@mastra/mcp-docs-server 0.13.31 → 0.13.32-alpha.0

package/.docs/raw/getting-started/installation.mdx

@@ -15,8 +15,8 @@ For more control over setup, or to add Mastra to an existing project, see the [m
 
 ## Before you start
 
-- You'll need an API key from a [model provider](/models) to complete setup. We recommend starting with [Gemini](https://aistudio.google.com/app/api-keys), as you likely already have a Google account and they don't require a card.
-- Node.js 20 or later.
+- You'll need an API key from a [model provider](/models) to complete setup. We suggest starting with [OpenAI](https://platform.openai.com/api-keys), but if you need a provider that doesn't require a credit card, Google's [Gemini](https://aistudio.google.com/app/api-keys) is also an option.
+- [Install](https://nodejs.org/en/download) Node.js 20 or later.
 
 ## Install with `create mastra`
 
@@ -89,15 +89,15 @@ If you prefer not to use our automatic `create mastra` CLI tool, you can set up
 
 <Steps>
 
-### Create a new project
+### Create project
 
 Create a new project and change directory:
 
 ```bash copy
-mkdir hello-mastra && cd hello-mastra
+mkdir my-first-agent && cd my-first-agent
 ```
 
-Initialize a TypeScript project including the `@mastra/core` package:
+Initialize a TypeScript project and install the following dependencies:
 
 {/*
 LLM CONTEXT: This Tabs component shows manual installation commands for different package managers.
@@ -107,55 +107,42 @@ This helps users manually set up a Mastra project with their preferred package m
 */}
 
 <Tabs items={["npm", "pnpm", "yarn", "bun"]}>
-
   <Tab>
     ```bash copy
     npm init -y
-
-    npm install typescript tsx @types/node mastra@latest --save-dev
-
-    npm install @mastra/core@latest zod@^3 @ai-sdk/openai@^1
+    npm install -D typescript @types/node mastra@latest
+    npm install @mastra/core@latest zod@^4
     ```
-
   </Tab>
   <Tab>
     ```bash copy
-    pnpm init
-
-    pnpm add typescript tsx @types/node mastra@latest --save-dev
-
-    pnpm add @mastra/core@latest zod@^3 @ai-sdk/openai@^1
+    pnpm init -y
+    pnpm add -D typescript @types/node mastra@latest
+    pnpm add @mastra/core@latest zod@^4
     ```
-
   </Tab>
   <Tab>
     ```bash copy
     yarn init -y
-
-    yarn add typescript tsx @types/node mastra@latest --dev
-
-    yarn add @mastra/core@latest zod@^3 @ai-sdk/openai@^1
+    yarn add -D typescript @types/node mastra@latest
+    yarn add @mastra/core@latest zod@^4
     ```
-
   </Tab>
   <Tab>
     ```bash copy
     bun init -y
-
-    bun add typescript tsx @types/node mastra@latest --dev
-
-    bun add @mastra/core@latest zod@^3 @ai-sdk/openai@^1
+    bun add -d typescript @types/node mastra@latest
+    bun add @mastra/core@latest zod@^4
     ```
-
   </Tab>
 </Tabs>
 
-Add the `dev` and `build` scripts to `package.json`:
+Add `dev` and `build` scripts to your `package.json` file:
 
-```json filename="package.json" copy
+```json filename="package.json" copy /,/ /"dev": "mastra dev",/ /"build": "mastra build"/
 {
   "scripts": {
-    // ...
+    "test": "echo \"Error: no test specified\" && exit 1",
     "dev": "mastra dev",
     "build": "mastra build"
   }
@@ -172,9 +159,8 @@ touch tsconfig.json
 
 Add the following configuration:
 
-Mastra requires `module` and `moduleResolution` values that support modern Node.js versions. Older settings like `CommonJS` or `node` are incompatible with Mastra’s packages and will cause resolution errors.
 
