Summary of entries of Classes for aiplatform.
Classes
CustomMetric
The custom evaluation metric.
A fully-customized CustomMetric that can be used to evaluate a single model by defining a metric function for a computation-based metric. The CustomMetric is computed on the client-side using the user-defined metric function in SDK only, not by the Vertex Gen AI Evaluation Service.
Attributes: name: The name of the metric. metric_function: The user-defined evaluation function to compute a metric score. Must use the dataset row dictionary as the metric function input and return per-instance metric result as a dictionary output. The metric score must mapped to the name of the CustomMetric as key.
EvalResult
Evaluation result.
EvalTask
A class representing an EvalTask.
An Evaluation Tasks is defined to measure the model's ability to perform a certain task in response to specific prompts or inputs. Evaluation tasks must contain an evaluation dataset, and a list of metrics to evaluate. Evaluation tasks help developers compare propmpt templates, track experiments, compare models and their settings, and assess the quality of the model's generated text.
Dataset Details:
Default dataset column names:
* prompt_column_name: "prompt"
* reference_column_name: "reference"
* response_column_name: "response"
* baseline_model_response_column_name: "baseline_model_response"
Requirement for different use cases:
* Bring-your-own-response (BYOR): You already have the data that you
want to evaluate stored in the dataset. Response column name can be
customized by providing `response_column_name` parameter, or in the
`metric_column_mapping`. For BYOR pairwise evaluation, the baseline
model response column name can be customized by providing
`baseline_model_response_column_name` parameter, or
in the `metric_column_mapping`. If the `response` column or
`baseline_model_response` column is present while the
corresponding model is specified, an error will be raised.
* Perform model inference without a prompt template: You have a dataset
containing the input prompts to the model and want to perform model
inference before evaluation. A column named `prompt` is required
in the evaluation dataset and is used directly as input to the model.
* Perform model inference with a prompt template: You have a dataset
containing the input variables to the prompt template and want to
assemble the prompts for model inference. Evaluation dataset
must contain column names corresponding to the variable names in
the prompt template. For example, if prompt template is
"Instruction: {instruction}, context: {context}", the dataset must
contain `instruction` and `context` columns.
Metrics Details:
The supported metrics descriptions, rating rubrics, and the required
input variables can be found on the Vertex AI public documentation page.
[Evaluation methods and metrics](https://cloud.google.com/vertex-ai/generative-ai/docs/models/determine-eval).
Usage Examples:
1. To perform bring-your-own-response(BYOR) evaluation, provide the model
responses in the `response` column in the dataset. If a pairwise metric is
used for BYOR evaluation, provide the baseline model responses in the
`baseline_model_response` column.
```
eval_dataset = pd.DataFrame({
"prompt" : [...],
"reference": [...],
"response" : [...],
"baseline_model_response": [...],
})
eval_task = EvalTask(
dataset=eval_dataset,
metrics=[
"bleu",
"rouge_l_sum",
MetricPromptTemplateExamples.Pointwise.FLUENCY,
MetricPromptTemplateExamples.Pairwise.SAFETY
],
experiment="my-experiment",
)
eval_result = eval_task.evaluate(experiment_run_name="eval-experiment-run")
```
2. To perform evaluation with Gemini model inference, specify the `model`
parameter with a `GenerativeModel` instance. The input column name to the
model is `prompt` and must be present in the dataset.
```
eval_dataset = pd.DataFrame({
"reference": [...],
"prompt" : [...],
})
result = EvalTask(
dataset=eval_dataset,
metrics=["exact_match", "bleu", "rouge_1", "rouge_l_sum"],
experiment="my-experiment",
).evaluate(
model=GenerativeModel("gemini-1.5-pro"),
experiment_run_name="gemini-eval-run"
)
```
3. If a `prompt_template` is specified, the `prompt` column is not required.
Prompts can be assembled from the evaluation dataset, and all prompt
template variable names must be present in the dataset columns.
```
eval_dataset = pd.DataFrame({
"context" : [...],
"instruction": [...],
})
result = EvalTask(
dataset=eval_dataset,
metrics=[MetricPromptTemplateExamples.Pointwise.SUMMARIZATION_QUALITY],
).evaluate(
model=GenerativeModel("gemini-1.5-pro"),
prompt_template="{instruction}. Article: {context}. Summary:",
)
```
4. To perform evaluation with custom model inference, specify the `model`
parameter with a custom inference function. The input column name to the
custom inference function is `prompt` and must be present in the dataset.
