@google/genai 1.0.1 → 1.2.0

package/README.md

@@ -33,7 +33,7 @@ npm install @google/genai
 
 ## Quickstart
 
-The simplest way to get started is to using an API key from
+The simplest way to get started is to use an API key from
 [Google AI Studio](https://aistudio.google.com/apikey):
 
 ```typescript
@@ -130,19 +130,19 @@ const ai = new GoogleGenAI({
 All API features are accessed through an instance of the `GoogleGenAI` classes.
 The submodules bundle together related API methods:
 
-- [`ai.models`](https://googleapis.github.io/js-genai/main/classes/models.Models.html):
+- [`ai.models`](https://googleapis.github.io/js-genai/release_docs/classes/models.Models.html):
   Use `models` to query models (`generateContent`, `generateImages`, ...), or
   examine their metadata.
-- [`ai.caches`](https://googleapis.github.io/js-genai/main/classes/caches.Caches.html):
+- [`ai.caches`](https://googleapis.github.io/js-genai/release_docs/classes/caches.Caches.html):
   Create and manage `caches` to reduce costs when repeatedly using the same
   large prompt prefix.
-- [`ai.chats`](https://googleapis.github.io/js-genai/main/classes/chats.Chats.html):
+- [`ai.chats`](https://googleapis.github.io/js-genai/release_docs/classes/chats.Chats.html):
   Create local stateful `chat` objects to simplify multi turn interactions.
-- [`ai.files`](https://googleapis.github.io/js-genai/main/classes/files.Files.html):
+- [`ai.files`](https://googleapis.github.io/js-genai/release_docs/classes/files.Files.html):
   Upload `files` to the API and reference them in your prompts.
   This reduces bandwidth if you use a file many times, and handles files too
   large to fit inline with your prompt.
-- [`ai.live`](https://googleapis.github.io/js-genai/main/classes/live.Live.html):
+- [`ai.live`](https://googleapis.github.io/js-genai/release_docs/classes/live.Live.html):
   Start a `live` session for real time interaction, allows text + audio + video
   input, and text or audio output.
 

package/dist/genai.d.ts

@@ -1282,15 +1282,15 @@ export declare interface DistillationHyperParameters {
 
 /** Tuning Spec for Distillation. */
 export declare interface DistillationSpec {
-    /** The base teacher model that is being distilled, e.g., "gemini-1.0-pro-002". */
+    /** The base teacher model that is being distilled. See [Supported models](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/tuning#supported_models). */
     baseTeacherModel?: string;
     /** Optional. Hyperparameters for Distillation. */
     hyperParameters?: DistillationHyperParameters;
-    /** Required. A path in a Cloud Storage bucket, which will be treated as the root output directory of the distillation pipeline. It is used by the system to generate the paths of output artifacts. */
+    /** Deprecated. A path in a Cloud Storage bucket, which will be treated as the root output directory of the distillation pipeline. It is used by the system to generate the paths of output artifacts. */
     pipelineRootDirectory?: string;
-    /** The student model that is being tuned, e.g., "google/gemma-2b-1.1-it". */
+    /** The student model that is being tuned, e.g., "google/gemma-2b-1.1-it". Deprecated. Use base_model instead. */
     studentModel?: string;
-    /** Required. Cloud Storage path to file containing training dataset for tuning. The dataset must be formatted as a JSONL file. */
+    /** Deprecated. Cloud Storage path to file containing training dataset for tuning. The dataset must be formatted as a JSONL file. */
     trainingDatasetUri?: string;
     /** The resource name of the Tuned teacher model. Format: `projects/{project}/locations/{location}/models/{model}`. */
     tunedTeacherModelSource?: string;
@@ -1619,6 +1619,8 @@ export { File_2 as File }
 
 /** URI based data. */
 export declare interface FileData {
+    /** Optional. Display name of the file data. Used to provide a label or filename to distinguish file datas. It is not currently used in the Gemini GenerateContent calls. */
+    displayName?: string;
     /** Required. URI. */
     fileUri?: string;
     /** Required. The IANA standard MIME type of the source data. */
@@ -1843,7 +1845,7 @@ export declare interface FunctionCall {
     /** The unique id of the function call. If populated, the client to execute the
      `function_call` and return the response with the matching `id`. */
     id?: string;
-    /** Optional. Required. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. */
+    /** Optional. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details. */
     args?: Record<string, unknown>;
     /** Required. The name of the function to call. Matches [FunctionDeclaration.name]. */
     name?: string;
@@ -2406,6 +2408,8 @@ export declare interface GenerateVideosConfig {
     negativePrompt?: string;
     /** Whether to use the prompt rewriting logic. */
     enhancePrompt?: boolean;
+    /** Whether to generate audio along with the video. */