-```json {4-5} filename="tsconfig.json" copy
+```json filename="tsconfig.json" copy
 {
   "compilerOptions": {
     "target": "ES2022",
@@ -192,12 +178,13 @@ Mastra requires `module` and `moduleResolution` values that support modern Node.
   ]
 }
 ```
+<Callout type="info">
+Mastra requires modern `module` and `moduleResolution` settings. Using `CommonJS` or `node` will cause resolution errors.
+</Callout>
 
-> This TypeScript configuration is optimized for Mastra projects, using modern module resolution and strict type checking.
-
-### Set up your API key
+### Set API key
 
-Create `.env` file:
+Create an `.env` file:
 
 ```bash copy
 touch .env
@@ -206,12 +193,14 @@ touch .env
 Add your API key:
 
 ```bash filename=".env" copy
-OPENAI_API_KEY=<your-api-key>
+GOOGLE_GENERATIVE_AI_API_KEY=<your-api-key>
 ```
 
-> This example uses OpenAI. Each LLM provider uses a unique name. See [Model Capabilities](/docs/getting-started/model-capability) for more information.
+<Callout type="default">
+This guide uses Google Gemini, but you can use any supported [model provider](/models), including OpenAI, Anthropic, and more.
+</Callout>
 
-### Create a Tool
+### Add tool
 
 Create a `weather-tool.ts` file:
 
@@ -242,9 +231,11 @@ export const weatherTool = createTool({
 });
 ```
 
-> See the full weatherTool example in [Giving an Agent a Tool](/examples/agents/using-a-tool).
+<Callout type="info">
+We've shortened and simplified the `weatherTool` example here. You can see the complete weather tool under [Giving an Agent a Tool](/examples/agents/using-a-tool).
+</Callout>
 
-### Create an Agent
+### Add agent
 
 Create a `weather-agent.ts` file:
 
@@ -255,7 +246,6 @@ mkdir -p src/mastra/agents && touch src/mastra/agents/weather-agent.ts
 Add the following code:
 
 ```ts filename="src/mastra/agents/weather-agent.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { Agent } from "@mastra/core/agent";
 import { weatherTool } from "../tools/weather-tool";
 
@@ -266,21 +256,21 @@ export const weatherAgent = new Agent({
 
       Your primary function is to help users get weather details for specific locations. When responding:
       - Always ask for a location if none is provided
-      - If the location name isn’t in English, please translate it
+      - If the location name isn't in English, please translate it
       - If giving a location with multiple parts (e.g. "New York, NY"), use the most relevant part (e.g. "New York")
       - Include relevant details like humidity, wind conditions, and precipitation
       - Keep responses concise but informative
 
       Use the weatherTool to fetch current weather data.
 `,
-  model: openai('gpt-4o-mini'),
+  model: "google/gemini-2.5-pro",
   tools: { weatherTool }
 });
 ```
 
-### Register the Agent
+### Register agent
 
-Create the Mastra entry point and register agent:
+Create the Mastra entry point and register your agent:
 
 ```bash copy
 touch src/mastra/index.ts
@@ -296,28 +286,31 @@ export const mastra = new Mastra({
   agents: { weatherAgent }
 });
 ```
+### Test your agent
+You can now launch the [Playground](/docs/server-db/local-dev-playground) and test your agent.
 
-You can now launch the [Mastra Development Server](/docs/server-db/local-dev-playground) and test your agent using the Mastra Playground.
-
-</Steps>
-
-## Add to an existing project
-
-Mastra can be installed and integrated into a wide range of projects. Below are links to integration guides to help you get started:
-
-- [Next.js](/docs/frameworks/web-frameworks/next-js)
-- [Vite + React](/docs/frameworks/web-frameworks/vite-react)
-- [Astro](/docs/frameworks/web-frameworks/astro)
-- [Express](/docs/frameworks/servers/express)
-
-
-### `mastra init`
-
-To install Mastra in an existing project, use the `mastra init` command.
-
-> See [mastra init](/reference/cli/init) for more information.
+<Tabs items={["npm", "pnpm", "yarn", "bun"]}>
+  <Tab>
+    ```bash copy
+    npm run dev
+    ```
+  </Tab>
+  <Tab>
+    ```bash copy
+    pnpm run dev
+    ```
+  </Tab>
+  <Tab>
+    ```bash copy
+    yarn run dev
+    ```
+  </Tab>
+  <Tab>
+    ```bash copy
+    bun run dev
+    ```
+  </Tab>
+</Tabs>
 
-### Next steps
 
-- [Local Development](/docs/server-db/local-dev-playground)
-- [Deploy to Mastra Cloud](/docs/deployment/overview)
+</Steps>

package/.docs/raw/memory/conversation-history.mdx

@@ -16,8 +16,8 @@ export const testAgent = new Agent({
   // ...
   memory: new Memory({
     options: {
-      lastMessages: 100
+      lastMessages: 20
     },
   })
 });
-```
+```

package/.docs/raw/memory/semantic-recall.mdx

@@ -98,40 +98,66 @@ const agent = new Agent({
 
 ### Embedder configuration
 
-Semantic recall relies on an [embedding model](/reference/memory/Memory#embedder) to convert messages into embeddings. You can specify any [embedding model](https://sdk.vercel.ai/docs/ai-sdk-core/embeddings) compatible with the AI SDK.
+Semantic recall relies on an [embedding model](/reference/memory/Memory#embedder) to convert messages into embeddings. Mastra supports embedding models through the model router using `provider/model` strings, or you can use any [embedding model](https://sdk.vercel.ai/docs/ai-sdk-core/embeddings) compatible with the AI SDK.
 
-To use FastEmbed (a local embedding model), install `@mastra/fastembed`:
+#### Using the Model Router (Recommended)
 
-```bash npm2yarn copy
-npm install @mastra/fastembed
+The simplest way is to use a `provider/model` string with autocomplete support:
+
+```ts {7}
+import { Memory } from "@mastra/memory";
+import { Agent } from "@mastra/core/agent";
+
+const agent = new Agent({
+  memory: new Memory({
+    // ... other memory options
+    embedder: "openai/text-embedding-3-small", // TypeScript autocomplete supported
+  }),
+});
 ```
 
