Firebase.AI

Summary

Enumerations
BlockReason{   Unknown = 0,   Safety,   Other,   Blocklist,   ProhibitedContent }	enum A type describing possible reasons to block a prompt.
ContentModality{   Unknown = 0,   Text,   Image,   Video,   Audio,   Document }	enum Content part modality.
FinishReason{   Unknown = 0,   Stop,   MaxTokens,   Safety,   Recitation,   Other,   Blocklist,   ProhibitedContent,   SPII,   MalformedFunctionCall }	enum Represents the reason why the model stopped generating content.
HarmCategory{   Unknown = 0,   Harassment,   HateSpeech,   SexuallyExplicit,   DangerousContent,   CivicIntegrity }	enum Categories describing the potential harm a piece of content may pose.
ImagenAspectRatio{   Square1x1,   Portrait9x16,   Landscape16x9,   Portrait3x4,   Landscape4x3 }	enum An aspect ratio for images generated by Imagen.
ResponseModality{   Text,   Image,   Audio }	enum The response type the model should return with.

Classes
Firebase.AI.Chat	An object that represents a back-and-forth chat with a model, capturing the history and saving the context in memory between each message sent.
Firebase.AI.FirebaseAI	The entry point for all FirebaseAI SDK functionality.
Firebase.AI.GenerativeModel	A type that represents a remote multimodal model (like Gemini), with the ability to generate content based on various input types.
Firebase.AI.ImagenModel	Represents a remote Imagen model with the ability to generate images using text prompts.
Firebase.AI.LiveGenerativeModel	A live, generative AI model for real-time interaction.
Firebase.AI.LiveSession	Manages asynchronous communication with Gemini model over a WebSocket connection.
Firebase.AI.Schema	A Schema object allows the definition of input and output data types.
Firebase.AI.TemplateGenerativeModel	A type that represents a remote multimodal model (like Gemini), with the ability to generate content based on defined server prompt templates.
Firebase.AI.TemplateImagenModel	Represents a remote Imagen model with the ability to generate images using server template prompts.

Structs
Firebase.AI.AudioTranscriptionConfig	A struct used to configure speech transcription settings.
Firebase.AI.Candidate	A struct representing a possible reply to a content generation prompt.
Firebase.AI.Citation	A struct describing a source attribution.
Firebase.AI.CitationMetadata	A collection of source attributions for a piece of content.
Firebase.AI.CodeExecution	A tool that allows the model to execute code.
Firebase.AI.CountTokensResponse	The model's response to a count tokens request.
Firebase.AI.FunctionCallingConfig	Configuration for specifying function calling behavior.
Firebase.AI.FunctionDeclaration	Structured representation of a function declaration.
Firebase.AI.GenerateContentResponse	The model's response to a generate content request.
Firebase.AI.GenerationConfig	A struct defining model parameters to be used when sending generative AI requests to the backend model.
Firebase.AI.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.
Firebase.AI.GroundingChunk	Represents a chunk of retrieved data that supports a claim in the model's response.
Firebase.AI.GroundingMetadata	Metadata returned to the client when grounding is enabled.
Firebase.AI.GroundingSupport	Provides information about how a specific segment of the model's response is supported by the retrieved grounding chunks.
Firebase.AI.ImagenGenerationConfig	Configuration options for generating images with Imagen.
Firebase.AI.ImagenGenerationResponse< T >	A response from a request to generate images with Imagen.
Firebase.AI.ImagenImageFormat	An image format for images generated by Imagen.
Firebase.AI.ImagenInlineImage	An image generated by Imagen, represented as inline data.
Firebase.AI.ImagenSafetySettings	Settings for controlling the aggressiveness of filtering out sensitive content.
Firebase.AI.LiveGenerationConfig	A struct defining model parameters to be used when generating live session content.
Firebase.AI.LiveSessionContent	Content generated by the model in a live session.
Firebase.AI.LiveSessionResponse	Represents the response from the model for live content updates.
Firebase.AI.LiveSessionToolCall	A request to use a tool from the live session.
Firebase.AI.LiveSessionToolCallCancellation	A request to cancel using a tool from the live session.
Firebase.AI.ModalityTokenCount	Represents token counting info for a single modality.
Firebase.AI.ModelContent	A type describing data in media formats interpretable by an AI model.
Firebase.AI.PromptFeedback	A metadata struct containing any feedback the model had on the prompt it was provided.
Firebase.AI.RequestOptions	Configuration parameters for sending requests to the backend.
Firebase.AI.SafetyRating	A type defining potentially harmful media categories and their model-assigned ratings.
Firebase.AI.SafetySetting	A type used to specify a threshold for harmful content, beyond which the model will return a fallback response instead of generated content.
Firebase.AI.SearchEntryPoint	A struct representing the Google Search entry point.
Firebase.AI.Segment	Represents a specific segment within a ModelContent struct, often used to pinpoint the exact location of text or data that grounding information refers to.
Firebase.AI.SpeechConfig	A struct used to configure speech generation settings.
Firebase.AI.ThinkingConfig	Configuration options for Thinking features.
Firebase.AI.Tool	A helper tool that the model may use when generating responses.
Firebase.AI.ToolConfig	Tool configuration for any Tool specified in the request.
Firebase.AI.Transcription	A transcription of the audio sent in a live session.
Firebase.AI.UrlContext	A tool that allows you to provide additional context to the models in the form of public web URLs.
Firebase.AI.UrlContextMetadata	Metadata related to the UrlContext tool.
Firebase.AI.UrlMetadata	Metadata for a single URL retrieved by the UrlContext tool.
Firebase.AI.UsageMetadata	Token usage metadata for processing the generate content request.
Firebase.AI.WebGroundingChunk	A grounding chunk sourced from the web.

