generative-ai.md

Home > @google/generative-ai

generative-ai package

Classes

Class	Description
ChatSession	ChatSession class that enables sending chat messages and stores history of sent and received messages so far.
GenerativeModel	Class for generative model APIs.
GoogleGenerativeAI	Top-level class for this SDK
GoogleGenerativeAIError	Basic error type for this SDK.
GoogleGenerativeAIFetchError	Error class covering HTTP errors when calling the server. Includes HTTP status, statusText, and optional details, if provided in the server response.
GoogleGenerativeAIRequestInputError	Errors in the contents of a request originating from user input.
GoogleGenerativeAIResponseError	Errors in the contents of a response from the model. This includes parsing errors, or responses including a safety block reason.

Enumerations

Enumeration	Description
BlockReason	Reason that a prompt was blocked.
FinishReason	Reason that a candidate finished.
FunctionCallingMode
FunctionDeclarationSchemaType	Contains the list of OpenAPI data types as defined by https://swagger.io/docs/specification/data-models/data-types/
HarmBlockThreshold	Threshold above which a prompt or candidate will be blocked.
HarmCategory	Harm categories that would cause prompts or candidates to be blocked.
HarmProbability	Probability that a prompt or candidate matches a harm category.
TaskType	Task type for embedding content.

Interfaces

Interface	Description
BaseParams	Base parameters for a number of methods.
BatchEmbedContentsRequest	Params for calling GenerativeModel.batchEmbedContents()
BatchEmbedContentsResponse	Response from calling GenerativeModel.batchEmbedContents().
CitationMetadata	Citation metadata that may be found on a GenerateContentCandidate.
CitationSource	A single citation source.
Content	Content type for both prompts and response candidates.
ContentEmbedding	A single content embedding.
CountTokensRequest	Params for calling GenerativeModel.countTokens()
CountTokensResponse	Response from calling GenerativeModel.countTokens().
EmbedContentRequest	Params for calling GenerativeModel.embedContent()
EmbedContentResponse	Response from calling GenerativeModel.embedContent().
EnhancedGenerateContentResponse	Response object wrapped with helper methods.
FileData	Data pointing to a file uploaded with the Files API.
FileDataPart	Content part interface if the part represents FunctionResponse.
FunctionCall	A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values.
FunctionCallingConfig
FunctionCallPart	Content part interface if the part represents FunctionResponse.
FunctionDeclaration	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.
FunctionDeclarationSchema	Schema for parameters passed to FunctionDeclaration.parameters.
FunctionDeclarationSchemaProperty	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.
FunctionDeclarationsTool	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.
FunctionResponse	The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction.
FunctionResponsePart	Content part interface if the part represents FunctionResponse.
GenerateContentCandidate	A candidate returned as part of a GenerateContentResponse.
GenerateContentRequest	Request sent to generateContent endpoint.
GenerateContentResponse	Individual response from GenerativeModel.generateContent() and GenerativeModel.generateContentStream(). generateContentStream() will return one in each chunk until the stream is done.
GenerateContentResult	Result object returned from generateContent() call.
GenerateContentStreamResult	Result object returned from generateContentStream() call. Iterate over stream to get chunks as they come in and/or use the response promise to get the aggregated response when the stream is done.
GenerationConfig	Config options for content-related requests
GenerativeContentBlob	Interface for sending an image.
InlineDataPart	Content part interface if the part represents an image.
ModelParams	Params passed to GoogleGenerativeAI.getGenerativeModel().
PromptFeedback	If the prompt was blocked, this will be populated with blockReason and the relevant safetyRatings.
RequestOptions	Params passed to getGenerativeModel() or GoogleAIFileManager().
SafetyRating	A safety rating associated with a GenerateContentCandidate
SafetySetting	Safety setting that can be sent as part of request parameters.
StartChatParams	Params for GenerativeModel.startChat().
TextPart	Content part interface if the part represents a text string.
ToolConfig	Tool config. This config is shared for all tools provided in the request.
UsageMetadata	Metadata on the generation request's token usage.

Variables

Variable	Description
POSSIBLE_ROLES	Possible roles.

Type Aliases

Type Alias	Description
Part	Content part - includes text or image part types.
Tool	Defines a tool that model can call to access external knowledge.