-Then configure it in your memory:
+Supported embedding models:
+- **OpenAI**: `text-embedding-3-small`, `text-embedding-3-large`, `text-embedding-ada-002`
+- **Google**: `gemini-embedding-001`, `text-embedding-004`
+
+The model router automatically handles API key detection from environment variables (`OPENAI_API_KEY`, `GOOGLE_GENERATIVE_AI_API_KEY`).
+
+#### Using AI SDK Packages
+
+You can also use AI SDK embedding models directly:
 
 ```ts {3,8}
 import { Memory } from "@mastra/memory";
 import { Agent } from "@mastra/core/agent";
-import { fastembed } from "@mastra/fastembed";
+import { openai } from "@ai-sdk/openai";
 
 const agent = new Agent({
   memory: new Memory({
     // ... other memory options
-    embedder: fastembed,
+    embedder: openai.embedding("text-embedding-3-small"),
   }),
 });
 ```
 
-Alternatively, use a different provider like OpenAI:
+#### Using FastEmbed (Local)
+
+To use FastEmbed (a local embedding model), install `@mastra/fastembed`:
+
+```bash npm2yarn copy
+npm install @mastra/fastembed
+```
+
+Then configure it in your memory:
 
 ```ts {3,8}
 import { Memory } from "@mastra/memory";
 import { Agent } from "@mastra/core/agent";
-import { openai } from "@ai-sdk/openai";
+import { fastembed } from "@mastra/fastembed";
 
 const agent = new Agent({
   memory: new Memory({
     // ... other memory options
-    embedder: openai.embedding("text-embedding-3-small"),
+    embedder: fastembed,
   }),
 });
 ```

package/.docs/raw/rag/chunking-and-embedding.mdx

@@ -73,28 +73,40 @@ We go deeper into chunking strategies in our [chunk documentation](/reference/ra
 
 ## Step 2: Embedding Generation
 
-Transform chunks into embeddings using your preferred provider. Mastra supports many embedding providers, including OpenAI and Cohere:
+Transform chunks into embeddings using your preferred provider. Mastra supports embedding models through the model router or AI SDK packages.
 
-### Using OpenAI
+### Using the Model Router (Recommended)
+
+The simplest way is to use Mastra's model router with `provider/model` strings:
 
 ```ts showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
+import { ModelRouterEmbeddingModel } from "@mastra/core";
 import { embedMany } from "ai";
 
+const embeddingModel = new ModelRouterEmbeddingModel("openai/text-embedding-3-small");
+
 const { embeddings } = await embedMany({
-  model: openai.embedding("text-embedding-3-small"),
+  model: embeddingModel,
   values: chunks.map((chunk) => chunk.text),
 });
 ```
 
