Module generative_models (1.45.0)

Classes for working with the Gemini models.

Classes

Candidate

Candidate()

A response candidate generated by the model.

ChatSession

ChatSession(
    model: vertexai.generative_models._generative_models._GenerativeModel,
    *,
    history: typing.Optional[
        typing.List[vertexai.generative_models._generative_models.Content]
    ] = None,
    response_validation: bool = True,
    raise_on_blocked: typing.Optional[bool] = None
)

Chat session holds the chat history.

Content

Content(
    *,
    parts: typing.Optional[
        typing.List[vertexai.generative_models._generative_models.Part]
    ] = None,
    role: typing.Optional[str] = None
)

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

FinishReason(value)

The reason why the model stopped generating tokens. If empty, the model has not stopped generating the tokens.

Values: FINISH_REASON_UNSPECIFIED (0): The finish reason is unspecified. STOP (1): Natural stop point of the model or provided stop sequence. MAX_TOKENS (2): The maximum number of tokens as specified in the request was reached. SAFETY (3): The token generation was stopped as the response was flagged for safety reasons. NOTE: When streaming the Candidate.content will be empty if content filters blocked the output. RECITATION (4): The token generation was stopped as the response was flagged for unauthorized citations. OTHER (5): All other reasons that stopped the token generation BLOCKLIST (6): The token generation was stopped as the response was flagged for the terms which are included from the terminology blocklist. PROHIBITED_CONTENT (7): The token generation was stopped as the response was flagged for the prohibited contents. SPII (8): The token generation was stopped as the response was flagged for Sensitive Personally Identifiable Information (SPII) contents.

FunctionDeclaration

FunctionDeclaration(
    *,
    name: str,
    parameters: typing.Dict[str, typing.Any],
    description: typing.Optional[str] = None
)

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"
        ]
    },
)
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

GenerationConfig(
    *,
    temperature: typing.Optional[float] = None,
    top_p: typing.Optional[float] = None,
    top_k: typing.Optional[int] = None,
    candidate_count: typing.Optional[int] = None,
    max_output_tokens: typing.Optional[int] = None,
    stop_sequences: typing.Optional[typing.List[str]] = None
)

Parameters for the generation.

GenerationResponse

GenerationResponse()

The response from the model.

GenerativeModel

GenerativeModel(
    model_name: str,
    *,
    generation_config: typing.Optional[
        typing.Union[
            vertexai.generative_models._generative_models.GenerationConfig,
            typing.Dict[str, typing.Any],
        ]
    ] = None,
    safety_settings: typing.Optional[
        typing.Union[
            typing.List[google.cloud.aiplatform_v1beta1.types.content.SafetySetting],
            typing.Dict[
                google.cloud.aiplatform_v1beta1.types.content.HarmCategory,
                google.cloud.aiplatform_v1beta1.types.content.SafetySetting.HarmBlockThreshold,
            ],
        ]
    ] = None,
    tools: typing.Optional[
        typing.List[vertexai.generative_models._generative_models.Tool]
    ] = None
)

Initializes GenerativeModel.

Usage:

model = GenerativeModel("gemini-pro")
print(model.generate_content("Hello"))
```
Parameter
Name Description
model_name str

Model Garden model resource name.

HarmBlockThreshold

HarmBlockThreshold(value)

Probability based thresholds levels for blocking.

Values: HARM_BLOCK_THRESHOLD_UNSPECIFIED (0): Unspecified harm block threshold. BLOCK_LOW_AND_ABOVE (1): Block low threshold and above (i.e. block more). BLOCK_MEDIUM_AND_ABOVE (2): Block medium threshold and above. BLOCK_ONLY_HIGH (3): Block only high threshold (i.e. block less). BLOCK_NONE (4): Block none.

HarmCategory

HarmCategory(value)

Harm categories that will block the content.

Values: HARM_CATEGORY_UNSPECIFIED (0): The harm category is unspecified. HARM_CATEGORY_HATE_SPEECH (1): The harm category is hate speech. HARM_CATEGORY_DANGEROUS_CONTENT (2): The harm category is dangerous content. HARM_CATEGORY_HARASSMENT (3): The harm category is harassment. HARM_CATEGORY_SEXUALLY_EXPLICIT (4): The harm category is sexually explicit content.

Image

Image()

The image that can be sent to a generative model.

Part

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

ResponseBlockedError(
    message: str,
    request_contents: typing.List[
        vertexai.generative_models._generative_models.Content
    ],
    responses: typing.List[
        vertexai.generative_models._generative_models.GenerationResponse
    ],
)

Common base class for all non-exit exceptions.

ResponseValidationError

ResponseValidationError(
    message: str,
    request_contents: typing.List[
        vertexai.generative_models._generative_models.Content
    ],
    responses: typing.List[
        vertexai.generative_models._generative_models.GenerationResponse
    ],
)

Common base class for all non-exit exceptions.

Tool

Tool(
    function_declarations: typing.List[
        vertexai.generative_models._generative_models.FunctionDeclaration
    ],
)

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"},
        }
    ),
))
```

grounding

grounding()

Grounding namespace.