The mlflow.openai module provides an API for logging and loading OpenAI models.
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.
Enables (or disables) and configures autologging from OpenAI to MLflow. Raises MlflowException if the OpenAI version < 1.0.
disable â If True, disables the OpenAI autologging integration. If False, enables the OpenAI autologging integration.
exclusive â 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 â If True, disable autologging for versions of OpenAI that have not been tested against this version of the MLflow client or are incompatible.
silent â If True, suppress all event logs and warnings from MLflow during OpenAI autologging. If False, show all events and warnings during OpenAI autologging.
log_traces â If True, traces are logged for OpenAI models. If False, no traces are collected during inference. Default to True.
Load an OpenAI model from a local file or a run.
model_uri â
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 â 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.
A dictionary representing the OpenAI model.
Log an OpenAI model as an MLflow artifact for the current run.
model â The OpenAI model name or reference instance, e.g., openai.Model.retrieve("gpt-4o-mini").
task â The task the model is performing, e.g., openai.chat.completions or 'chat.completions'.
artifact_path â Deprecated. Use name instead.
conda_env â
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 â
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 â 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 â
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 â 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 â 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 â 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 modelâs conda environment (conda.yaml) file.
extra_pip_requirements â
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 userâs 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 modelâs conda environment (conda.yaml) file.
Warning
The following arguments canât 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 â Custom metadata dictionary passed to the model and stored in the MLmodel file.
prompts â
A list of prompt URIs registered in the MLflow Prompt Registry, to be associated with the model. Each prompt URI should be in the form prompt:/<name>/<version>. The prompts should be registered in the MLflow Prompt Registry before being associated with the model.
This will create a mutual link between the model and the prompt. The associated prompts can be seen in the modelâs metadata stored in the MLmodel file. From the Prompt Registry UI, you can navigate to the model as well.
import mlflow
prompt_template = "Hi, {name}! How are you doing today?"
# Register a prompt in the MLflow Prompt Registry
mlflow.prompts.register_prompt("my_prompt", prompt_template, description="A simple prompt")
# Log a model with the registered prompt
with mlflow.start_run():
model_info = mlflow.pyfunc.log_model(
name=MyModel(),
name="model",
prompts=["prompt:/my_prompt/1"]
)
print(model_info.prompts)
# Output: ['prompt:/my_prompt/1']
# Load the prompt
prompt = mlflow.genai.load_prompt(model_info.prompts[0])
name â Model name.
params â A dictionary of parameters to log with the model.
tags â A dictionary of tags to log with the model.
model_type â The type of the model.
step â The step at which to log the model outputs and metrics
model_id â The ID of the model.
kwargs â 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.
A ModelInfo instance that contains the metadata of the logged model.
import mlflow
import openai
import pandas as pd
# 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}."}],
name="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,
name="embeddings",
)
model = mlflow.pyfunc.load_model(info.model_uri)
print(model.predict(["hello", "world"]))
Save an OpenAI model to a path on the local file system.
model â The OpenAI model name.
task â The task the model is performing, e.g., openai.chat.completions or 'chat.completions'.
path â Local path where the model is to be saved.
conda_env â
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 â
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 â mlflow.models.Model this flavor is being added to.
signature â
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 â 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 â 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 modelâs conda environment (conda.yaml) file.
extra_pip_requirements â
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 userâs 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 modelâs conda environment (conda.yaml) file.
Warning
The following arguments canât 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 â Custom metadata dictionary passed to the model and stored in the MLmodel file.
kwargs â 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",
)
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4