```
from openai import OpenAI
client = OpenAI()
def custom_model_fn(input: str) -> str:
response = client.chat.completions.create(
model="gpt-3.5-turbo",
messages=[
{"role": "user", "content": input}
]
)
return response.choices[0].message.content
eval_dataset = pd.DataFrame({
"prompt" : [...],
"reference": [...],
})
result = EvalTask(
dataset=eval_dataset,
metrics=[MetricPromptTemplateExamples.Pointwise.SAFETY],
experiment="my-experiment",
).evaluate(
model=custom_model_fn,
experiment_run_name="gpt-eval-run"
)
```
5. To perform pairwise metric evaluation with model inference step, specify
the `baseline_model` input to a `PairwiseMetric` instance and the candidate
`model` input to the `EvalTask.evaluate()` function. The input column name
to both models is `prompt` and must be present in the dataset.
```
baseline_model = GenerativeModel("gemini-1.0-pro")
candidate_model = GenerativeModel("gemini-1.5-pro")
pairwise_groundedness = PairwiseMetric(
metric_prompt_template=MetricPromptTemplateExamples.get_prompt_template(
"pairwise_groundedness"
),
baseline_model=baseline_model,
)
eval_dataset = pd.DataFrame({
"prompt" : [...],
})
result = EvalTask(
dataset=eval_dataset,
metrics=[pairwise_groundedness],
experiment="my-pairwise-experiment",
).evaluate(
model=candidate_model,
experiment_run_name="gemini-pairwise-eval-run",
)
```
MetricPromptTemplateExamples
Examples of metric prompt templates for model-based evaluation.
Pairwise
Example PairwiseMetric instances.
Pointwise
Example PointwiseMetric instances.
PairwiseMetric
A Model-based Pairwise Metric.
A model-based evaluation metric that compares two generative models' responses side-by-side, and allows users to A/B test their generative models to determine which model is performing better.
For more details on when to use pairwise metrics, see Evaluation methods and metrics.
Result Details:
* In `EvalResult.summary_metrics`, win rates for both the baseline and
candidate model are computed. The win rate is computed as proportion of
wins of one model's responses to total attempts as a decimal value
between 0 and 1.
* In `EvalResult.metrics_table`, a pairwise metric produces two
evaluation results per dataset row:
* `pairwise_choice`: The choice shows whether the candidate model or
the baseline model performs better, or if they are equally good.
* `explanation`: The rationale behind each verdict using
chain-of-thought reasoning. The explanation helps users scrutinize
the judgment and builds appropriate trust in the decisions.
See [documentation
page](https://cloud.google.com/vertex-ai/generative-ai/docs/models/determine-eval#understand-results)
for more details on understanding the metric results.
Usage Examples:
```
baseline_model = GenerativeModel("gemini-1.0-pro")
candidate_model = GenerativeModel("gemini-1.5-pro")
pairwise_groundedness = PairwiseMetric(
metric_prompt_template=MetricPromptTemplateExamples.get_prompt_template(
"pairwise_groundedness"
),
baseline_model=baseline_model,
)
eval_dataset = pd.DataFrame({
"prompt" : [...],
})
pairwise_task = EvalTask(
dataset=eval_dataset,
metrics=[pairwise_groundedness],
experiment="my-pairwise-experiment",
)
pairwise_result = pairwise_task.evaluate(
model=candidate_model,
experiment_run_name="gemini-pairwise-eval-run",
)
```
PairwiseMetricPromptTemplate
Pairwise metric prompt template for pairwise model-based metrics.
PointwiseMetric
A Model-based Pointwise Metric.
A model-based evaluation metric that evaluate a single generative model's response.
For more details on when to use model-based pointwise metrics, see Evaluation methods and metrics.
Usage Examples:
```
candidate_model = GenerativeModel("gemini-1.5-pro")
eval_dataset = pd.DataFrame({
"prompt" : [...],
})
fluency_metric = PointwiseMetric(
metric="fluency",
metric_prompt_template=MetricPromptTemplateExamples.get_prompt_template('fluency'),
)
pointwise_eval_task = EvalTask(
dataset=eval_dataset,
metrics=[
fluency_metric,
MetricPromptTemplateExamples.Pointwise.GROUNDEDNESS,
],
)
pointwise_result = pointwise_eval_task.evaluate(
model=candidate_model,
)
```
PointwiseMetricPromptTemplate
Pointwise metric prompt template for pointwise model-based metrics.
PromptTemplate
A prompt template for creating prompts with variables.
The PromptTemplate class allows users to define a template string with
variables represented in curly braces {variable}. The variable
names cannot contain spaces. These variables can be replaced with specific
values using the assemble method, providing flexibility in generating
dynamic prompts.
Usage:
```
template_str = "Hello, {name}! Today is {day}. How are you?"
prompt_template = PromptTemplate(template_str)
completed_prompt = prompt_template.assemble(name="John", day="Monday")
print(completed_prompt)
```
Rouge
The ROUGE Metric.
Calculates the recall of n-grams in prediction as compared to reference and returns a score ranging between 0 and 1. Supported rouge types are rougen[1-9], rougeL, and rougeLsum.
