@ai-sdk/amazon-bedrock 4.0.37 → 4.0.38

package/CHANGELOG.md

@@ -1,5 +1,11 @@
 # @ai-sdk/amazon-bedrock
 
+## 4.0.38
+
+### Patch Changes
+
+- 3988c08: docs: fix incorrect and outdated provider docs
+
 ## 4.0.37
 
 ### Patch Changes

package/dist/anthropic/index.js

@@ -35,7 +35,7 @@ var import_provider_utils = require("@ai-sdk/provider-utils");
 var import_aws4fetch = require("aws4fetch");
 
 // src/version.ts
-var VERSION = true ? "4.0.37" : "0.0.0-test";
+var VERSION = true ? "4.0.38" : "0.0.0-test";
 
 // src/bedrock-sigv4-fetch.ts
 function createSigV4FetchFunction(getCredentials, fetch = globalThis.fetch) {

package/dist/anthropic/index.mjs

@@ -24,7 +24,7 @@ import {
 import { AwsV4Signer } from "aws4fetch";
 
 // src/version.ts
-var VERSION = true ? "4.0.37" : "0.0.0-test";
+var VERSION = true ? "4.0.38" : "0.0.0-test";
 
 // src/bedrock-sigv4-fetch.ts
 function createSigV4FetchFunction(getCredentials, fetch = globalThis.fetch) {

package/dist/index.js

@@ -1868,7 +1868,7 @@ var import_provider_utils7 = require("@ai-sdk/provider-utils");
 var import_aws4fetch = require("aws4fetch");
 
 // src/version.ts
-var VERSION = true ? "4.0.37" : "0.0.0-test";
+var VERSION = true ? "4.0.38" : "0.0.0-test";
 
 // src/bedrock-sigv4-fetch.ts
 function createSigV4FetchFunction(getCredentials, fetch = globalThis.fetch) {

package/dist/index.mjs

@@ -1885,7 +1885,7 @@ import {
 import { AwsV4Signer } from "aws4fetch";
 
 // src/version.ts
-var VERSION = true ? "4.0.37" : "0.0.0-test";
+var VERSION = true ? "4.0.38" : "0.0.0-test";
 
 // src/bedrock-sigv4-fetch.ts
 function createSigV4FetchFunction(getCredentials, fetch = globalThis.fetch) {

package/docs/08-amazon-bedrock.mdx

@@ -168,6 +168,27 @@ You can use the following optional settings to customize the Amazon Bedrock prov
   Optional. The AWS credential provider chain that you want to use for the API calls.
   It uses the specified credentials by default.
 
+- **apiKey** _string_
+
+  Optional. API key for authenticating requests using Bearer token authentication.
+  When provided, this will be used instead of AWS SigV4 authentication.
+  It uses the `AWS_BEARER_TOKEN_BEDROCK` environment variable by default.
+
+- **baseURL** _string_
+
+  Optional. Base URL for the Bedrock API calls.
+  Useful for custom endpoints or proxy configurations.
+
+- **headers** _Record<string, string>_
+
+  Optional. Custom headers to include in the requests.
+
+- **fetch** _(input: RequestInfo, init?: RequestInit) => Promise<Response>_
+
+  Optional. Custom [fetch](https://developer.mozilla.org/en-US/docs/Web/API/fetch) implementation.
+  You can use it as a middleware to intercept requests,
+  or to provide a custom fetch implementation for e.g. testing.
+
 ## Language Models
 
 You can create models that call the Bedrock API using the provider instance.
@@ -491,7 +512,7 @@ They are available via the `tools` property of the provider instance.
 The Bash Tool allows running bash commands. Here's how to create and use it:
 
 ```ts
-const bashTool = anthropic.tools.bash_20241022({
+const bashTool = bedrock.tools.bash_20241022({
   execute: async ({ command, restart }) => {
     // Implement your bash command execution logic here
     // Return the result of the command execution
@@ -511,7 +532,7 @@ The Text Editor Tool provides functionality for viewing and editing text files.
 **For Claude 4 models (Opus & Sonnet):**
 
 ```ts
-const textEditorTool = anthropic.tools.textEditor_20250429({
+const textEditorTool = bedrock.tools.textEditor_20250429({
   execute: async ({
     command,
     path,
@@ -530,7 +551,7 @@ const textEditorTool = anthropic.tools.textEditor_20250429({
 **For Claude 3.5 Sonnet and earlier models:**
 
 ```ts
-const textEditorTool = anthropic.tools.textEditor_20241022({
+const textEditorTool = bedrock.tools.textEditor_20241022({
   execute: async ({
     command,
     path,
@@ -588,7 +609,7 @@ const response = await generateText({
 The Computer Tool enables control of keyboard and mouse actions on a computer:
 
 ```ts
-const computerTool = anthropic.tools.computer_20241022({
+const computerTool = bedrock.tools.computer_20241022({
   displayWidthPx: 1920,
   displayHeightPx: 1080,
   displayNumber: 0, // Optional, for X11 environments
@@ -749,22 +770,81 @@ The following optional provider options are available for Bedrock Titan embeddin
 
   Flag indicating whether or not to normalize the output embeddings. Defaults to true.
 
