoc-members:
+    :show-inheritance:
+    :exclude-members: EvaluationMetric
+
+.. autoclass:: mlflow.models.model.ModelInfo
+    :members:

docs/api_reference/source/python_api/mlflow.onnx.rst

@@ -0,0 +1,7 @@
+mlflow.onnx
+==================
+
+.. automodule:: mlflow.onnx
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.openai.rst

@@ -0,0 +1,7 @@
+mlflow.openai
+=============
+
+.. automodule:: mlflow.openai
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.paddle.rst

@@ -0,0 +1,7 @@
+mlflow.paddle
+==================
+
+.. automodule:: mlflow.paddle
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.pmdarima.rst

@@ -0,0 +1,7 @@
+mlflow.pmdarima
+===============
+
+.. automodule:: mlflow.pmdarima
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.projects.rst

@@ -0,0 +1,7 @@
+mlflow.projects
+===============
+
+.. automodule:: mlflow.projects
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.prophet.rst

@@ -0,0 +1,7 @@
+mlflow.prophet
+==================
+
+.. automodule:: mlflow.prophet
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.pydantic_ai.rst

@@ -0,0 +1,7 @@
+mlflow.pydantic_ai
+==================
+
+.. automodule:: mlflow.pydantic_ai
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.pyfunc.rst

@@ -0,0 +1,43 @@
+mlflow.pyfunc
+=============
+
+.. automodule:: mlflow.pyfunc
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. Include ``get_default_pip_requirements`` and ``get_default_conda_env``,
+   which are imported from `mlflow.pyfunc.model`, in the `mlflow.pyfunc` namespace
+.. autofunction:: mlflow.pyfunc.get_default_pip_requirements
+.. autofunction:: mlflow.pyfunc.get_default_conda_env
+
+.. Include ``PythonModelContext`` as a renamed class to avoid documenting constructor parameters.
+   This class is meant to be constructed implicitly, and users should only be aware of its
+   documented member properties.
+.. autoclass:: mlflow.pyfunc.PythonModelContext()
+    :members:
+    :undoc-members:
+
+.. Include ``PythonModel``, which is imported from `mlflow.pyfunc.model`, in the
+   `mlflow.pyfunc` namespace
+.. autoclass:: mlflow.pyfunc.PythonModel
+    :members:
+    :undoc-members:
+
+.. Include ``ChatModel``, which is imported from `mlflow.pyfunc.model`, in the
+   `mlflow.pyfunc` namespace
+.. autoclass:: mlflow.pyfunc.ChatModel
+    :members:
+    :undoc-members:
+
+.. Include ``ChatAgent``, which is imported from `mlflow.pyfunc.model`, in the
+   `mlflow.pyfunc` namespace
+.. autoclass:: mlflow.pyfunc.ChatAgent
+    :members:
+    :undoc-members:
+
+.. Include ``ResponsesAgent``, which is imported from `mlflow.pyfunc.model`, in the
+   `mlflow.pyfunc` namespace
+.. autoclass:: mlflow.pyfunc.ResponsesAgent
+    :members:
+    :undoc-members:

docs/api_reference/source/python_api/mlflow.pyspark.ml.rst

@@ -0,0 +1,7 @@
+mlflow.pyspark.ml
+=================
+
+.. automodule:: mlflow.pyspark.ml
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.pytorch.rst

@@ -0,0 +1,7 @@
+mlflow.pytorch
+==================
+
+.. automodule:: mlflow.pytorch
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.rst

