@google/genai 1.21.0 → 1.23.0

package/dist/node/node.d.ts

@@ -5,8 +5,7 @@ import { GoogleAuthOptions } from 'google-auth-library';
 /** Marks the end of user activity.
 
  This can only be sent if automatic (i.e. server-side) activity detection is
- disabled.
- */
+ disabled. */
 export declare interface ActivityEnd {
 }
 
@@ -29,8 +28,7 @@ export declare enum ActivityHandling {
 /** Marks the start of user activity.
 
  This can only be sent if automatic (i.e. server-side) activity detection is
- disabled.
- */
+ disabled. */
 export declare interface ActivityStart {
 }
 
@@ -1069,6 +1067,18 @@ export declare interface CodeExecutionResult {
     output?: string;
 }
 
+/** Tool to support computer use. */
+export declare interface ComputerUse {
+    /** Required. The environment being operated. */
+    environment?: Environment;
+    /** By default, predefined functions are included in the final model call.
+     Some of them can be explicitly excluded from being automatically included.
+     This can serve two purposes:
+     1. Using a more restricted / different action space.
+     2. Improving the definitions / instructions of predefined functions. */
+    excludedPredefinedFunctions?: string[];
+}
+
 /** Optional parameters for computing tokens. */
 export declare interface ComputeTokensConfig {
     /** Used to override HTTP request options. */
@@ -1141,8 +1151,7 @@ export declare type ContentListUnion = Content | Content[] | PartUnion | PartUni
 
  A content reference image represents a subject to reference (ex. person,
  product, animal) provided by the user. It can optionally be provided in
- addition to a style reference image (ex. background, style reference).
- */
+ addition to a style reference image (ex. background, style reference). */
 export declare class ContentReferenceImage {
     /** The reference image for the editing operation. */
     referenceImage?: Image_2;
@@ -1182,8 +1191,7 @@ export declare interface ControlReferenceConfig {
  enable_control_image_computation field in the config should be set to True.
 
  A control image is an image that represents a sketch image of areas for the
- model to fill in based on the prompt.
- */
+ model to fill in based on the prompt. */
 export declare class ControlReferenceImage {
     /** The reference image for the editing operation. */
     referenceImage?: Image_2;
@@ -1378,8 +1386,7 @@ export declare interface CreateCachedContentParameters {
 /** Parameters for initializing a new chat session.
 
  These parameters are used when creating a chat session with the
- `chats.create()` method.
- */
+ `chats.create()` method. */
 export declare interface CreateChatParameters {
     /** The name of the model to use for the chat session.
 
@@ -1463,6 +1470,16 @@ export declare class CreateFileResponse {
     sdkHttpResponse?: HttpResponse;
 }
 
+/**
+ * Creates a `FunctionResponsePart` object from a `base64` encoded `string`.
+ */
+export declare function createFunctionResponsePartFromBase64(data: string, mimeType: string): FunctionResponsePart;
+
+/**
+ * Creates a `FunctionResponsePart` object from a `URI` string.
+ */
+export declare function createFunctionResponsePartFromUri(uri: string, mimeType: string): FunctionResponsePart;
+
 /**
  * Creates a `Content` object with a model role from a `PartListUnion` object or `string`.
  */
@@ -1491,7 +1508,7 @@ export declare function createPartFromFunctionCall(name: string, args: Record<st
 /**
  * Creates a `Part` object from a `FunctionResponse` object.
  */
-export declare function createPartFromFunctionResponse(id: string, name: string, response: Record<string, unknown>): Part;
+export declare function createPartFromFunctionResponse(id: string, name: string, response: Record<string, unknown>, parts?: FunctionResponsePart[]): Part;
 
 /**
  * Creates a `Part` object from a `text` string.
@@ -1837,6 +1854,8 @@ export declare interface EditImageConfig {
     outputCompressionQuality?: number;
     /** Whether to add a watermark to the generated images. */
     addWatermark?: boolean;
+    /** User specified labels to track billing usage. */
+    labels?: Record<string, string>;
     /** Describes the editing mode for the request. */
     editMode?: EditMode;
     /** The number of sampling steps. A higher value has better image
@@ -2290,8 +2309,7 @@ export declare interface FileStatus {
 
 /** Output only. The reason why the model stopped generating tokens.
 