Candidate
A response candidate generated by the model.
ChatSession
Chat session holds the chat history.
Content
The multi-part content of a message.
Usage:
```
response = model.generate_content(contents=[
Content(role="user", parts=[Part.from_text("Why is sky blue?")])
])
```
FinishReason
The reason why the model stopped generating tokens. If empty, the model has not stopped generating the tokens.
FunctionCall
Function call.
FunctionDeclaration
A representation of a function declaration.
Usage: Create function declaration and tool:
```
get_current_weather_func = generative_models.FunctionDeclaration(
name="get_current_weather",
description="Get the current weather in a given location",
parameters={
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA"
},
"unit": {
"type": "string",
"enum": [
"celsius",
"fahrenheit",
]
}
},
"required": [
"location"
]
},
# Optional:
response={
"type": "object",
"properties": {
"weather": {
"type": "string",
"description": "The weather in the city"
},
},
},
)
weather_tool = generative_models.Tool(
function_declarations=[get_current_weather_func],
)
```
Use tool in `GenerativeModel.generate_content`:
```
model = GenerativeModel("gemini-pro")
print(model.generate_content(
"What is the weather like in Boston?",
# You can specify tools when creating a model to avoid having to send them with every request.
tools=[weather_tool],
))
```
Use tool in chat:
```
model = GenerativeModel(
"gemini-pro",
# You can specify tools when creating a model to avoid having to send them with every request.
tools=[weather_tool],
)
chat = model.start_chat()
print(chat.send_message("What is the weather like in Boston?"))
print(chat.send_message(
Part.from_function_response(
name="get_current_weather",
response={
"content": {"weather_there": "super nice"},
}
),
))
```
GenerationConfig
Parameters for the generation.
Modality
The modalities of the response.
RoutingConfig
The configuration for model router requests.
The routing config is either one of the two nested classes:
- AutoRoutingMode: Automated routing.
- ManualRoutingMode: Manual routing.
Usage:
AutoRoutingMode:
routing_config=generative_models.RoutingConfig( routing_config=generative_models.RoutingConfig.AutoRoutingMode( model_routing_preference=generative_models.RoutingConfig.AutoRoutingMode.ModelRoutingPreference.BALANCED, ), )ManualRoutingMode:
routing_config=generative_models.RoutingConfig( routing_config=generative_models.RoutingConfig.ManutalRoutingMode( model_name="gemini-1.5-pro-001", ), )
AutoRoutingMode
When automated routing is specified, the routing will be determined by the routing model predicted quality and customer provided model routing preference.
ModelRoutingPreference
The model routing preference.
ManualRoutingMode
When manual routing is set, the specified model will be used directly.
GenerationResponse
The response from the model.
GenerativeModel
Initializes GenerativeModel.
Usage:
```
model = GenerativeModel("gemini-pro")
print(model.generate_content("Hello"))
```
HarmBlockThreshold
Probability based thresholds levels for blocking.
HarmCategory
Harm categories that will block the content.
Image
The image that can be sent to a generative model.
Part
A part of a multi-part Content message.
Usage:
```
text_part = Part.from_text("Why is sky blue?")
image_part = Part.from_image(Image.load_from_file("image.jpg"))
video_part = Part.from_uri(uri="gs://.../video.mp4", mime_type="video/mp4")
function_response_part = Part.from_function_response(
name="get_current_weather",
response={
"content": {"weather_there": "super nice"},
}
)
response1 = model.generate_content([text_part, image_part])
response2 = model.generate_content(video_part)
response3 = chat.send_message(function_response_part)
```
ResponseValidationError
API documentation for ResponseValidationError class.
SafetySetting
Parameters for the generation.
HarmBlockMethod
Probability vs severity.
HarmBlockThreshold
Probability based thresholds levels for blocking.
HarmCategory
Harm categories that will block the content.
Tool
A collection of functions that the model may use to generate response.
Usage: Create tool from function declarations:
```
get_current_weather_func = generative_models.FunctionDeclaration(...)
weather_tool = generative_models.Tool(
function_declarations=[get_current_weather_func],
)
```
Use tool in `GenerativeModel.generate_content`:
```
model = GenerativeModel("gemini-pro")
print(model.generate_content(
"What is the weather like in Boston?",
# You can specify tools when creating a model to avoid having to send them with every request.
tools=[weather_tool],
))
```
Use tool in chat:
```
model = GenerativeModel(
"gemini-pro",
# You can specify tools when creating a model to avoid having to send them with every request.
tools=[weather_tool],
)
chat = model.start_chat()
print(chat.send_message("What is the weather like in Boston?"))
print(chat.send_message(
Part.from_function_response(
name="get_current_weather",
response={
"content": {"weather_there": "super nice"},
}
),
))
```
ToolConfig
Config shared for all tools provided in the request.
