ai package

The Firebase AI Web SDK.

Functions

Classes

Interfaces

Variables

Type Aliases

function(app, ...)

getAI(app, options)

Returns the default AI instance that is associated with the provided FirebaseApp. If no instance exists, initializes a new instance with the default settings.

Signature:

export declare function getAI(app?: FirebaseApp, options?: AIOptions): AI;

Parameters

Returns:

AI

The default AI instance for the given FirebaseApp.

Example 1

const ai = getAI(app);

Example 2

// Get an AI instance configured to use the Gemini Developer API (via Google AI).
const ai = getAI(app, { backend: new GoogleAIBackend() });

Example 3

// Get an AI instance configured to use the Vertex AI Gemini API.
const ai = getAI(app, { backend: new VertexAIBackend() });

function(ai, ...)

getGenerativeModel(ai, modelParams, requestOptions)

Returns a GenerativeModel class with methods for inference and other functionality.

Signature:

export declare function getGenerativeModel(ai: AI, modelParams: ModelParams, requestOptions?: RequestOptions): GenerativeModel;

Parameters

Returns:

GenerativeModel

getImagenModel(ai, modelParams, requestOptions)

This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

Returns an ImagenModel class with methods for using Imagen.

Only Imagen 3 models (named imagen-3.0-*) are supported.

Signature:

export declare function getImagenModel(ai: AI, modelParams: ImagenModelParams, requestOptions?: RequestOptions): ImagenModel;

Parameters

Returns:

ImagenModel

Exceptions

If the apiKey or projectId fields are missing in your Firebase config.

AIErrorCode

Standardized error codes that AIError can have.

Signature:

AIErrorCode: {
    readonly ERROR: "error";
    readonly REQUEST_ERROR: "request-error";
    readonly RESPONSE_ERROR: "response-error";
    readonly FETCH_ERROR: "fetch-error";
    readonly INVALID_CONTENT: "invalid-content";
    readonly API_NOT_ENABLED: "api-not-enabled";
    readonly INVALID_SCHEMA: "invalid-schema";
    readonly NO_API_KEY: "no-api-key";
    readonly NO_APP_ID: "no-app-id";
    readonly NO_MODEL: "no-model";
    readonly NO_PROJECT_ID: "no-project-id";
    readonly PARSE_FAILED: "parse-failed";
    readonly UNSUPPORTED: "unsupported";
}

BackendType

An enum-like object containing constants that represent the supported backends for the Firebase AI SDK. This determines which backend service (Vertex AI Gemini API or Gemini Developer API) the SDK will communicate with.

These values are assigned to the backendType property within the specific backend configuration objects (GoogleAIBackend or VertexAIBackend) to identify which service to target.

Signature:

BackendType: {
    readonly VERTEX_AI: "VERTEX_AI";
    readonly GOOGLE_AI: "GOOGLE_AI";
}

BlockReason

Reason that a prompt was blocked.

Signature:

BlockReason: {
    readonly SAFETY: "SAFETY";
    readonly OTHER: "OTHER";
    readonly BLOCKLIST: "BLOCKLIST";
    readonly PROHIBITED_CONTENT: "PROHIBITED_CONTENT";
}

FinishReason

Reason that a candidate finished.

Signature:

FinishReason: {
    readonly STOP: "STOP";
    readonly MAX_TOKENS: "MAX_TOKENS";
    readonly SAFETY: "SAFETY";
    readonly RECITATION: "RECITATION";
    readonly OTHER: "OTHER";
    readonly BLOCKLIST: "BLOCKLIST";
    readonly PROHIBITED_CONTENT: "PROHIBITED_CONTENT";
    readonly SPII: "SPII";
    readonly MALFORMED_FUNCTION_CALL: "MALFORMED_FUNCTION_CALL";
}

FunctionCallingMode

Signature:

FunctionCallingMode: {
    readonly AUTO: "AUTO";
    readonly ANY: "ANY";
    readonly NONE: "NONE";
}

HarmBlockMethod

This property is not supported in the Gemini Developer API (GoogleAIBackend).

Signature:

HarmBlockMethod: {
    readonly SEVERITY: "SEVERITY";
    readonly PROBABILITY: "PROBABILITY";
}

HarmBlockThreshold

Threshold above which a prompt or candidate will be blocked.

