firebase_ai library

Classes

AudioTranscriptionConfig
The audio transcription configuration.
AutoFunctionDeclaration
A FunctionDeclaration for auto function calling.
Candidate
Response candidate generated from a GenerativeModel.
ChatSession
A back-and-forth chat with a generative model.
Citation
Citation to a source for a portion of a specific response.
CitationMetadata
Source attributions for a piece of content.
CodeExecution
A tool that allows the model to use Code Execution.
CodeExecutionResultPart
A Part that represents the code execution result from the model.
Content
The base structured datatype containing multi-part content of a message.
ContextWindowCompressionConfig
Enables context window compression to manage the model's context window.
CountTokensResponse
Response for Count Tokens
ExecutableCodePart
A Part that represents the code that is executed by the model.
FileData
A Part with Firebase Storage uri as prompt content
FirebaseAI
The entrypoint for generative models.
FunctionCall
A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name with the arguments and their values.
FunctionCallingConfig
Configuration specifying how the model should use the functions provided as tools.
FunctionDeclaration
Structured representation of a function declaration as defined by the OpenAPI 3.03 specification.
FunctionResponse
The response class for FunctionCall
GenerateContentResponse
Response from the model; supports multiple candidates.
GenerationConfig
Configuration options for model generation and outputs.
GenerativeModel
A multimodel generative model (like Gemini).
GoingAwayNotice
A server message indicating that the server will not be able to service the client soon.
GoogleMaps
A tool that allows a Gemini model to connect to Google Maps to access and incorporate location-based information into its responses.
GoogleMapsGroundingChunk
A grounding chunk sourced from Google Maps.
GoogleSearch
A tool that allows the generative model to connect to Google Search to access and incorporate up-to-date information from the web into its responses.
GroundingChunk
Represents a chunk of retrieved data that supports a claim in the model's response.
ImageConfig
Configuration options for generating images with Gemini models.
ImagenBackgroundMask
A background mask.
ImagenControlConfig
The configuration for the control.
ImagenControlReference
A control reference.
ImagenDimensions
The dimensions of an image.
ImagenEditingConfig
The configuration for image editing.
ImagenForegroundMask
A foreground mask.
ImagenFormat
Represents the image format and compression quality.
ImagenGenerationConfig
Configuration options for image generation.
ImagenImagePlacement
The placement of an image.
ImagenInlineImage
Represents an image stored as a base64-encoded string.
ImagenMaskConfig
The configuration for the mask.
ImagenMaskReference
A reference image that is a mask.
ImagenModel
Represents a remote Imagen model with the ability to generate images using text prompts.
ImagenRawImage
A raw image.
ImagenRawMask
A raw mask.
ImagenReferenceImage
A reference image for image editing.
ImagenSafetySettings
A class representing safety settings for image generation.
ImagenSemanticMask
A semantic mask.
ImagenStyleConfig
The configuration for the style.
ImagenStyleReference
A style reference.
ImagenSubjectConfig
The configuration for the subject.
ImagenSubjectReference
A subject reference.
InlineDataPart
A Part with the byte content of a file.
JSONSchema
The definition of a JSON Schema data type.
LatLng
An object that represents a latitude/longitude pair.
LiveGenerationConfig
Configures live generation settings.
LiveGenerativeModel
A live, generative AI model for real-time interaction.
LiveServerContent
Content generated by the model in a live stream.
LiveServerMessage
An abstract class representing a message received from a live server.
LiveServerResponse
A single response chunk received during a live content generation.
LiveServerToolCall
A tool call in a live stream.
LiveServerToolCallCancellation
A tool call cancellation in a live stream.
LiveSession
Manages asynchronous communication with Gemini model over a WebSocket connection.
Part
A datatype containing media that is part of a multi-part Content message.
PromptFeedback
Feedback metadata of a prompt specified in a GenerativeModel request.
RetrievalConfig
The configuration that specifies information which can be used by tools during inference calls.
SafetyRating
Safety rating for a piece of content.
SafetySetting
Safety setting, affecting the safety-blocking behavior.
Schema
The definition of an input or output data types.
SessionResumptionConfig
Configuration for the session resumption mechanism.
SessionResumptionUpdate
An update of the session resumption state.
SlidingWindow
Configures the sliding window context compression mechanism.
SpeechConfig
Configures speech synthesis settings.
TemplateAutoFunctionDeclaration
A function declaration for a template tool that can be called by the model.
TemplateChatSession
A back-and-forth chat with a server template.
TemplateFunctionDeclaration
A function declaration for a template tool.
TemplateGenerativeModel
A generative model that connects to a remote server template.
TemplateImagenModel
An image model that connects to a remote server template.
TemplateTool
A collection of template tools.
TemplateToolConfig
Config for template tools to use with server prompts.
TextPart
A Part with the text content.
ThinkingConfig
Config for thinking features.
Tool
Tool details that the model may use to generate a response.
ToolConfig
Config for tools to use with model.
Transcription
Audio transcription message.
UnknownPart
A Part that contains unparsable data.
UrlContext
A tool that allows you to provide additional context to the models in the form of public web URLs. By including URLs in your request, the Gemini model will access the content from those pages to inform and enhance its response.
UsageMetadata
Metadata on the generation request's token usage.
WebGroundingChunk
A grounding chunk sourced from the web.

Enums

BlockReason
The reason why a prompt was blocked.
FinishReason
Reason why a model stopped generating tokens.
FunctionCallingMode
The mode in which the model should use the functions provided as tools.
HarmBlockMethod
Specifies how the block method computes the score that will be compared against the HarmBlockThreshold in SafetySetting.
HarmBlockThreshold
Probability of harm which causes content to be blocked.
HarmCategory
The category of a rating.
HarmProbability
The probability that a piece of content is harmful.
ImageAspectRatio
An aspect ratio for generated images.
ImagenAspectRatio
The aspect ratio for the image.
ImagenControlType
The type of control image.
ImagenEditMode
The desired outcome of the image editing.
ImagenMaskMode
The mode of the mask.
ImagenPersonFilterLevel
Allow generation of people by the model.
ImagenSafetyFilterLevel
Specifies the level of safety filtering for image generation.
ImagenSubjectReferenceType
The type of the subject in the image.
ImageSize
The size of images to generate.
ResponseModalities
The available response modalities.
SchemaType
The value type of a Schema.
ThinkingLevel
A preset that balances the trade-off between reasoning quality and response speed for a model's "thinking" process.

Exceptions / Errors

FirebaseAIException
Exception thrown when generating content fails.
FirebaseAISdkException
Exception indicating a stale package version or implementation bug.
InvalidApiKey
Exception thrown when the server rejects the API key.
QuotaExceeded
Exception thrown when the quota is exceeded.
ServerException
Exception thrown when the server failed to generate content.
ServiceApiNotEnabled
Exception thrown when the service API is not enabled.
UnsupportedUserLocation
Exception thrown when the user location is unsupported.