Usage: Create ToolConfig
```
tool_config = ToolConfig(
function_calling_config=ToolConfig.FunctionCallingConfig(
mode=ToolConfig.FunctionCallingConfig.Mode.ANY,
allowed_function_names=["get_current_weather_func"],
))
```
Use ToolConfig in `GenerativeModel.generate_content`:
```
model = GenerativeModel("gemini-pro")
print(model.generate_content(
"What is the weather like in Boston?",
# You can specify tools when creating a model to avoid having to send them with every request.
tools=[weather_tool],
tool_config=tool_config,
))
```
Use ToolConfig in chat:
```
model = GenerativeModel(
"gemini-pro",
# You can specify tools when creating a model to avoid having to send them with every request.
tools=[weather_tool],
tool_config=tool_config,
)
chat = model.start_chat()
print(chat.send_message("What is the weather like in Boston?"))
print(chat.send_message(
Part.from_function_response(
name="get_current_weather",
response={
"content": {"weather_there": "super nice"},
}
),
))
```
grounding
Grounding namespace.
DynamicRetrievalConfig
Config for dynamic retrieval.
Mode
The mode of the predictor to be used in dynamic retrieval.
GoogleSearchRetrieval
Tool to retrieve public web data for grounding, powered by Google Search.
Retrieval
Defines a retrieval tool that model can call to access external knowledge.
VertexAISearch
Retrieve from Vertex AI Search data store for grounding. See https://cloud.google.com/products/agent-builder
ChatMessage
A chat message.
ChatModel
ChatModel represents a language model that is capable of chat.
Examples::
chat_model = ChatModel.from_pretrained("chat-bison@001")
chat = chat_model.start_chat(
context="My name is Ned. You are my personal assistant. My favorite movies are Lord of the Rings and Hobbit.",
examples=[
InputOutputTextPair(
input_text="Who do you work for?",
output_text="I work for Ned.",
),
InputOutputTextPair(
input_text="What do I like?",
output_text="Ned likes watching movies.",
),
],
temperature=0.3,
)
chat.send_message("Do you know any cool events this weekend?")
ChatSession
ChatSession represents a chat session with a language model.
Within a chat session, the model keeps context and remembers the previous conversation.
CodeChatModel
CodeChatModel represents a model that is capable of completing code.
.. rubric:: Examples
code_chat_model = CodeChatModel.from_pretrained("codechat-bison@001")
code_chat = code_chat_model.start_chat( context="I'm writing a large-scale enterprise application.", max_output_tokens=128, temperature=0.2, )
code_chat.send_message("Please help write a function to calculate the min of two numbers")
CodeChatSession
CodeChatSession represents a chat session with code chat language model.
Within a code chat session, the model keeps context and remembers the previous converstion.
CodeGenerationModel
Creates a LanguageModel.
This constructor should not be called directly.
Use LanguageModel.from_pretrained(model_name=...) instead.
GroundingSource
API documentation for GroundingSource class.
InlineContext
InlineContext represents a grounding source using provided inline context. .. attribute:: inline_context
The content used as inline context.
:type: str
VertexAISearch
VertexAISearchDatastore represents a grounding source using Vertex AI Search datastore .. attribute:: data_store_id
Data store ID of the Vertex AI Search datastore.
:type: str
WebSearch
WebSearch represents a grounding source using public web search. .. attribute:: disable_attribution
If set to True, skip finding claim attributions (i.e not generate grounding citation). Default: False.
:type: bool
InputOutputTextPair
InputOutputTextPair represents a pair of input and output texts.
TextEmbedding
Text embedding vector and statistics.
TextEmbeddingInput
Structural text embedding input.
TextEmbeddingModel
Creates a LanguageModel.
This constructor should not be called directly.
Use LanguageModel.from_pretrained(model_name=...) instead.
TextGenerationModel
Creates a LanguageModel.
This constructor should not be called directly.
Use LanguageModel.from_pretrained(model_name=...) instead.
TextGenerationResponse
TextGenerationResponse represents a response of a language model. .. attribute:: text
The generated text
:type: str
_TunableModelMixin
Model that can be tuned with supervised fine tuning (SFT).
AutomaticFunctionCallingResponder
Responder that automatically responds to model's function calls.
CallableFunctionDeclaration
A function declaration plus a function.
Candidate
A response candidate generated by the model.
ChatSession
Chat session holds the chat history.
Content
The multi-part content of a message.
Usage:
```
response = model.generate_content(contents=[
Content(role="user", parts=[Part.from_text("Why is sky blue?")])
])
```
FinishReason
The reason why the model stopped generating tokens. If empty, the model has not stopped generating the tokens.
FunctionCall
Function call.
FunctionDeclaration
A representation of a function declaration.