Signature:

HarmBlockThreshold: {
    readonly BLOCK_LOW_AND_ABOVE: "BLOCK_LOW_AND_ABOVE";
    readonly BLOCK_MEDIUM_AND_ABOVE: "BLOCK_MEDIUM_AND_ABOVE";
    readonly BLOCK_ONLY_HIGH: "BLOCK_ONLY_HIGH";
    readonly BLOCK_NONE: "BLOCK_NONE";
    readonly OFF: "OFF";
}

HarmCategory

Harm categories that would cause prompts or candidates to be blocked.

Signature:

HarmCategory: {
    readonly HARM_CATEGORY_HATE_SPEECH: "HARM_CATEGORY_HATE_SPEECH";
    readonly HARM_CATEGORY_SEXUALLY_EXPLICIT: "HARM_CATEGORY_SEXUALLY_EXPLICIT";
    readonly HARM_CATEGORY_HARASSMENT: "HARM_CATEGORY_HARASSMENT";
    readonly HARM_CATEGORY_DANGEROUS_CONTENT: "HARM_CATEGORY_DANGEROUS_CONTENT";
}

HarmProbability

Probability that a prompt or candidate matches a harm category.

Signature:

HarmProbability: {
    readonly NEGLIGIBLE: "NEGLIGIBLE";
    readonly LOW: "LOW";
    readonly MEDIUM: "MEDIUM";
    readonly HIGH: "HIGH";
}

HarmSeverity

Harm severity levels.

Signature:

HarmSeverity: {
    readonly HARM_SEVERITY_NEGLIGIBLE: "HARM_SEVERITY_NEGLIGIBLE";
    readonly HARM_SEVERITY_LOW: "HARM_SEVERITY_LOW";
    readonly HARM_SEVERITY_MEDIUM: "HARM_SEVERITY_MEDIUM";
    readonly HARM_SEVERITY_HIGH: "HARM_SEVERITY_HIGH";
    readonly HARM_SEVERITY_UNSUPPORTED: "HARM_SEVERITY_UNSUPPORTED";
}

ImagenAspectRatio

This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

Aspect ratios for Imagen images.

To specify an aspect ratio for generated images, set the aspectRatio property in your ImagenGenerationConfig.

See the documentation for more details and examples of the supported aspect ratios.

Signature:

ImagenAspectRatio: {
    readonly SQUARE: "1:1";
    readonly LANDSCAPE_3x4: "3:4";
    readonly PORTRAIT_4x3: "4:3";
    readonly LANDSCAPE_16x9: "16:9";
    readonly PORTRAIT_9x16: "9:16";
}

ImagenPersonFilterLevel

This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

A filter level controlling whether generation of images containing people or faces is allowed.

See the personGeneration documentation for more details.

Signature:

ImagenPersonFilterLevel: {
    readonly BLOCK_ALL: "dont_allow";
    readonly ALLOW_ADULT: "allow_adult";
    readonly ALLOW_ALL: "allow_all";
}

ImagenSafetyFilterLevel

This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

A filter level controlling how aggressively to filter sensitive content.

Text prompts provided as inputs and images (generated or uploaded) through Imagen on Vertex AI are assessed against a list of safety filters, which include 'harmful categories' (for example, violence, sexual, derogatory, and toxic). This filter level controls how aggressively to filter out potentially harmful content from responses. See the documentation and the Responsible AI and usage guidelines for more details.

Signature:

ImagenSafetyFilterLevel: {
    readonly BLOCK_LOW_AND_ABOVE: "block_low_and_above";
    readonly BLOCK_MEDIUM_AND_ABOVE: "block_medium_and_above";
    readonly BLOCK_ONLY_HIGH: "block_only_high";
    readonly BLOCK_NONE: "block_none";
}

Modality

Content part modality.

Signature:

Modality: {
    readonly MODALITY_UNSPECIFIED: "MODALITY_UNSPECIFIED";
    readonly TEXT: "TEXT";
    readonly IMAGE: "IMAGE";
    readonly VIDEO: "VIDEO";
    readonly AUDIO: "AUDIO";
    readonly DOCUMENT: "DOCUMENT";
}

POSSIBLE_ROLES

Possible roles.

Signature:

POSSIBLE_ROLES: readonly ["user", "model", "function", "system"]

ResponseModality

This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

Generation modalities to be returned in generation responses.