-### Using Cohere
+Supported embedding models:
+- **OpenAI**: `text-embedding-3-small`, `text-embedding-3-large`, `text-embedding-ada-002`
+- **Google**: `gemini-embedding-001`, `text-embedding-004`
+
+The model router automatically handles API key detection from environment variables.
+
+### Using AI SDK Packages
+
+You can also use AI SDK embedding models directly:
 
 ```ts showLineNumbers copy
-import { cohere } from "@ai-sdk/cohere";
+import { openai } from "@ai-sdk/openai";
 import { embedMany } from "ai";
 
 const { embeddings } = await embedMany({
-  model: cohere.embedding("embed-english-v3.0"),
+  model: openai.embedding("text-embedding-3-small"),
   values: chunks.map((chunk) => chunk.text),
 });
 ```

package/.docs/raw/reference/client-js/agents.mdx

@@ -67,27 +67,11 @@ const response = await agent.stream({
 
 // Process data stream with the processDataStream util
 response.processDataStream({
-  onTextPart: (text) => {
-    process.stdout.write(text);
-  },
-  onFilePart: (file) => {
-    console.log(file);
-  },
-  onDataPart: (data) => {
-    console.log(data);
-  },
-  onErrorPart: (error) => {
-    console.error(error);
+  onChunk: async(chunk) => {
+    console.log(chunk);
   },
 });
 
-// Process text stream with the processTextStream util
-// (used with structured output)
- response.processTextStream({
-      onTextPart: text => {
-        process.stdout.write(text);
-      },
-});
 
 // You can also read from response body directly
 const reader = response.body.getReader();
@@ -134,8 +118,13 @@ const response = await agent.stream({
 });
 
 response.processDataStream({
-  onTextPart: (text) => console.log(text),
-  onToolCallPart: (toolCall) => console.log('Tool called:', toolCall.toolName),
+  onChunk: async (chunk) => {
+    if (chunk.type === 'text-delta') {
+      console.log(chunk.payload.text);
+    } else if (chunk.type === 'tool-call') {
+      console.log(`calling tool ${chunk.payload.toolName} with args ${JSON.stringify(chunk.payload.args, null, 2)}`);
+    }
+  },
 });
 ```
 
@@ -176,15 +165,45 @@ const response = await agent.stream(
 
 // Process the stream
 response.processDataStream({
-  onChunk: (chunk) => {
-    console.log(chunk);
+  onChunk: async (chunk) => {
+    if (chunk.type === 'text-delta') {
+      console.log(chunk.payload.text);
+    }
   },
 });
 ```
 
-Currently, AI SDK V5 format is not supported in the client SDK.
-For AI SDK v5 compatible format, leverage the `@mastra/ai-sdk` package
-[AI SDK v5 Stream Compatibility](/docs/frameworks/agentic-uis/ai-sdk#enabling-stream-compatibility)
+#### AI SDK compatible format
+
+To stream AI SDK-formatted parts on the client from an `agent.stream(...)` response, wrap `response.processDataStream` into a `ReadableStream<ChunkType>` and use `toAISdkFormat`:
+
+```typescript filename="client-ai-sdk-transform.ts" copy
+import { createUIMessageStream } from 'ai';
+import { toAISdkFormat } from '@mastra/ai-sdk';
+import type { ChunkType, MastraModelOutput } from '@mastra/core/stream';
+
+const response = await agent.stream({ messages: 'Tell me a story' });
+
+const chunkStream: ReadableStream<ChunkType> = new ReadableStream<ChunkType>({
+  start(controller) {
+    response.processDataStream({
+      onChunk: async (chunk) => controller.enqueue(chunk as ChunkType),
+    }).finally(() => controller.close());
+  },
+});
+
+const uiMessageStream = createUIMessageStream({
+  execute: async ({ writer }) => {
+    for await (const part of toAISdkFormat(chunkStream as unknown as MastraModelOutput, { from: 'agent' })) {
+      writer.write(part);
+    }
+  },
+});
+
+for await (const part of uiMessageStream) {
+  console.log(part);
+}
+```
 
 ### Generate
 

package/.docs/raw/reference/scorers/answer-relevancy.mdx

@@ -116,10 +116,9 @@ A relevancy score between 0 and 1:
 In this example, the response accurately addresses the input query with specific and relevant information.
 
 ```typescript filename="src/example-high-answer-relevancy.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { createAnswerRelevancyScorer } from "@mastra/evals/scorers/llm";
 
-const scorer = createAnswerRelevancyScorer({ model: openai("gpt-4o-mini") });
+const scorer = createAnswerRelevancyScorer({ model: 'openai/gpt-4o-mini' });
 
 const inputMessages = [{ role: 'user', content: "What are the health benefits of regular exercise?" }];
 const outputMessage = { text: "Regular exercise improves cardiovascular health, strengthens muscles, boosts metabolism, and enhances mental well-being through the release of endorphins." };
@@ -148,10 +147,9 @@ The output receives a high score because it accurately answers the query without
 In this example, the response addresses the query in part but includes additional information that isn’t directly relevant.
 
