@ai-sdk/google 3.0.49 → 3.0.50

package/docs/15-google-generative-ai.mdx

@@ -1131,6 +1131,28 @@ const { embedding } = await embed({
     google: {
       outputDimensionality: 512, // optional, number of dimensions for the embedding
       taskType: 'SEMANTIC_SIMILARITY', // optional, specifies the task type for generating embeddings
+      content: [[{ text: 'additional context' }]], // optional, per-value multimodal content (only 1 here, since `value` is only a single one)
+    } satisfies GoogleEmbeddingModelOptions,
+  },
+});
+```
+
+When using `embedMany`, provide per-value multimodal content via the `content` option. Each entry corresponds to a value at the same index; use `null` for text-only entries:
+
+```ts
+import { google, type GoogleEmbeddingModelOptions } from '@ai-sdk/google';
+import { embedMany } from 'ai';
+
+const { embeddings } = await embedMany({
+  model: google.embedding('gemini-embedding-2-preview'),
+  values: ['sunny day at the beach', 'rainy afternoon in the city'],
+  providerOptions: {
+    google: {
+      // content array must have the same length as values
+      content: [
+        [{ inlineData: { mimeType: 'image/png', data: '<base64>' } }], // pairs with values[0]
+        null, // text-only, pairs with values[1]
+      ],
     } satisfies GoogleEmbeddingModelOptions,
   },
 });
@@ -1155,11 +1177,16 @@ The following optional provider options are available for Google Generative AI e
   - `FACT_VERIFICATION`: Optimized for verifying factual information.
   - `CODE_RETRIEVAL_QUERY`: Optimized for retrieving code blocks based on natural language queries.
 
+- **content**: _array_
+
+  Optional. Per-value multimodal content parts for embedding non-text content (images, video, PDF, audio). Each entry corresponds to the embedding value at the same index — its parts are merged with the text value in the request. Use `null` for entries that are text-only. The array length must match the number of values being embedded. Each non-null entry is an array of parts, where each part can be either `{ text: string }` or `{ inlineData: { mimeType: string, data: string } }`. Supported by `gemini-embedding-2-preview`.
+
 ### Model Capabilities
 
-| Model                  | Default Dimensions | Custom Dimensions   |
-| ---------------------- | ------------------ | ------------------- |
-| `gemini-embedding-001` | 3072               | <Check size={18} /> |
+| Model                        | Default Dimensions | Custom Dimensions   | Multimodal          |
+| ---------------------------- | ------------------ | ------------------- | ------------------- |
+| `gemini-embedding-001`       | 3072               | <Check size={18} /> | <Cross size={18} /> |
+| `gemini-embedding-2-preview` | 3072               | <Check size={18} /> | <Check size={18} /> |
 
 ## Image Models
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ai-sdk/google",
-  "version": "3.0.49",
+  "version": "3.0.50",
   "license": "Apache-2.0",
   "sideEffects": false,
   "main": "./dist/index.js",
@@ -36,16 +36,16 @@
     }
   },
   "dependencies": {
-    "@ai-sdk/provider-utils": "4.0.20",
-    "@ai-sdk/provider": "3.0.8"
+    "@ai-sdk/provider": "3.0.8",
+    "@ai-sdk/provider-utils": "4.0.20"
   },
   "devDependencies": {
     "@types/node": "20.17.24",
     "tsup": "^8",
     "typescript": "5.8.3",
     "zod": "3.25.76",
-    "@vercel/ai-tsconfig": "0.0.0",
-    "@ai-sdk/test-server": "1.0.3"
+    "@ai-sdk/test-server": "1.0.3",
+    "@vercel/ai-tsconfig": "0.0.0"
   },
   "peerDependencies": {
     "zod": "^3.25.76 || ^4.1.8"

package/src/google-generative-ai-embedding-model.ts

@@ -74,14 +74,24 @@ export class GoogleGenerativeAIEmbeddingModel implements EmbeddingModelV3 {
       headers,
     );
 
-    const multimodalContent = googleOptions?.content ?? [];
+    const multimodalContent = googleOptions?.content;
+
+    if (
+      multimodalContent != null &&
+      multimodalContent.length !== values.length
+    ) {
+      throw new Error(
+        `The number of multimodal content entries (${multimodalContent.length}) must match the number of values (${values.length}).`,
+      );
+    }
 
     // For single embeddings, use the single endpoint
     if (values.length === 1) {
+      const valueParts = multimodalContent?.[0];
       const textPart = values[0] ? [{ text: values[0] }] : [];
       const parts =
-        multimodalContent.length > 0
-          ? [...textPart, ...multimodalContent]
+        valueParts != null
+          ? [...textPart, ...valueParts]
           : [{ text: values[0] }];
 
       const {
@@ -116,7 +126,6 @@ export class GoogleGenerativeAIEmbeddingModel implements EmbeddingModelV3 {
     }
 
     // For multiple values, use the batch endpoint
-    // If multimodal content is provided, merge it into each request's parts
     const {
       responseHeaders,
       value: response,
@@ -125,15 +134,16 @@ export class GoogleGenerativeAIEmbeddingModel implements EmbeddingModelV3 {
       url: `${this.config.baseURL}/models/${this.modelId}:batchEmbedContents`,
       headers: mergedHeaders,
       body: {
-        requests: values.map(value => {
+        requests: values.map((value, index) => {
+          const valueParts = multimodalContent?.[index];
           const textPart = value ? [{ text: value }] : [];
           return {
             model: `models/${this.modelId}`,
             content: {
               role: 'user',
               parts:
-                multimodalContent.length > 0
-                  ? [...textPart, ...multimodalContent]
+                valueParts != null
+                  ? [...textPart, ...valueParts]
                   : [{ text: value }],
             },
             outputDimensionality: googleOptions?.outputDimensionality,

package/src/google-generative-ai-embedding-options.ts

@@ -7,6 +7,7 @@ import { z } from 'zod/v4';
 
 export type GoogleGenerativeAIEmbeddingModelId =
   | 'gemini-embedding-001'
+  | 'gemini-embedding-2-preview'
   | (string & {});
 
 const googleEmbeddingContentPartSchema = z.union([
@@ -54,11 +55,17 @@ export const googleEmbeddingModelOptions = lazySchema(() =>
         .optional(),
 
       /**
-       * Optional. Multimodal content parts for embedding non-text content
-       * (images, video, PDF, audio). When provided, these parts are merged
-       * with the text values in the embedding request.
+       * Optional. Per-value multimodal content parts for embedding non-text
+       * content (images, video, PDF, audio). Each entry corresponds to the
+       * embedding value at the same index and its parts are merged with the
+       * text value in the request. Use `null` for entries that are text-only.
+       *
+       * The array length must match the number of values being embedded. In
+       * the case of a single embedding, the array length must be 1.
        */
-      content: z.array(googleEmbeddingContentPartSchema).min(1).optional(),
+      content: z
+        .array(z.array(googleEmbeddingContentPartSchema).min(1).nullable())
+        .optional(),
     }),
   ),
 );