@@ -0,0 +1,83 @@
+mlflow
+======
+
+.. automodule:: mlflow
+    :members:
+    :undoc-members:
+    :exclude-members:
+        MlflowClient,
+        add_trace,
+        trace,
+        start_span,
+        start_span_no_context,
+        get_trace,
+        search_traces,
+        log_assessment,
+        log_expectation,
+        log_feedback,
+        update_assessment,
+        delete_assessment,
+        get_current_active_span,
+        get_last_active_trace_id,
+        create_external_model,
+        delete_logged_model_tag,
+        finalize_logged_model,
+        get_logged_model,
+        initialize_logged_model,
+        last_logged_model,
+        search_logged_models,
+        set_active_model,
+        set_logged_model_tags,
+        log_model_params,
+        clear_active_model,
+        load_prompt,
+        register_prompt,
+        search_prompts,
+        set_prompt_alias,
+        delete_prompt_alias,
+
+.. _mlflow-tracing-fluent-python-apis:
+
+MLflow Tracing APIs
+===================
+
+The ``mlflow`` module provides a set of high-level APIs for `MLflow Tracing <../llms/tracing/index.html>`_. For the detailed
+guidance on how to use these tracing APIs, please refer to the `Tracing Fluent APIs Guide <../llms/tracing/index.html#tracing-fluent-apis>`_.
+
+.. autofunction:: mlflow.trace
+.. autofunction:: mlflow.start_span
+.. autofunction:: mlflow.start_span_no_context
+.. autofunction:: mlflow.get_trace
+.. autofunction:: mlflow.search_traces
+.. autofunction:: mlflow.get_current_active_span
+.. autofunction:: mlflow.get_last_active_trace_id
+.. autofunction:: mlflow.add_trace
+.. autofunction:: mlflow.log_assessment
+.. autofunction:: mlflow.log_expectation
+.. autofunction:: mlflow.log_feedback
+.. autofunction:: mlflow.update_assessment
+.. autofunction:: mlflow.delete_assessment
+
+.. automodule:: mlflow.tracing
+    :members:
+    :undoc-members:
+    :noindex:
+
+.. _mlflow-logged-model-fluent-python-apis:
+
+MLflow Logged Model APIs
+========================
+
+The ``mlflow`` module provides a set of high-level APIs to interact with ``MLflow Logged Models``.
+
+.. autofunction:: mlflow.clear_active_model
+.. autofunction:: mlflow.create_external_model
+.. autofunction:: mlflow.delete_logged_model_tag
+.. autofunction:: mlflow.finalize_logged_model
+.. autofunction:: mlflow.get_logged_model
+.. autofunction:: mlflow.initialize_logged_model
+.. autofunction:: mlflow.last_logged_model
+.. autofunction:: mlflow.search_logged_models
+.. autofunction:: mlflow.set_active_model
+.. autofunction:: mlflow.set_logged_model_tags
+.. autofunction:: mlflow.log_model_params

docs/api_reference/source/python_api/mlflow.sagemaker.rst

@@ -0,0 +1,7 @@
+mlflow.sagemaker
+================
+
+.. automodule:: mlflow.sagemaker
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.sentence_transformers.rst

@@ -0,0 +1,7 @@
+mlflow.sentence_transformers
+============================
+
+.. automodule:: mlflow.sentence_transformers
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.server.rst

@@ -0,0 +1,7 @@
+mlflow.server
+=============
+
+.. automodule:: mlflow.server
+    :members: get_app_client
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.shap.rst

@@ -0,0 +1,8 @@
+mlflow.shap
+===========
+
+.. automodule:: mlflow.shap
+    :members:
+    :undoc-members:
+    :show-inheritance:
+    :exclude-members: save_model

docs/api_reference/source/python_api/mlflow.sklearn.rst

@@ -0,0 +1,7 @@
+mlflow.sklearn
+==============
+
+.. automodule:: mlflow.sklearn
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.smolagents.rst

@@ -0,0 +1,7 @@
+mlflow.smolagents
+==================
+
+.. automodule:: mlflow.smolagents
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.spacy.rst

@@ -0,0 +1,7 @@
+mlflow.spacy
+============
+
+.. automodule:: mlflow.spacy
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.spark.rst

@@ -0,0 +1,7 @@
+mlflow.spark
+===============
+
+.. automodule:: mlflow.spark
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.statsmodels.rst

@@ -0,0 +1,7 @@
+mlflow.statsmodels
+==================
+
+.. automodule:: mlflow.statsmodels
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.strands.rst

@@ -0,0 +1,7 @@
+mlflow.strands
+==================
+
+.. automodule:: mlflow.strands
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.system_metrics.rst

