Package @google-cloud/vertexai (1.1.0)

The ChatSession class is used to make multiturn send message requests. You can instantiate this class by using the startChat method in the GenerativeModel class. The sendMessage method makes an async call to get the response of a chat message at at once. The sendMessageStream method makes an async call to stream the response of a chat message as it's being generated.

The ChatSessionPreview class is used to make multiturn send message requests. You can instantiate this class by using the startChat method in the GenerativeModelPreview class. The sendMessage method makes an async call to get the response of a chat message at at once. The sendMessageStream method makes an async call to stream the response of a chat message as it's being generated.

ClientError is thrown when http 4XX status is received. For details please refer to https://developer.mozilla.org/en-US/docs/Web/HTTP/Status#client_error_responses

Helper class to render any extra properties out of GenerateContentResponse or properties of GenerateContentResponse

The GenerativeModel class is the base class for the generative models on Vertex AI. NOTE: Don't instantiate this class directly. Use vertexai.getGenerativeModel() instead.

The GenerativeModelPreview class is the base class for the generative models that are in preview. NOTE: Don't instantiate this class directly. Use vertexai.preview.getGenerativeModel() instead.

GoogleAuthError is thrown when there is authentication issue with the request

GoogleGenerativeAIError is thrown when http response is not ok and status code is not 4XX For details please refer to https://developer.mozilla.org/en-US/docs/Web/HTTP/Status

The VertexAI class is the base class for authenticating to Vertex AI. To use Vertex AI's generative AI models, use the getGenerativeModel method. To use generative AI features that are in Preview, use the preview namespace.

Base params for initializing a model or calling GenerateContent.

A part of a turn in a conversation with the model with a fixed MIME type. It has one of the following mutually exclusive fields: 1. text 2. inlineData 3. fileData 4. functionResponse 5. functionCall

Source attributions for content.

A collection of source attributions for a piece of content.

The base structured datatype containing multi-part content of a message.

Params used to call the countTokens method.

Response returned from countTokens method.

URI based data.

A file data part of a conversation with the model.

A predicted FunctionCall returned from the model that contains a string representating the FunctionDeclaration.name with the parameters and their values.

A function call part of a conversation with the model.

Structured representation of a function declaration as defined by the [OpenAPI 3.0 specification](https://spec.openapis.org/oas/v3.0.3). Included in this declaration are the function name and parameters. This FunctionDeclaration is a representation of a block of code that can be used as a Tool by the model and executed by the client.

Schema for parameters passed to FunctionDeclaration.parameters.

Schema is used to define the format of input/output data. Represents a select subset of an OpenAPI 3.0 schema object. More fields may be added in the future as needed.

A FunctionDeclarationsTool is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model.

The result output of a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function call. It is used as context to the model.

A function response part of a conversation with the model.

A response candidate generated from the model.

Params used to call the generateContent method.

Response from the model supporting multiple candidates.

Wrapper for respones from a generateContent request.

Configuration options for model generation and outputs.

Raw media bytes sent directly in the request. Text should not be sent as raw bytes.

Params used to call the getGenerativeModel method.

Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following:

A full date, with non-zero year, month, and day values. A month and day, with a zero year (for example, an anniversary). A year on its own, with a zero month and a zero day. A year and month, with a zero day (for example, a credit card expiration date).

Tool to retrieve public web data for grounding, powered by Google.

Defines a retrieval tool that model can call to access external knowledge.

Grounding attribution.

Attribution from context retrieved by the retrieval tools.

Segment of the content this attribution belongs to.

Attribution from the web.

A collection of grounding attributions for a piece of content.

An inline data part of a conversation with the model.

Configuration for initializing a model, for example via getGenerativeModel in VertexAI class.

Content filter results for a prompt sent in the request.

Request options params passed to getGenerativeModel method in VertexAI class.

Defines a retrieval tool that model can call to access external knowledge.

Defines a retrieval tool that model can call to access external knowledge.

Safety rating corresponding to the generated content.

Safety feedback for an entire request.

Params to initiate a multiturn chat with the model via startChat.

All params passed to initiate multiturn chat via startChat.

Wrapper for respones from a generateContentStream method.

A text part of a conversation with the model.

Usage metadata about response(s).

Retrieve from Vertex AI Search datastore for grounding.

Params used to initialize the Vertex SDK.

The reason why the reponse is blocked.

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

Contains the list of OpenAPI data types as defined by https://swagger.io/docs/specification/data-models/data-types/

Probability based thresholds levels for blocking.

Harm categories that will block the content.

Harm probability levels in the content.

Harm severity levels