Usage: Create function declaration and tool:
```
get_current_weather_func = generative_models.FunctionDeclaration(
name="get_current_weather",
description="Get the current weather in a given location",
parameters={
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA"
},
"unit": {
"type": "string",
"enum": [
"celsius",
"fahrenheit",
]
}
},
"required": [
"location"
]
},
# Optional:
response={
"type": "object",
"properties": {
"weather": {
"type": "string",
"description": "The weather in the city"
},
},
},
)
weather_tool = generative_models.Tool(
function_declarations=[get_current_weather_func],
)
```
Use tool in `GenerativeModel.generate_content`:
```
model = GenerativeModel("gemini-pro")
print(model.generate_content(
"What is the weather like in Boston?",
# You can specify tools when creating a model to avoid having to send them with every request.
tools=[weather_tool],
))
```
Use tool in chat:
```
model = GenerativeModel(
"gemini-pro",
# You can specify tools when creating a model to avoid having to send them with every request.
tools=[weather_tool],
)
chat = model.start_chat()
print(chat.send_message("What is the weather like in Boston?"))
print(chat.send_message(
Part.from_function_response(
name="get_current_weather",
response={
"content": {"weather_there": "super nice"},
}
),
))
```
GenerationConfig
Parameters for the generation.
Modality
The modalities of the response.
RoutingConfig
The configuration for model router requests.
The routing config is either one of the two nested classes:
- AutoRoutingMode: Automated routing.
- ManualRoutingMode: Manual routing.
Usage:
AutoRoutingMode:
routing_config=generative_models.RoutingConfig( routing_config=generative_models.RoutingConfig.AutoRoutingMode( model_routing_preference=generative_models.RoutingConfig.AutoRoutingMode.ModelRoutingPreference.BALANCED, ), )ManualRoutingMode:
routing_config=generative_models.RoutingConfig( routing_config=generative_models.RoutingConfig.ManutalRoutingMode( model_name="gemini-1.5-pro-001", ), )
AutoRoutingMode
When automated routing is specified, the routing will be determined by the routing model predicted quality and customer provided model routing preference.
ModelRoutingPreference
The model routing preference.
ManualRoutingMode
When manual routing is set, the specified model will be used directly.
GenerationResponse
The response from the model.
GenerativeModel
Initializes GenerativeModel.
Usage:
```
model = GenerativeModel("gemini-pro")
print(model.generate_content("Hello"))
```
HarmBlockThreshold
Probability based thresholds levels for blocking.
HarmCategory
Harm categories that will block the content.
Image
The image that can be sent to a generative model.
Part
A part of a multi-part Content message.
Usage:
```
text_part = Part.from_text("Why is sky blue?")
image_part = Part.from_image(Image.load_from_file("image.jpg"))
video_part = Part.from_uri(uri="gs://.../video.mp4", mime_type="video/mp4")
function_response_part = Part.from_function_response(
name="get_current_weather",
response={
"content": {"weather_there": "super nice"},
}
)
response1 = model.generate_content([text_part, image_part])
response2 = model.generate_content(video_part)
response3 = chat.send_message(function_response_part)
```
ResponseBlockedError
API documentation for ResponseBlockedError class.
ResponseValidationError
API documentation for ResponseValidationError class.
SafetySetting
Parameters for the generation.
HarmBlockMethod
Probability vs severity.
HarmBlockThreshold
Probability based thresholds levels for blocking.
HarmCategory
Harm categories that will block the content.
Tool
A collection of functions that the model may use to generate response.
Usage: Create tool from function declarations:
```
get_current_weather_func = generative_models.FunctionDeclaration(...)
weather_tool = generative_models.Tool(
function_declarations=[get_current_weather_func],
)
```
Use tool in `GenerativeModel.generate_content`:
```
model = GenerativeModel("gemini-pro")
print(model.generate_content(
"What is the weather like in Boston?",
# You can specify tools when creating a model to avoid having to send them with every request.
tools=[weather_tool],
))
```
Use tool in chat:
```
model = GenerativeModel(
"gemini-pro",
# You can specify tools when creating a model to avoid having to send them with every request.
tools=[weather_tool],
)
chat = model.start_chat()
print(chat.send_message("What is the weather like in Boston?"))
print(chat.send_message(
Part.from_function_response(
name="get_current_weather",
response={
"content": {"weather_there": "super nice"},
}
),
))
```
ToolConfig
Config shared for all tools provided in the request.