+    generateAudio?: boolean;
 }
 
 /** A video generation operation. */
@@ -2448,6 +2452,8 @@ export declare class GenerateVideosResponse {
 
 /** Generation config. */
 export declare interface GenerationConfig {
+    /** Optional. Config for model selection. */
+    modelSelectionConfig?: ModelSelectionConfig;
     /** Optional. If enabled, audio timestamp will be included in the request to the model. */
     audioTimestamp?: boolean;
     /** Optional. Number of candidates to generate. */
@@ -2466,16 +2472,22 @@ export declare interface GenerationConfig {
     responseLogprobs?: boolean;
     /** Optional. Output response mimetype of the generated candidate text. Supported mimetype: - `text/plain`: (default) Text output. - `application/json`: JSON response in the candidates. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. This is a preview feature. */
     responseMimeType?: string;
+    /** Optional. The modalities of the response. */
+    responseModalities?: Modality[];
     /** Optional. The `Schema` object allows the definition of input and output data types. These types can be objects, but also primitives and arrays. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema). If set, a compatible response_mime_type must also be set. Compatible mimetypes: `application/json`: Schema for JSON response. */
     responseSchema?: Schema;
     /** Optional. Routing configuration. */
     routingConfig?: GenerationConfigRoutingConfig;
     /** Optional. Seed. */
     seed?: number;
+    /** Optional. The speech generation config. */
+    speechConfig?: SpeechConfig;
     /** Optional. Stop sequences. */
     stopSequences?: string[];
     /** Optional. Controls the randomness of predictions. */
     temperature?: number;
+    /** Optional. Config for thinking features. An error will be returned if this field is set for models that don't support thinking. */
+    thinkingConfig?: GenerationConfigThinkingConfig;
     /** Optional. If specified, top-k sampling will be used. */
     topK?: number;
     /** Optional. If specified, nucleus sampling will be used. */
@@ -2498,10 +2510,18 @@ export declare interface GenerationConfigRoutingConfigAutoRoutingMode {
 
 /** When manual routing is set, the specified model will be used directly. */
 export declare interface GenerationConfigRoutingConfigManualRoutingMode {
-    /** The model name to use. Only the public LLM models are accepted. e.g. 'gemini-1.5-pro-001'. */
+    /** The model name to use. Only the public LLM models are accepted. See [Supported models](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference#supported-models). */
     modelName?: string;
 }
 
+/** Config for thinking features. */
+export declare interface GenerationConfigThinkingConfig {
+    /** Optional. Indicates whether to include thoughts in the response. If true, thoughts are returned only when available. */
+    includeThoughts?: boolean;
+    /** Optional. Indicates the thinking budget in tokens. This is only applied when enable_thinking is true. */
+    thinkingBudget?: number;
+}
+
 /** Optional parameters for caches.get method. */
 export declare interface GetCachedContentConfig {
     /** Used to override HTTP request options. */
@@ -2764,6 +2784,8 @@ export declare interface GroundingChunk {
 
 /** Chunk from context retrieved by the retrieval tools. */
 export declare interface GroundingChunkRetrievedContext {
+    /** Additional context for the RAG retrieval result. This is only populated when using the RAG retrieval tool. */
+    ragChunk?: RagChunk;
     /** Text of the attribution. */
     text?: string;
     /** Title of the attribution. */
@@ -2875,7 +2897,7 @@ export declare enum HarmCategory {
      */
     HARM_CATEGORY_SEXUALLY_EXPLICIT = "HARM_CATEGORY_SEXUALLY_EXPLICIT",
     /**
-     * The harm category is civic integrity.
+     * Deprecated: Election filter is not longer supported. The harm category is civic integrity.
      */
     HARM_CATEGORY_CIVIC_INTEGRITY = "HARM_CATEGORY_CIVIC_INTEGRITY"
 }
@@ -3675,8 +3697,6 @@ export declare interface LiveMusicGenerationConfig {
     muteDrums?: boolean;
     /** Whether the audio output should contain only bass and drums. */
     onlyBassAndDrums?: boolean;
-    /** The mode of music generation. Default mode is QUALITY. */
-    musicGenerationMode?: MusicGenerationMode;
 }
 
 /** The playback control signal to apply to the music generation. */
@@ -4126,7 +4146,7 @@ export declare enum Modality {
      */
     IMAGE = "IMAGE",
     /**
-     * Indicates the model should return images.
+     * Indicates the model should return audio.
      */
     AUDIO = "AUDIO"
 }
@@ -4500,24 +4520,6 @@ export declare interface MultiSpeakerVoiceConfig {
     speakerVoiceConfigs?: SpeakerVoiceConfig[];
 }
 
-/** The mode of music generation. */
-export declare enum MusicGenerationMode {
-    /**
-     * This value is unused.