+### Nova Embedding Models
+
+Amazon Nova embedding models support additional provider options:
+
+```ts
+import { bedrock } from '@ai-sdk/amazon-bedrock';
+import { embed } from 'ai';
+
+const { embedding } = await embed({
+  model: bedrock.embedding('amazon.nova-embed-text-v2:0'),
+  value: 'sunny day at the beach',
+  providerOptions: {
+    bedrock: {
+      embeddingDimension: 1024, // optional, number of dimensions
+      embeddingPurpose: 'TEXT_RETRIEVAL', // optional, purpose of embedding
+      truncate: 'END', // optional, truncation behavior
+    },
+  },
+});
+```
+
+The following optional provider options are available for Nova embedding models:
+
+- **embeddingDimension** _number_
+
+  The number of dimensions for the output embeddings. Supported values: 256, 384, 1024 (default), 3072.
+
+- **embeddingPurpose** _string_
+
+  The purpose of the embedding. Accepts: `GENERIC_INDEX` (default), `TEXT_RETRIEVAL`, `IMAGE_RETRIEVAL`, `VIDEO_RETRIEVAL`, `DOCUMENT_RETRIEVAL`, `AUDIO_RETRIEVAL`, `GENERIC_RETRIEVAL`, `CLASSIFICATION`, `CLUSTERING`.
+
+- **truncate** _string_
+
+  Truncation behavior when input exceeds the model's context length. Accepts: `NONE`, `START`, `END` (default).
+
+### Cohere Embedding Models
+
+Cohere embedding models on Bedrock require an `inputType` and support truncation:
+
+```ts
+import { bedrock } from '@ai-sdk/amazon-bedrock';
+import { embed } from 'ai';
+
+const { embedding } = await embed({
+  model: bedrock.embedding('cohere.embed-english-v3'),
+  value: 'sunny day at the beach',
+  providerOptions: {
+    bedrock: {
+      inputType: 'search_document', // required for Cohere
+      truncate: 'END', // optional, truncation behavior
+    },
+  },
+});
+```
+
+The following provider options are available for Cohere embedding models:
+
+- **inputType** _string_
+
+  Input type for Cohere embedding models. Accepts: `search_document`, `search_query` (default), `classification`, `clustering`.
+
+- **truncate** _string_
+
+  Truncation behavior when input exceeds the model's context length. Accepts: `NONE`, `START`, `END`.
+
 ### Model Capabilities
 
 | Model                          | Default Dimensions | Custom Dimensions   |
 | ------------------------------ | ------------------ | ------------------- |
 | `amazon.titan-embed-text-v1`   | 1536               | <Cross size={18} /> |
 | `amazon.titan-embed-text-v2:0` | 1024               | <Check size={18} /> |
+| `amazon.nova-embed-text-v2:0`  | 1024               | <Check size={18} /> |
 | `cohere.embed-english-v3`      | 1024               | <Cross size={18} /> |
 | `cohere.embed-multilingual-v3` | 1024               | <Cross size={18} /> |
 
-<Note>
-  Cohere embedding models on Bedrock require an <code>input_type</code>. Set it
-  via
-  <code>providerOptions.bedrock.inputType</code> (defaults to{' '}
-  <code>search_query</code>).
-</Note>
-
 ## Reranking Models
 
 You can create models that call the [Bedrock Rerank API](https://docs.aws.amazon.com/bedrock/latest/userguide/rerank-api.html)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ai-sdk/amazon-bedrock",
-  "version": "4.0.37",
+  "version": "4.0.38",
   "license": "Apache-2.0",
   "sideEffects": false,
   "main": "./dist/index.js",
@@ -47,8 +47,8 @@
     "tsup": "^8.3.0",
     "typescript": "5.8.3",
     "zod": "3.25.76",
-    "@ai-sdk/test-server": "1.0.3",
-    "@vercel/ai-tsconfig": "0.0.0"
+    "@vercel/ai-tsconfig": "0.0.0",
+    "@ai-sdk/test-server": "1.0.3"
   },
   "peerDependencies": {
     "zod": "^3.25.76 || ^4.1.8"