Interfaces
Firebase.AI.IImagenImage	An image generated by Imagen.
Firebase.AI.ILiveSessionMessage	Represents a message received from a live session.

Enumerations

BlockReason

 BlockReason

A type describing possible reasons to block a prompt.

Properties
Blocklist	The prompt was blocked because it contained terms from the terminology blocklist.
Other	All other block reasons.
ProhibitedContent	The prompt was blocked due to prohibited content.
Safety	The prompt was blocked because it was deemed unsafe.
Unknown	A new and not yet supported value.

ContentModality

 ContentModality

Content part modality.

Properties
Audio	Audio.
Document	Document, e.g. PDF.
Image	Image.
Text	Plain text.
Unknown	A new and not yet supported value.
Video	Video.

FinishReason

 FinishReason

Represents the reason why the model stopped generating content.

Properties
Blocklist	Token generation was stopped because the response contained forbidden terms.
MalformedFunctionCall	Token generation was stopped because the function call generated by the model was invalid.
MaxTokens	The maximum number of tokens as specified in the request was reached.
Other	All other reasons that stopped token generation.
ProhibitedContent	Token generation was stopped because the response contained potentially prohibited content.
Recitation	The token generation was stopped because the response was flagged for unauthorized citations.
SPII	Token generation was stopped because of Sensitive Personally Identifiable Information (SPII).
Safety	The token generation was stopped because the response was flagged for safety reasons.
Stop	Natural stop point of the model or provided stop sequence.
Unknown	A new and not yet supported value.

HarmCategory

 HarmCategory

Categories describing the potential harm a piece of content may pose.

Properties
CivicIntegrity	Content that may be used to harm civic integrity.
DangerousContent	Promotes or enables access to harmful goods, services, or activities.
Harassment	Harassment content.
HateSpeech	Negative or harmful comments targeting identity and/or protected attributes.
SexuallyExplicit	Contains references to sexual acts or other lewd content.
Unknown	A new and not yet supported value.

ImagenAspectRatio

 ImagenAspectRatio

An aspect ratio for images generated by Imagen.

To specify an aspect ratio for generated images, set AspectRatio in your ImagenGenerationConfig. See the Cloud documentation for more details and examples of the supported aspect ratios.

Properties
Landscape16x9	Widescreen (16:9) aspect ratio. This ratio has replaced Landscape4x3 as the most common aspect ratio for TVs, monitors, and mobile phone screens (landscape). Use this aspect ratio when you want to capture more of the background (for example, scenic landscapes).
Landscape4x3	Fullscreen (4:3) aspect ratio. This aspect ratio is commonly used in media or film. It is also the dimensions of most old (non-widescreen) TVs and medium format cameras. It captures more of the scene horizontally (compared to Square1x1), making it a preferred aspect ratio for photography.
Portrait3x4	Portrait full screen (3:4) aspect ratio. This is the Landscape4x3 aspect ratio rotated 90 degrees. This lets to capture more of the scene vertically compared to the Square1x1 aspect ratio.
Portrait9x16	Portrait widescreen (9:16) aspect ratio. This is the Landscape16x9 aspect ratio rotated 90 degrees. This a relatively new aspect ratio that has been popularized by short form video apps (for example, YouTube shorts). Use this for tall objects with strong vertical orientations such as buildings, trees, waterfalls, or other similar objects.
Square1x1	Square (1:1) aspect ratio. Common uses for this aspect ratio include social media posts.

ResponseModality

 ResponseModality

The response type the model should return with.

Properties
Audio	Public Experimental: Specifies that the model should generate audio data. Use this modality with a LiveGenerationConfig to create audio content based on the provided input or prompts with a LiveGenerativeModel.
Image	Public Experimental: Specifies that the model should generate image data. Use this modality when you want the model to create visual content based on the provided input or prompts. The response might contain one or more generated images. See the image generation documentation for more details. Warning: Image generation using Gemini 2.0 Flash is a Public Experimental feature, which means that it is not subject to any SLA or deprecation policy and could change in backwards-incompatible ways.
Text	Specifies that the model should generate textual content. Use this modality when you need the model to produce written language, such as answers to questions, summaries, creative writing, code snippets, or structured data formats like JSON.