Signature:

ResponseModality: {
    readonly TEXT: "TEXT";
    readonly IMAGE: "IMAGE";
}

SchemaType

Contains the list of OpenAPI data types as defined by the OpenAPI specification

Signature:

SchemaType: {
    readonly STRING: "string";
    readonly NUMBER: "number";
    readonly INTEGER: "integer";
    readonly BOOLEAN: "boolean";
    readonly ARRAY: "array";
    readonly OBJECT: "object";
}

AIErrorCode

Standardized error codes that AIError can have.

Signature:

export type AIErrorCode = (typeof AIErrorCode)[keyof typeof AIErrorCode];

BackendType

Type alias representing valid backend types. It can be either 'VERTEX_AI' or 'GOOGLE_AI'.

Signature:

export type BackendType = (typeof BackendType)[keyof typeof BackendType];

BlockReason

Reason that a prompt was blocked.

Signature:

export type BlockReason = (typeof BlockReason)[keyof typeof BlockReason];

FinishReason

Reason that a candidate finished.

Signature:

export type FinishReason = (typeof FinishReason)[keyof typeof FinishReason];

FunctionCallingMode

Signature:

export type FunctionCallingMode = (typeof FunctionCallingMode)[keyof typeof FunctionCallingMode];

HarmBlockMethod

This property is not supported in the Gemini Developer API (GoogleAIBackend).

Signature:

export type HarmBlockMethod = (typeof HarmBlockMethod)[keyof typeof HarmBlockMethod];

HarmBlockThreshold

Threshold above which a prompt or candidate will be blocked.

Signature:

export type HarmBlockThreshold = (typeof HarmBlockThreshold)[keyof typeof HarmBlockThreshold];

HarmCategory

Harm categories that would cause prompts or candidates to be blocked.

Signature:

export type HarmCategory = (typeof HarmCategory)[keyof typeof HarmCategory];

HarmProbability

Probability that a prompt or candidate matches a harm category.

Signature:

export type HarmProbability = (typeof HarmProbability)[keyof typeof HarmProbability];

HarmSeverity

Harm severity levels.

Signature:

export type HarmSeverity = (typeof HarmSeverity)[keyof typeof HarmSeverity];

ImagenAspectRatio

This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

Aspect ratios for Imagen images.

To specify an aspect ratio for generated images, set the aspectRatio property in your ImagenGenerationConfig.

See the the documentation for more details and examples of the supported aspect ratios.

Signature:

export type ImagenAspectRatio = (typeof ImagenAspectRatio)[keyof typeof ImagenAspectRatio];

ImagenPersonFilterLevel

This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

A filter level controlling whether generation of images containing people or faces is allowed.

See the personGeneration documentation for more details.

Signature:

export type ImagenPersonFilterLevel = (typeof ImagenPersonFilterLevel)[keyof typeof ImagenPersonFilterLevel];

ImagenSafetyFilterLevel

This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

A filter level controlling how aggressively to filter sensitive content.

Text prompts provided as inputs and images (generated or uploaded) through Imagen on Vertex AI are assessed against a list of safety filters, which include 'harmful categories' (for example, violence, sexual, derogatory, and toxic). This filter level controls how aggressively to filter out potentially harmful content from responses. See the documentation and the Responsible AI and usage guidelines for more details.

Signature:

export type ImagenSafetyFilterLevel = (typeof ImagenSafetyFilterLevel)[keyof typeof ImagenSafetyFilterLevel];

Modality

Content part modality.

Signature:

export type Modality = (typeof Modality)[keyof typeof Modality];

Part

Content part - includes text, image/video, or function call/response part types.

Signature:

export type Part = TextPart | InlineDataPart | FunctionCallPart | FunctionResponsePart | FileDataPart;

ResponseModality

This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

Generation modalities to be returned in generation responses.

Signature:

export type ResponseModality = (typeof ResponseModality)[keyof typeof ResponseModality];

Role

Role is the producer of the content.

Signature:

export type Role = (typeof POSSIBLE_ROLES)[number];

SchemaType

Contains the list of OpenAPI data types as defined by the OpenAPI specification

Signature:

export type SchemaType = (typeof SchemaType)[keyof typeof SchemaType];

Tool

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

Signature:

export type Tool = FunctionDeclarationsTool | GoogleSearchTool;

TypedSchema

A type that includes all specific Schema types.

Signature:

export type TypedSchema = IntegerSchema | NumberSchema | StringSchema | BooleanSchema | ObjectSchema | ArraySchema | AnyOfSchema;