- If empty, the model has not stopped generating the tokens.
- */
+ If empty, the model has not stopped generating the tokens. */
 export declare enum FinishReason {
     /**
      * The finish reason is unspecified.
@@ -2344,7 +2362,15 @@ export declare enum FinishReason {
     /**
      * The tool call generated by the model is invalid.
      */
-    UNEXPECTED_TOOL_CALL = "UNEXPECTED_TOOL_CALL"
+    UNEXPECTED_TOOL_CALL = "UNEXPECTED_TOOL_CALL",
+    /**
+     * Image generation stopped because the generated images have prohibited content.
+     */
+    IMAGE_PROHIBITED_CONTENT = "IMAGE_PROHIBITED_CONTENT",
+    /**
+     * The model was expected to generate an image, but none was generated.
+     */
+    NO_IMAGE = "NO_IMAGE"
 }
 
 /** A function call. */
@@ -2393,8 +2419,7 @@ export declare enum FunctionCallingConfigMode {
 /** Defines a function that the model can generate JSON inputs for.
 
  The inputs are based on `OpenAPI 3.0 specifications
- <https://spec.openapis.org/oas/v3.0.3>`_.
- */
+ <https://spec.openapis.org/oas/v3.0.3>`_. */
 export declare interface FunctionDeclaration {
     /** Defines the function behavior. */
     behavior?: Behavior;
@@ -2432,8 +2457,7 @@ export declare class FunctionResponse {
 /** Raw media bytes for function response.
 
  Text should not be sent as raw bytes, use the FunctionResponse.response
- field.
- */
+ field. */
 export declare class FunctionResponseBlob {
     /** Required. The IANA standard MIME type of the source data. */
     mimeType?: string;
@@ -2458,8 +2482,7 @@ export declare class FunctionResponseFileData {
 
  A `FunctionResponsePart` must have a fixed IANA MIME type identifying the
  type and subtype of the media if the `inline_data` field is filled with raw
- bytes.
- */
+ bytes. */
 export declare class FunctionResponsePart {
     /** Optional. Inline media bytes. */
     inlineData?: FunctionResponseBlob;
@@ -2506,8 +2529,7 @@ export declare interface GeminiPreferenceExampleCompletion {
 /** Optional model configuration parameters.
 
  For more information, see `Content generation parameters
- <https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/content-generation-parameters>`_.
- */
+ <https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/content-generation-parameters>`_. */
 export declare interface GenerateContentConfig {
     /** Used to override HTTP request options. */
     httpOptions?: HttpOptions;
@@ -2650,6 +2672,9 @@ export declare interface GenerateContentConfig {
     /** The thinking features configuration.
      */
     thinkingConfig?: ThinkingConfig;
+    /** The image generation configuration.
+     */
+    imageConfig?: ImageConfig;
 }
 
 /** Config for models.generate_content parameters. */
@@ -2926,6 +2951,8 @@ export declare interface GenerateImagesConfig {
     outputCompressionQuality?: number;
     /** Whether to add a watermark to the generated images. */
     addWatermark?: boolean;
+    /** User specified labels to track billing usage. */
+    labels?: Record<string, string>;
     /** The size of the largest dimension of the generated image.
      Supported sizes are 1K and 2K (not supported for Imagen 3 models). */
     imageSize?: string;
@@ -3783,6 +3810,13 @@ declare interface Image_2 {
 }
 export { Image_2 as Image }
 