Usage: Create ToolConfig
```
tool_config = ToolConfig(
function_calling_config=ToolConfig.FunctionCallingConfig(
mode=ToolConfig.FunctionCallingConfig.Mode.ANY,
allowed_function_names=["get_current_weather_func"],
))
```
Use ToolConfig in `GenerativeModel.generate_content`:
```
model = GenerativeModel("gemini-pro")
print(model.generate_content(
"What is the weather like in Boston?",
# You can specify tools when creating a model to avoid having to send them with every request.
tools=[weather_tool],
tool_config=tool_config,
))
```
Use ToolConfig in chat:
```
model = GenerativeModel(
"gemini-pro",
# You can specify tools when creating a model to avoid having to send them with every request.
tools=[weather_tool],
tool_config=tool_config,
)
chat = model.start_chat()
print(chat.send_message("What is the weather like in Boston?"))
print(chat.send_message(
Part.from_function_response(
name="get_current_weather",
response={
"content": {"weather_there": "super nice"},
}
),
))
```
ChatMessage
A chat message.
CountTokensResponse
The response from a count_tokens request. .. attribute:: total_tokens
The total number of tokens counted across all instances passed to the request.
:type: int
EvaluationClassificationMetric
The evaluation metric response for classification metrics.
EvaluationMetric
The evaluation metric response.
EvaluationQuestionAnsweringSpec
Spec for question answering model evaluation tasks.
EvaluationTextClassificationSpec
Spec for text classification model evaluation tasks.
EvaluationTextGenerationSpec
Spec for text generation model evaluation tasks.
EvaluationTextSummarizationSpec
Spec for text summarization model evaluation tasks.
InputOutputTextPair
InputOutputTextPair represents a pair of input and output texts.
TextEmbedding
Text embedding vector and statistics.
TextEmbeddingInput
Structural text embedding input.
TextGenerationResponse
TextGenerationResponse represents a response of a language model. .. attribute:: text
The generated text
:type: str
TuningEvaluationSpec
Specification for model evaluation to perform during tuning.
Prompt
A prompt which may be a template with variables.
The Prompt class allows users to define a template string with
variables represented in curly braces {variable}. The variable
name must be a valid Python variable name (no spaces, must start with a
letter). These placeholders can be replaced with specific values using the
assemble_contents method, providing flexibility in generating dynamic prompts.
Usage: Generate content from a single set of variables:
prompt = Prompt(
prompt_data="Hello, {name}! Today is {day}. How are you?",
variables=[{"name": "Alice", "day": "Monday"}]
generation_config=GenerationConfig(
temperature=0.1,
top_p=0.95,
top_k=20,
candidate_count=1,
max_output_tokens=100,
),
model_name="gemini-1.0-pro-002",
safety_settings=[SafetySetting(
category=SafetySetting.HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT,
threshold=SafetySetting.HarmBlockThreshold.BLOCK_MEDIUM_AND_ABOVE,
method=SafetySetting.HarmBlockMethod.SEVERITY,
)],
system_instruction="Please answer in a short sentence.",
)
# Generate content using the assembled prompt.
prompt.generate_content(
contents=prompt.assemble_contents(**prompt.variables)
)
```
Generate content with multiple sets of variables:
```
prompt = Prompt(
prompt_data="Hello, {name}! Today is {day}. How are you?",
variables=[
{"name": "Alice", "day": "Monday"},
{"name": "Bob", "day": "Tuesday"},
],
generation_config=GenerationConfig(
temperature=0.1,
top_p=0.95,
top_k=20,
candidate_count=1,
max_output_tokens=100,
),
model_name="gemini-1.0-pro-002",
safety_settings=[SafetySetting(
category=SafetySetting.HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT,
threshold=SafetySetting.HarmBlockThreshold.BLOCK_MEDIUM_AND_ABOVE,
method=SafetySetting.HarmBlockMethod.SEVERITY,
)],
system_instruction="Please answer in a short sentence.",
)
# Generate content using the assembled prompt for each variable set.
for i in range(len(prompt.variables)):
prompt.generate_content(
contents=prompt.assemble_contents(**prompt.variables[i])
)
```
LangchainAgent
A Langchain Agent.
See https://cloud.google.com/vertex-ai/generative-ai/docs/reasoning-engine/develop for details.
Queryable
Protocol for Reasoning Engine applications that can be queried.
ReasoningEngine
Represents a Vertex AI Reasoning Engine resource.
TuningJob
Represents a TuningJob that runs with Google owned models.
SupervisedTuningJob
Initializes class with project, location, and api_client.
ControlImageConfig
Control image config.
ControlReferenceImage
Control reference image.
This encapsulates the control reference image type.
EntityLabel
Entity label holding a text label and any associated confidence score.
GeneratedImage
Generated image.
GeneratedMask
Generated image mask.
Image
Image.
ImageCaptioningModel
Generates captions from image.
Examples::
model = ImageCaptioningModel.from_pretrained("imagetext@001")
image = Image.load_from_file("image.png")
captions = model.get_captions(
image=image,
# Optional:
number_of_results=1,
language="en",
)
ImageGenerationModel
Generates images from text prompt.