@@ -0,0 +1,7 @@
+mlflow.system_metrics
+======================
+
+.. automodule:: mlflow.system_metrics
+    :members:
+    :undoc-members:
+    

docs/api_reference/source/python_api/mlflow.tensorflow.rst

@@ -0,0 +1,11 @@
+mlflow.tensorflow
+==================
+
+.. automodule:: mlflow.tensorflow
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. autoclass:: mlflow.tensorflow.MlflowCallback
+    :members:
+    :undoc-members:

docs/api_reference/source/python_api/mlflow.tracing.rst

@@ -0,0 +1,21 @@
+mlflow.tracing
+==============
+
+.. attention::
+
+    The ``mlflow.tracing`` namespace only contains a few utility functions fo managing traces. The main entry point for MLflow
+    Tracing is :ref:`Tracing Fluent APIs <mlflow-tracing-fluent-python-apis>` defined directly under the
+    :py:mod:`mlflow` namespace, or the low-level `Tracing Client APIs <../llms/tracing/index.html#tracing-client-apis>`_
+
+.. automodule:: mlflow.tracing
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+mlflow.tracing.attachments
+--------------------------
+
+.. automodule:: mlflow.tracing.attachments
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.transformers.rst

@@ -0,0 +1,7 @@
+mlflow.transformers
+===================
+
+.. automodule:: mlflow.transformers
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.types.rst

@@ -0,0 +1,28 @@
+mlflow.types
+==============
+
+.. automodule:: mlflow.types
+    :members:
+    :show-inheritance:
+
+.. automodule:: mlflow.types.responses
+    :members:
+
+.. automodule:: mlflow.types.responses_helpers
+    :members:
+
+.. automodule:: mlflow.types.agent
+    :members:
+
+.. automodule:: mlflow.types.llm
+    :members:
+
+.. automodule:: mlflow.types.chat
+    :members:
+
+.. automodule:: mlflow.types.schema
+    :members: Array, Map, Object, Property, AnyType
+    :undoc-members:
+
+.. automodule:: mlflow.types.llm._BaseDataclass
+    :undoc-members:

docs/api_reference/source/python_api/mlflow.utils.rst

@@ -0,0 +1,10 @@
+mlflow.utils
+==================
+
+.. automodule:: mlflow.utils.async_logging
+    :members:
+    :undoc-members:
+
+.. automodule:: mlflow.utils.async_logging.run_operations
+    :members:
+    :undoc-members:

docs/api_reference/source/python_api/mlflow.webhooks.rst

@@ -0,0 +1,7 @@
+mlflow.webhooks
+===============
+
+.. automodule:: mlflow.webhooks
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/mlflow.xgboost.rst

@@ -0,0 +1,7 @@
+mlflow.xgboost
+==============
+
+.. automodule:: mlflow.xgboost
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api_reference/source/python_api/openai/messages.rst