+/** The image generation configuration to be used in GenerateContentConfig. */
+export declare interface ImageConfig {
+    /** Aspect ratio of the generated images. Supported values are
+     "1:1", "2:3", "3:2", "3:4", "4:3", "9:16", "16:9", and "21:9". */
+    aspectRatio?: string;
+}
+
 /** Enum that specifies the language of the text in the prompt. */
 export declare enum ImagePromptLanguage {
     /**
@@ -3857,8 +3891,7 @@ export declare class InlinedResponse {
  The start time must be less than or equal to the end time.
  When the start equals the end time, the interval is an empty interval.
  (matches no time)
- When both start and end are unspecified, the interval matches any time.
- */
+ When both start and end are unspecified, the interval matches any time. */
 export declare interface Interval {
     /** The start time of the interval. */
     startTime?: string;
@@ -3945,8 +3978,7 @@ export declare enum Language {
  This is expressed as a pair of doubles to represent degrees latitude and
  degrees longitude. Unless specified otherwise, this object must conform to the
  <a href="https://en.wikipedia.org/wiki/World_Geodetic_System#1984_version">
- WGS84 standard</a>. Values must be within normalized ranges.
- */
+ WGS84 standard</a>. Values must be within normalized ranges. */
 export declare interface LatLng {
     /** The latitude in degrees. It must be in the range [-90.0, +90.0]. */
     latitude?: number;
@@ -4187,8 +4219,7 @@ export declare interface LiveCallbacks {
  All the content here will unconditionally be appended to the conversation
  history and used as part of the prompt to the model to generate content.
 
- A message here will interrupt any current model generation.
- */
+ A message here will interrupt any current model generation. */
 export declare interface LiveClientContent {
     /** The content appended to the current conversation with the model.
 
@@ -4228,8 +4259,7 @@ export declare interface LiveClientMessage {
  - Even before the end of turn, the data is processed incrementally
  to optimize for a fast start of the response from the model.
  - Is always assumed to be the user's input (cannot be used to populate
- conversation history).
- */
+ conversation history). */
 export declare interface LiveClientRealtimeInput {
     /** Inlined bytes data for media input. */
     mediaChunks?: Blob_2[];
@@ -4306,8 +4336,7 @@ export declare interface LiveClientSetup {
  Note that in the unary and server-streaming GenerateContent APIs function
  calling happens by exchanging the `Content` parts, while in the bidi
  GenerateContent APIs function calling happens over this dedicated set of
- messages.
- */
+ messages. */
 export declare class LiveClientToolResponse {
     /** The response to the function calls. */
     functionResponses?: FunctionResponse[];
@@ -4362,6 +4391,11 @@ export declare interface LiveConnectConfig {
     /** The speech generation configuration.
      */
     speechConfig?: SpeechConfig;
+    /** Config for thinking features.
+     An error will be returned if this field is set for models that don't
+     support thinking.
+     */
+    thinkingConfig?: ThinkingConfig;
     /** If enabled, the model will detect emotions and adapt its responses accordingly. */
     enableAffectiveDialog?: boolean;
     /** The user provided system instructions for the model.
@@ -4582,8 +4616,7 @@ export declare enum LiveMusicPlaybackControl {
 /** Server update generated by the model in response to client messages.
 
  Content is generated as quickly as possible, and not in real time.
- Clients may choose to buffer and play it out in real time.
- */
+ Clients may choose to buffer and play it out in real time. */
 export declare interface LiveMusicServerContent {
     /** The audio chunks that the model has generated. */
     audioChunks?: AudioChunk[];
@@ -4745,8 +4778,7 @@ export declare class LiveSendToolResponseParameters {
 /** Incremental server update generated by the model in response to client messages.
 
  Content is generated as quickly as possible, and not in real time. Clients
- may choose to buffer and play it out in real time.
- */
+ may choose to buffer and play it out in real time. */
 export declare interface LiveServerContent {
     /** The content that the model has generated as part of the current conversation with the user. */
     modelTurn?: Content;
@@ -4827,8 +4859,7 @@ export declare class LiveServerMessage {
 
 /** Update of the session resumption state.
 