-     */
-    MUSIC_GENERATION_MODE_UNSPECIFIED = "MUSIC_GENERATION_MODE_UNSPECIFIED",
-    /**
-     * Steer text prompts to regions of latent space with higher quality
-     music.
-     */
-    QUALITY = "QUALITY",
-    /**
-     * Steer text prompts to regions of latent space with a larger diversity
-     of music.
-     */
-    DIVERSITY = "DIVERSITY"
-}
-
 /** A long-running operation. */
 export declare interface Operation {
     /** The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`. */
@@ -4717,12 +4719,12 @@ export declare interface Part {
     thought?: boolean;
     /** Optional. Inlined bytes data. */
     inlineData?: Blob_2;
+    /** Optional. URI based data. */
+    fileData?: FileData;
     /** Optional. Result of executing the [ExecutableCode]. */
     codeExecutionResult?: CodeExecutionResult;
     /** Optional. Code generated by the model that is meant to be executed. */
     executableCode?: ExecutableCode;
-    /** Optional. URI based data. */
-    fileData?: FileData;
     /** Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values. */
     functionCall?: FunctionCall;
     /** Optional. The result output of a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function call. It is used as context to the model. */
@@ -4766,6 +4768,22 @@ export declare interface ProactivityConfig {
     proactiveAudio?: boolean;
 }
 
+/** A RagChunk includes the content of a chunk of a RagFile, and associated metadata. */
+export declare interface RagChunk {
+    /** If populated, represents where the chunk starts and ends in the document. */
+    pageSpan?: RagChunkPageSpan;
+    /** The content of the chunk. */
+    text?: string;
+}
+
+/** Represents where the chunk starts and ends in the document. */
+export declare interface RagChunkPageSpan {
+    /** Page where chunk starts in the document. Inclusive. 1-indexed. */
+    firstPage?: number;
+    /** Page where chunk ends in the document. Inclusive. 1-indexed. */
+    lastPage?: number;
+}
+
 /** Specifies the context retrieval config. */
 export declare interface RagRetrievalConfig {
     /** Optional. Config for filters. */
@@ -4804,7 +4822,7 @@ export declare interface RagRetrievalConfigRanking {
 
 /** Config for LlmRanker. */
 export declare interface RagRetrievalConfigRankingLlmRanker {
-    /** Optional. The model name used for ranking. Format: `gemini-1.5-pro` */
+    /** Optional. The model name used for ranking. See [Supported models](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference#supported-models). */
     modelName?: string;
 }
 
@@ -4890,6 +4908,8 @@ export declare interface Retrieval {
 export declare interface RetrievalConfig {
     /** Optional. The location of the user. */
     latLng?: LatLng;
+    /** The language code of the user. */
+    languageCode?: string;
 }
 
 /** Metadata related to retrieval in the grounding flow. */
@@ -5002,7 +5022,12 @@ export declare enum Scale {
     B_MAJOR_A_FLAT_MINOR = "B_MAJOR_A_FLAT_MINOR"
 }
 
-/** Schema is used to define the format of input/output data. 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. */
+/** Schema is used to define the format of input/output data.
+
+ 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.
+ */
 export declare interface Schema {
     /** Optional. The value should be validated against any (one or more) of the subschemas in the list. */
     anyOf?: Schema[];
@@ -5415,15 +5440,17 @@ export declare interface SupervisedTuningDatasetDistributionDatasetBucket {
 
 /** Tuning data statistics for Supervised Tuning. */
 export declare interface SupervisedTuningDataStats {
+    /** Output only. For each index in `truncated_example_indices`, the user-facing reason why the example was dropped. */
+    droppedExampleReasons?: string[];
     /** Output only. Number of billable characters in the tuning dataset. */
     totalBillableCharacterCount?: string;
     /** Output only. Number of billable tokens in the tuning dataset. */
     totalBillableTokenCount?: string;
-    /** The number of examples in the dataset that have been truncated by any amount. */
+    /** Output only. The number of examples in the dataset that have been dropped. An example can be dropped for reasons including: too many tokens, contains an invalid image, contains too many images, etc. */
     totalTruncatedExampleCount?: string;
     /** Output only. Number of tuning characters in the tuning dataset. */
     totalTuningCharacterCount?: string;
-    /** A partial sample of the indices (starting from 1) of the truncated examples. */
+    /** Output only. A partial sample of the indices (starting from 1) of the dropped examples. */
     truncatedExampleIndices?: string[];
     /** Output only. Number of examples in the tuning dataset. */
     tuningDatasetExampleCount?: string;
@@ -5441,14 +5468,14 @@ export declare interface SupervisedTuningDataStats {
 
 /** Tuning Spec for Supervised Tuning for first party models. */