@@ -0,0 +1,256 @@
+:orphan:
+
+.. _mlflow.openai.messages:
+
+Supported ``messages`` formats for OpenAI chat completion task
+==============================================================
+
+This document covers the following:
+
+- Supported ``messages`` formats for OpenAI chat completion task in the ``openai`` flavor.
+- Logged model signature for each format.
+- Payload sent to OpenAI chat completion API for each format.
+- Expected prediction input types for each format.
+
+
+``messages`` with variables
+---------------------------
+
+The ``messages`` argument accepts a list of dictionaries with ``role`` and ``content`` keys. The
+``content`` field in each message can contain variables (= named format fields). When the logged
+model is loaded and makes a prediction, the variables are replaced with the values from the
+prediction input.
+
+Single variable
+~~~~~~~~~~~~~~~
+
+.. code-block:: python
+
+    import mlflow
+    import openai
+
+    with mlflow.start_run():
+        model_info = mlflow.openai.log_model(
+            name="model",
+            model="gpt-4o-mini",
+            task=openai.chat.completions,
+            messages=[
+                {
+                    "role": "user",
+                    "content": "Tell me a {adjective} joke",
+                    #                     ^^^^^^^^^^
+                    #                     variable
+                },
+                # Can contain more messages
+            ],
+        )
+
+    model = mlflow.pyfunc.load_model(model_info.model_uri)
+    print(model.predict([{"adjective": "funny"}]))
+
+Logged model signature:
+
+.. code-block:: python
+
+    {
+        "inputs": [{"type": "string"}],
+        "outputs": [{"type": "string"}],
+    }
+
+Expected prediction input types:
+
+.. code-block:: python
+
+    # A list of dictionaries with 'adjective' key
+    [{"adjective": "funny"}, ...]
+
+    # A list of strings
+    ["funny", ...]
+
+
+Payload sent to OpenAI chat completion API:
+
+.. code-block:: python
+
+    {
+        "model": "gpt-4o-mini",
+        "messages": [
+            {
+                "role": "user",
+                "content": "Tell me a funny joke",
+            }
+        ],
+    }
+
+
+Multiple variables
+~~~~~~~~~~~~~~~~~~
+
+.. code-block:: python
+
+    import mlflow
+    import openai
+
+    with mlflow.start_run():
+        model_info = mlflow.openai.log_model(
+            name="model",
+            model="gpt-4o-mini",
+            task=openai.chat.completions,
+            messages=[
+                {
+                    "role": "user",
+                    "content": "Tell me a {adjective} joke about {thing}.",
+                    #                     ^^^^^^^^^^             ^^^^^^^
+                    #                     variable               another variable
+                },
+                # Can contain more messages
+            ],
+        )
+
+    model = mlflow.pyfunc.load_model(model_info.model_uri)
+    print(model.predict([{"adjective": "funny", "thing": "vim"}]))
+
+Logged model signature:
+
+.. code-block:: python
+
+    {
+        "inputs": [
+            {"name": "adjective", "type": "string"},
+            {"name": "thing", "type": "string"},
+        ],
+        "outputs": [{"type": "string"}],
+    }
+
+Expected prediction input types:
+
+.. code-block:: python
+
+    # A list of dictionaries with 'adjective' and 'thing' keys
+    [{"adjective": "funny", "thing": "vim"}, ...]
+
+Payload sent to OpenAI chat completion API:
+
+.. code-block:: python
+
+    {
+        "model": "gpt-4o-mini",
+        "messages": [
+            {
+                "role": "user",
+                "content": "Tell me a funny joke about vim",
+            }
+        ],
+    }
+
+
+``messages`` without variables
+------------------------------
+
+If no variables are provided, the prediction input will be _appended_ to the logged ``messages``
+with ``role = user``.
+
+.. code-block:: python
+
+    with mlflow.start_run():
+        model_info = mlflow.openai.log_model(
+            name="model",
+            model="gpt-4o-mini",
+            task=openai.chat.completions,
+            messages=[
+                {
+                    "role": "system",
+                    "content": "You're a frontend engineer.",
+                }
+            ],
+        )
+
+    model = mlflow.pyfunc.load_model(model_info.model_uri)
+    print(model.predict(["Tell me a funny joke."]))
+
+Logged model signature:
+
+.. code-block:: python
+
+    {
+        "inputs": [{"type": "string"}],
+        "outputs": [{"type": "string"}],
+    }
+
+Expected prediction input type:
+
+- A list of dictionaries with a single key
+- A list of strings
+
+Payload sent to OpenAI chat completion API:
+
+.. code-block:: python
+
+    {
+        "model": "gpt-4o-mini",
+        "messages": [
+            {
+                "role": "system",
+                "content": "You're a frontend engineer.",
+            },
+            {
+                "role": "user",
+                "content": "Tell me a funny joke.",
+            },
+        ],
+    }
+
+
+No ``messages``
+---------------
+
+The ``messages`` argument is optional and can be omitted. If omitted, the prediction input will be
+sent to the OpenAI chat completion API as-is with ``role = user``.
+
+.. code-block:: python
+
+    import mlflow
+    import openai
+
+    with mlflow.start_run():
+        model_info = mlflow.openai.log_model(
+            name="model",
+            model="gpt-4o-mini",
+            task=openai.chat.completions,
+        )
+
+    model = mlflow.pyfunc.load_model(model_info.model_uri)
+    print(model.predict(["Tell me a funny joke."]))
+
+Logged model signature:
+
+.. code-block:: python
+
+    {
+        "inputs": [{"type": "string"}],
+        "outputs": [{"type": "string"}],
+    }
+
+Expected prediction input types:
+
+.. code-block:: python
+
+    # A list of dictionaries with a single key
+    [{"<any key>": "Tell me a funny joke."}, ...]
+
+    # A list of strings
+    ["Tell me a funny joke.", ...]
+
+Payload sent to OpenAI chat completion API:
+
+.. code-block:: python
+
+    {
+        "model": "gpt-4o-mini",
+        "messages": [
+            {
+                "role": "user",
+                "content": "Tell me a funny joke.",
+            }
+        ],
+    }