- Only sent if `session_resumption` was set in the connection config.
- */
+ Only sent if `session_resumption` was set in the connection config. */
 export declare interface LiveServerSessionResumptionUpdate {
     /** New handle that represents state that can be resumed. Empty if `resumable`=false. */
     newHandle?: string;
@@ -4858,8 +4889,7 @@ export declare interface LiveServerToolCall {
 
  If there were side-effects to those tool calls, clients may attempt to undo
  the tool calls. This message occurs only in cases where the clients interrupt
- server turns.
- */
+ server turns. */
 export declare interface LiveServerToolCallCancellation {
     /** The ids of the tool calls to be cancelled. */
     ids?: string[];
@@ -4910,8 +4940,7 @@ export declare interface MaskReferenceConfig {
 
  A mask image is an image whose non-zero values indicate where to edit the base
  image. If the user provides a mask image, the mask must be in the same
- dimensions as the raw image.
- */
+ dimensions as the raw image. */
 export declare class MaskReferenceImage {
     /** The reference image for the editing operation. */
     referenceImage?: Image_2;
@@ -5675,8 +5704,7 @@ export declare class Pager<T> implements AsyncIterable<T> {
 
  Exactly one field within a Part should be set, representing the specific type
  of content being conveyed. Using multiple fields within the same `Part`
- instance is considered invalid.
- */
+ instance is considered invalid. */
 export declare interface Part {
     /** Metadata for a given video. */
     videoMetadata?: VideoMetadata;
@@ -5851,8 +5879,7 @@ export declare interface RagRetrievalConfigRankingRankService {
 
  A raw reference image represents the base image to edit, provided by the user.
  It can optionally be provided in addition to a mask reference image or
- a style reference image.
- */
+ a style reference image. */
 export declare class RawReferenceImage {
     /** The reference image for the editing operation. */
     referenceImage?: Image_2;
@@ -5867,8 +5894,7 @@ export declare class RawReferenceImage {
 /** Marks the end of user activity.
 
  This can only be sent if automatic (i.e. server-side) activity detection is
- disabled.
- */
+ disabled. */
 export declare interface RealtimeInputConfig {
     /** If not set, automatic activity detection is enabled by default. If automatic voice detection is disabled, the client must send activity signals. */
     automaticActivityDetection?: AutomaticActivityDetection;
@@ -5912,6 +5938,8 @@ export declare interface RecontextImageConfig {
     outputCompressionQuality?: number;
     /** Whether to use the prompt rewriting logic. */
     enhancePrompt?: boolean;
+    /** User specified labels to track billing usage. */
+    labels?: Record<string, string>;
 }
 
 /** The parameters for recontextualizing an image. */
@@ -6125,8 +6153,7 @@ export declare enum Scale {
 
  Represents a select subset of an [OpenAPI 3.0 schema
  object](https://spec.openapis.org/oas/v3.0.3#schema-object). More fields may
- be added in the future as needed.
- */
+ be added in the future as needed. */
 export declare interface Schema {
     /** Optional. The value should be validated against any (one or more) of the subschemas in the list. */
     anyOf?: Schema[];
@@ -6231,6 +6258,8 @@ export declare interface SegmentImageConfig {
      can be set to a decimal value between 0 and 255 non-inclusive.
      Set to -1 for no binary color thresholding. */
     binaryColorThreshold?: number;
+    /** User specified labels to track billing usage. */
+    labels?: Record<string, string>;
 }
 
 /** The parameters for segmenting an image. */
@@ -6274,8 +6303,7 @@ export declare enum SegmentMode {
 
 /** Parameters for sending a message within a chat session.
 
- These parameters are used with the `chat.sendMessage()` method.
- */
+ These parameters are used with the `chat.sendMessage()` method. */
 export declare interface SendMessageParameters {
     /** The message to send to the model.
 
@@ -6421,8 +6449,7 @@ export declare class Session {
 /** Configuration of session resumption mechanism.
 