 export declare interface SupervisedTuningSpec {
+    /** Optional. If set to true, disable intermediate checkpoints for SFT and only the last checkpoint will be exported. Otherwise, enable intermediate checkpoints for SFT. Default is false. */
+    exportLastCheckpointOnly?: boolean;
     /** Optional. Hyperparameters for SFT. */
     hyperParameters?: SupervisedHyperParameters;
     /** Required. Cloud Storage path to file containing training dataset for tuning. The dataset must be formatted as a JSONL file. */
     trainingDatasetUri?: string;
     /** Optional. Cloud Storage path to file containing validation dataset for tuning. The dataset must be formatted as a JSONL file. */
     validationDatasetUri?: string;
-    /** Optional. If set to true, disable intermediate checkpoints for SFT and only the last checkpoint will be exported. */
-    exportLastCheckpointOnly?: boolean;
 }
 
 export declare interface TestTableFile {
@@ -5516,7 +5543,7 @@ export declare interface Tool {
     googleMaps?: GoogleMaps;
     /** Optional. Tool to support URL context retrieval. */
     urlContext?: UrlContext;
-    /** Optional. CodeExecution tool type. Enables the model to execute code as part of generation. This field is only used by the Gemini Developer API services. */
+    /** Optional. CodeExecution tool type. Enables the model to execute code as part of generation. */
     codeExecution?: ToolCodeExecution;
 }
 
@@ -5644,7 +5671,7 @@ export declare interface TuningJob {
     error?: GoogleRpcStatus;
     /** Optional. The description of the TuningJob. */
     description?: string;
-    /** The base model that is being tuned, e.g., "gemini-1.0-pro-002". . */
+    /** The base model that is being tuned. See [Supported models](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/tuning#supported_models). */
     baseModel?: string;
     /** Output only. The tuned model resources associated with this TuningJob. */
     tunedModel?: TunedModel;
@@ -5664,6 +5691,8 @@ export declare interface TuningJob {
     labels?: Record<string, string>;
     /** Output only. The resource name of the PipelineJob associated with the TuningJob. Format: `projects/{project}/locations/{location}/pipelineJobs/{pipeline_job}`. */
     pipelineJob?: string;
+    /** The service account that the tuningJob workload runs as. If not specified, the Vertex AI Secure Fine-Tuned Service Agent in the project will be used. See https://cloud.google.com/iam/docs/service-agents#vertex-ai-secure-fine-tuning-service-agent Users starting the pipeline must have the `iam.serviceAccounts.actAs` permission on this service account. */
+    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;
 }
@@ -5757,7 +5786,11 @@ export declare enum Type {
     /**
      * OpenAPI object type
      */
-    OBJECT = "OBJECT"
+    OBJECT = "OBJECT",
+    /**
+     * Null type
+     */
+    NULL = "NULL"
 }
 
 declare namespace types {
@@ -5773,10 +5806,10 @@ declare namespace types {
         createModelContent,
         Outcome,
         Language,
+        Type,
         HarmCategory,
         HarmBlockMethod,
         HarmBlockThreshold,
-        Type,
         Mode,
         AuthType,
         FinishReason,
@@ -5809,21 +5842,20 @@ declare namespace types {
         TurnCoverage,
         FunctionResponseScheduling,
         Scale,
-        MusicGenerationMode,
         LiveMusicPlaybackControl,
         VideoMetadata,
         Blob_2 as Blob,
+        FileData,
         CodeExecutionResult,
         ExecutableCode,
-        FileData,
         FunctionCall,
         FunctionResponse,
         Part,
         Content,
         HttpOptions,
+        Schema,
         ModelSelectionConfig,
         SafetySetting,
-        Schema,
         FunctionDeclaration,
         Interval,
         GoogleSearch,
@@ -5871,6 +5903,8 @@ declare namespace types {
         CitationMetadata,
         UrlMetadata,
         UrlContextMetadata,
+        RagChunkPageSpan,
+        RagChunk,
         GroundingChunkRetrievedContext,
         GroundingChunkWeb,
         GroundingChunk,
@@ -5923,6 +5957,7 @@ declare namespace types {
         DeleteModelConfig,
         DeleteModelParameters,
         DeleteModelResponse,
+        GenerationConfigThinkingConfig,
         GenerationConfig,
         CountTokensConfig,
         CountTokensParameters,
@@ -6287,6 +6322,10 @@ export declare interface VertexAISearch {
     datastore?: string;
     /** Optional. Fully-qualified Vertex AI Search engine resource ID. Format: `projects/{project}/locations/{location}/collections/{collection}/engines/{engine}` */
     engine?: string;
+    /** Optional. Filter strings to be passed to the search API. */
+    filter?: string;
+    /** Optional. Number of search results to return per query. The default value is 10. The maximumm allowed value is 10. */
+    maxResults?: number;
 }
 
 /** Retrieve from Vertex RAG Store for grounding. */