Examples::
model = ImageGenerationModel.from_pretrained("imagegeneration@002")
response = model.generate_images(
prompt="Astronaut riding a horse",
# Optional:
number_of_images=1,
seed=0,
)
response[0].show()
response[0].save("image1.png")
ImageGenerationResponse
Image generation response.
ImageQnAModel
Answers questions about an image.
Examples::
model = ImageQnAModel.from_pretrained("imagetext@001")
image = Image.load_from_file("image.png")
answers = model.ask_question(
image=image,
question="What color is the car in this image?",
# Optional:
number_of_results=1,
)
ImageSegmentationModel
Segments an image.
ImageSegmentationResponse
Image Segmentation response.
ImageTextModel
Generates text from images.
Examples::
model = ImageTextModel.from_pretrained("imagetext@001")
image = Image.load_from_file("image.png")
captions = model.get_captions(
image=image,
# Optional:
number_of_results=1,
language="en",
)
answers = model.ask_question(
image=image,
question="What color is the car in this image?",
# Optional:
number_of_results=1,
)
MaskImageConfig
Mask image config.
MaskReferenceImage
Mask reference image. This encapsulates the mask reference image type.
MultiModalEmbeddingModel
Generates embedding vectors from images and videos.
Examples::
model = MultiModalEmbeddingModel.from_pretrained("multimodalembedding@001")
image = Image.load_from_file("image.png")
video = Video.load_from_file("video.mp4")
embeddings = model.get_embeddings(
image=image,
video=video,
contextual_text="Hello world",
)
image_embedding = embeddings.image_embedding
video_embeddings = embeddings.video_embeddings
text_embedding = embeddings.text_embedding
MultiModalEmbeddingResponse
The multimodal embedding response.
RawReferenceImage
Raw reference image.
This encapsulates the raw reference image type.
ReferenceImage
Reference image.
This is a new base API object for Imagen 3.0 Capabilities.
Scribble
Input scribble for image segmentation.
StyleImageConfig
Style image config.
StyleReferenceImage
Style reference image. This encapsulates the style reference image type.
SubjectImageConfig
Subject image config.
SubjectReferenceImage
Subject reference image.
This encapsulates the subject reference image type.
Video
Video.
VideoEmbedding
Embeddings generated from video with offset times.
VideoSegmentConfig
The specific video segments (in seconds) the embeddings are generated for.
WatermarkVerificationModel
Verifies if an image has a watermark.
WatermarkVerificationResponse
WatermarkVerificationResponse(_prediction_response: Any, watermark_verification_result: Optional[str] = None)
Arguments
Arguments. Child of Execution.
Execution
Execution. Child of MultimodalPrompt.
MultimodalPrompt
MultimodalPrompt. Child of PromptDatasetMetadata.
PromptDatasetMetadata
PromptDatasetMetadata.
PromptMetadata
Metadata containing the display name and prompt id of a prompt.
Returned by the list_prompts method.
PromptVersionMetadata
Metadata containing the display name, prompt id, and version id of a prompt version.
Returned by the list_prompt_versions method.
Prompt
A prompt which may be a template with variables.
The Prompt class allows users to define a template string with
variables represented in curly braces {variable}. The variable
name must be a valid Python variable name (no spaces, must start with a
letter). These placeholders can be replaced with specific values using the
assemble_contents method, providing flexibility in generating dynamic prompts.
Usage: Generate content from a single set of variables:
prompt = Prompt(
prompt_data="Hello, {name}! Today is {day}. How are you?",
variables=[{"name": "Alice", "day": "Monday"}]
generation_config=GenerationConfig(
temperature=0.1,
top_p=0.95,
top_k=20,
candidate_count=1,
max_output_tokens=100,
),
model_name="gemini-1.0-pro-002",
safety_settings=[SafetySetting(
category=SafetySetting.HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT,
threshold=SafetySetting.HarmBlockThreshold.BLOCK_MEDIUM_AND_ABOVE,
method=SafetySetting.HarmBlockMethod.SEVERITY,
)],
system_instruction="Please answer in a short sentence.",
)
# Generate content using the assembled prompt.
prompt.generate_content(
contents=prompt.assemble_contents(**prompt.variables)
)
```
Generate content with multiple sets of variables:
```
prompt = Prompt(
prompt_data="Hello, {name}! Today is {day}. How are you?",
variables=[
{"name": "Alice", "day": "Monday"},
{"name": "Bob", "day": "Tuesday"},
],
generation_config=GenerationConfig(
temperature=0.1,
top_p=0.95,
top_k=20,
candidate_count=1,
max_output_tokens=100,
),
model_name="gemini-1.0-pro-002",
safety_settings=[SafetySetting(
category=SafetySetting.HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT,
threshold=SafetySetting.HarmBlockThreshold.BLOCK_MEDIUM_AND_ABOVE,
method=SafetySetting.HarmBlockMethod.SEVERITY,
)],
system_instruction="Please answer in a short sentence.",
)
# Generate content using the assembled prompt for each variable set.
for i in range(len(prompt.variables)):
prompt.generate_content(
contents=prompt.assemble_contents(**prompt.variables[i])
)
```
ModelMonitor
Initializer for ModelMonitor.