  Included in `LiveConnectConfig.session_resumption`. If included server
- will send `LiveServerSessionResumptionUpdate` messages.
- */
+ will send `LiveServerSessionResumptionUpdate` messages. */
 export declare interface SessionResumptionConfig {
     /** Session resumption handle of previous session (session to restore).
 
@@ -6469,8 +6496,7 @@ export declare class SingleEmbedContentResponse {
  Context window will always be cut at start of USER role turn. System
  instructions and `BidiGenerateContentSetup.prefix_turns` will not be
  subject to the sliding window mechanism, they will always stay at the
- beginning of context window.
- */
+ beginning of context window. */
 export declare interface SlidingWindow {
     /** Session reduction target -- how many tokens we should keep. Window shortening operation has some latency costs, so we should avoid running it on every turn. Should be < trigger_tokens. If not set, trigger_tokens/2 is assumed. */
     targetTokens?: string;
@@ -6530,8 +6556,7 @@ export declare interface StyleReferenceConfig {
  additionally optional config parameters for the style reference image.
 
  A raw reference image can also be provided as a destination for the style to
- be applied to.
- */
+ be applied to. */
 export declare class StyleReferenceImage {
     /** The reference image for the editing operation. */
     referenceImage?: Image_2;
@@ -6559,8 +6584,7 @@ export declare interface SubjectReferenceConfig {
  additionally optional config parameters for the subject reference image.
 
  A raw reference image can also be provided as a destination for the subject to
- be applied to.
- */
+ be applied to. */
 export declare class SubjectReferenceImage {
     /** The reference image for the editing operation. */
     referenceImage?: Image_2;
@@ -6827,7 +6851,7 @@ export declare interface Tool {
     /** Optional. Tool to support the model interacting directly with the
      computer. If enabled, it automatically populates computer-use specific
      Function Declarations. */
-    computerUse?: ToolComputerUse;
+    computerUse?: ComputerUse;
     /** Optional. CodeExecution tool type. Enables the model to execute code as part of generation. */
     codeExecution?: ToolCodeExecution;
 }
@@ -6836,22 +6860,9 @@ export declare interface Tool {
 export declare interface ToolCodeExecution {
 }
 
-/** Tool to support computer use. */
-export declare interface ToolComputerUse {
-    /** Required. The environment being operated. */
-    environment?: Environment;
-    /** By default, predefined functions are included in the final model call.
-     Some of them can be explicitly excluded from being automatically included.
-     This can serve two purposes:
-     1. Using a more restricted / different action space.
-     2. Improving the definitions / instructions of predefined functions. */
-    excludedPredefinedFunctions?: string[];
-}
-
 /** Tool config.
 
- This config is shared for all tools provided in the request.
- */
+ This config is shared for all tools provided in the request. */
 export declare interface ToolConfig {
     /** Optional. Function calling config. */
     functionCallingConfig?: FunctionCallingConfig;
@@ -7002,6 +7013,8 @@ export declare interface TuningJob {
     serviceAccount?: string;
     /** Optional. The display name of the TunedModel. The name can be up to 128 characters long and can consist of any UTF-8 characters. */
     tunedModelDisplayName?: string;
+    /** Tuning Spec for Veo Tuning. */
+    veoTuningSpec?: VeoTuningSpec;
 }
 
 /** Tuning mode. */
@@ -7085,6 +7098,22 @@ declare class Tunings extends BaseModule {
     private tuneMldevInternal;
 }
 
+/** Optional. The tuning task. Either I2V or T2V. */
+export declare enum TuningTask {
+    /**
+     * Default value. This value is unused.
+     */
+    TUNING_TASK_UNSPECIFIED = "TUNING_TASK_UNSPECIFIED",
+    /**
+     * Tuning task for image to video.
+     */
+    TUNING_TASK_I2V = "TUNING_TASK_I2V",
+    /**
+     * Tuning task for text to video.
+     */
+    TUNING_TASK_T2V = "TUNING_TASK_T2V"
+}
+
 export declare interface TuningValidationDataset {
     /** GCS URI of the file containing validation dataset in JSONL format. */
     gcsUri?: string;
@@ -7166,6 +7195,8 @@ export declare enum Type {
 
 declare namespace types {
     export {
+        createFunctionResponsePartFromBase64,
+        createFunctionResponsePartFromUri,
         createPartFromUri,
         createPartFromText,
         createPartFromFunctionCall,
@@ -7195,6 +7226,7 @@ declare namespace types {
         JobState,
         TuningMode,
         AdapterSize,
+        TuningTask,
         FeatureSelectionPreference,
         Behavior,
         DynamicRetrievalConfigMode,
@@ -7253,7 +7285,7 @@ declare namespace types {
         AuthConfig,
         GoogleMaps,
         UrlContext,
-        ToolComputerUse,
+        ComputerUse,
         ApiAuthApiKeyConfig,
         ApiAuth,
         ExternalApiElasticSearchParams,
@@ -7283,6 +7315,7 @@ declare namespace types {
         SpeechConfig,
         AutomaticFunctionCallingConfig,
         ThinkingConfig,
+        ImageConfig,
         GenerationConfigRoutingConfigAutoRoutingMode,
         GenerationConfigRoutingConfigManualRoutingMode,
         GenerationConfigRoutingConfig,
@@ -7405,6 +7438,8 @@ declare namespace types {
         TuningDataStats,
         EncryptionSpec,
         PartnerModelTuningSpec,
+        VeoHyperParameters,
+        VeoTuningSpec,
         TuningJob,
         ListTuningJobsConfig,
         ListTuningJobsParameters,
@@ -7661,8 +7696,7 @@ export declare interface UploadFileParameters {
 
  For more information on this configuration, refer to
  the `Imagen API reference documentation
- <https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/imagen-api>`_.
- */
+ <https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/imagen-api>`_. */
 export declare interface UpscaleImageConfig {
     /** Used to override HTTP request options. */
     httpOptions?: HttpOptions;
@@ -7692,6 +7726,8 @@ export declare interface UpscaleImageConfig {
      output image will have be more different from the input image, but
      with finer details and less noise. */
     imagePreservationFactor?: number;
+    /** User specified labels to track billing usage. */
+    labels?: Record<string, string>;
 }
 
 /** User-facing config UpscaleImageParameters. */
@@ -7782,6 +7818,26 @@ export declare interface UsageMetadata {
     trafficType?: TrafficType;
 }
 
+/** Hyperparameters for Veo. */
+export declare interface VeoHyperParameters {
+    /** Optional. Number of complete passes the model makes over the entire training dataset during training. */
+    epochCount?: string;
+    /** Optional. Multiplier for adjusting the default learning rate. */
+    learningRateMultiplier?: number;
+    /** Optional. The tuning task. Either I2V or T2V. */
+    tuningTask?: TuningTask;
+}
+
+/** Tuning Spec for Veo Model Tuning. */
+export declare interface VeoTuningSpec {
+    /** Optional. Hyperparameters for Veo. */
+    hyperParameters?: VeoHyperParameters;
+    /** Required. Training dataset used for tuning. The dataset can be specified as either a Cloud Storage path to a JSONL file or as the resource name of a Vertex Multimodal Dataset. */
+    trainingDatasetUri?: string;
+    /** Optional. Validation dataset used for tuning. The dataset can be specified as either a Cloud Storage path to a JSONL file or as the resource name of a Vertex Multimodal Dataset. */
+    validationDatasetUri?: string;
+}
+
 /** Retrieve from Vertex AI Search datastore or engine for grounding. datastore and engine are mutually exclusive. See https://cloud.google.com/products/agent-builder */
 export declare interface VertexAISearch {
     /** Specifications that define the specific DataStores to be searched, along with configurations for those data stores. This is only considered for Engines with multiple data stores. It should only be set if engine is used. */