ModelMonitoringJob
Initializer for ModelMonitoringJob.
Example Usage:
my_monitoring_job = aiplatform.ModelMonitoringJob(
model_monitoring_job_name='projects/123/locations/us-central1/modelMonitors/\
my_model_monitor_id/modelMonitoringJobs/my_monitoring_job_id'
)
or
my_monitoring_job = aiplatform.aiplatform.ModelMonitoringJob(
model_monitoring_job_name='my_monitoring_job_id',
model_monitor_id='my_model_monitor_id',
)
DataDriftSpec
Data drift monitoring spec.
Data drift measures the distribution distance between the current dataset and a baseline dataset. A typical use case is to detect data drift between the recent production serving dataset and the training dataset, or to compare the recent production dataset with a dataset from a previous period.
.. rubric:: Example
feature_drift_spec=DataDriftSpec( features=["feature1"] categorical_metric_type="l_infinity", numeric_metric_type="jensen_shannon_divergence", default_categorical_alert_threshold=0.01, default_numeric_alert_threshold=0.02, feature_alert_thresholds={"feature1":0.02, "feature2":0.01}, )
FeatureAttributionSpec
Feature attribution spec.
.. rubric:: Example
feature_attribution_spec=FeatureAttributionSpec( features=["feature1"] default_alert_threshold=0.01, feature_alert_thresholds={"feature1":0.02, "feature2":0.01}, batch_dedicated_resources=BatchDedicatedResources( starting_replica_count=1, max_replica_count=2, machine_spec=my_machine_spec, ), )
FieldSchema
Field Schema.
The class identifies the data type of a single feature, which combines together to form the Schema for different fields in ModelMonitoringSchema.
ModelMonitoringSchema
Initializer for ModelMonitoringSchema.
MonitoringInput
Model monitoring data input spec.
NotificationSpec
Initializer for NotificationSpec.
ObjectiveSpec
Initializer for ObjectiveSpec.
OutputSpec
Initializer for OutputSpec.
TabularObjective
Initializer for TabularObjective.
GeneratedImage
Generated image.
Image
Image.
ImageCaptioningModel
Generates captions from image.
Examples::
model = ImageCaptioningModel.from_pretrained("imagetext@001")
image = Image.load_from_file("image.png")
captions = model.get_captions(
image=image,
# Optional:
number_of_results=1,
language="en",
)
ImageGenerationModel
Generates images from text prompt.
Examples::
model = ImageGenerationModel.from_pretrained("imagegeneration@002")
response = model.generate_images(
prompt="Astronaut riding a horse",
# Optional:
number_of_images=1,
seed=0,
)
response[0].show()
response[0].save("image1.png")
ImageGenerationResponse
Image generation response.
ImageQnAModel
Answers questions about an image.
Examples::
model = ImageQnAModel.from_pretrained("imagetext@001")
image = Image.load_from_file("image.png")
answers = model.ask_question(
image=image,
question="What color is the car in this image?",
# Optional:
number_of_results=1,
)
ImageTextModel
Generates text from images.
Examples::
model = ImageTextModel.from_pretrained("imagetext@001")
image = Image.load_from_file("image.png")
captions = model.get_captions(
image=image,
# Optional:
number_of_results=1,
language="en",
)
answers = model.ask_question(
image=image,
question="What color is the car in this image?",
# Optional:
number_of_results=1,
)
MultiModalEmbeddingModel
Generates embedding vectors from images and videos.
Examples::
model = MultiModalEmbeddingModel.from_pretrained("multimodalembedding@001")
image = Image.load_from_file("image.png")
video = Video.load_from_file("video.mp4")
embeddings = model.get_embeddings(
image=image,
video=video,
contextual_text="Hello world",
)
image_embedding = embeddings.image_embedding
video_embeddings = embeddings.video_embeddings
text_embedding = embeddings.text_embedding
MultiModalEmbeddingResponse
The multimodal embedding response.
Video
Video.
VideoEmbedding
Embeddings generated from video with offset times.
VideoSegmentConfig
The specific video segments (in seconds) the embeddings are generated for.
Modules
_language_models
Classes for working with language models.
generative_models
Classes for working with the Gemini models.
language_models
Classes for working with language models.
prompts
API documentation for prompts module.
sft
Classes for supervised tuning.
vision_models
Classes for working with vision models.
_prompt_management
API documentation for _prompt_management module.
_prompts
API documentation for _prompts module.