 ```typescript filename="src/example-partial-answer-relevancy.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { createAnswerRelevancyScorer } from "@mastra/evals/scorers/llm";
 
-const scorer = createAnswerRelevancyScorer({ model: openai("gpt-4o-mini") });
+const scorer = createAnswerRelevancyScorer({ model: 'openai/gpt-4o-mini' });
 
 const inputMessages = [{ role: 'user', content: "What should a healthy breakfast include?" }];
 const outputMessage = { text: "A nutritious breakfast should include whole grains and protein. However, the timing of your breakfast is just as important - studies show eating within 2 hours of waking optimizes metabolism and energy levels throughout the day." };
@@ -180,10 +178,9 @@ The output receives a lower score because it partially answers the query. While
 In this example, the response does not address the query and contains information that is entirely unrelated.
 
 ```typescript filename="src/example-low-answer-relevancy.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { createAnswerRelevancyScorer } from "@mastra/evals/scorers/llm";
 
-const scorer = createAnswerRelevancyScorer({ model: openai("gpt-4o-mini") });
+const scorer = createAnswerRelevancyScorer({ model: 'openai/gpt-4o-mini' });
 
 const inputMessages = [{ role: 'user', content: "What are the benefits of meditation?" }];
 const outputMessage = { text: "The Great Wall of China is over 13,000 miles long and was built during the Ming Dynasty to protect against invasions." };

package/.docs/raw/reference/scorers/answer-similarity.mdx

@@ -175,12 +175,11 @@ await runExperiment({
 In this example, the agent's output semantically matches the ground truth perfectly.
 
 ```typescript filename="src/example-perfect-similarity.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { runExperiment } from "@mastra/core/scores";
 import { createAnswerSimilarityScorer } from "@mastra/evals/scorers/llm";
 import { myAgent } from "./agent";
 
-const scorer = createAnswerSimilarityScorer({ model: openai("gpt-4o-mini") });
+const scorer = createAnswerSimilarityScorer({ model: 'openai/gpt-4o-mini' });
 
 const result = await runExperiment({
   data: [
@@ -214,12 +213,11 @@ The output receives a perfect score because both the agent's answer and ground t
 In this example, the agent provides the same information as the ground truth but with different phrasing.
 
 ```typescript filename="src/example-semantic-similarity.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { runExperiment } from "@mastra/core/scores";
 import { createAnswerSimilarityScorer } from "@mastra/evals/scorers/llm";
 import { myAgent } from "./agent";
 
-const scorer = createAnswerSimilarityScorer({ model: openai("gpt-4o-mini") });
+const scorer = createAnswerSimilarityScorer({ model: 'openai/gpt-4o-mini' });
 
 const result = await runExperiment({
   data: [
@@ -253,12 +251,11 @@ The output receives a high score because it conveys the same information with eq
 In this example, the agent's response is partially correct but missing key information.
 
 ```typescript filename="src/example-partial-similarity.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { runExperiment } from "@mastra/core/scores";
 import { createAnswerSimilarityScorer } from "@mastra/evals/scorers/llm";
 import { myAgent } from "./agent";
 
-const scorer = createAnswerSimilarityScorer({ model: openai("gpt-4o-mini") });
+const scorer = createAnswerSimilarityScorer({ model: 'openai/gpt-4o-mini' });
 
 const result = await runExperiment({
   data: [
@@ -292,12 +289,11 @@ The output receives a moderate score because it includes some correct informatio
 In this example, the agent provides factually incorrect information that contradicts the ground truth.
 
 ```typescript filename="src/example-contradiction.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { runExperiment } from "@mastra/core/scores";
 import { createAnswerSimilarityScorer } from "@mastra/evals/scorers/llm";
 import { myAgent } from "./agent";
 
-const scorer = createAnswerSimilarityScorer({ model: openai("gpt-4o-mini") });
+const scorer = createAnswerSimilarityScorer({ model: 'openai/gpt-4o-mini' });
 
 const result = await runExperiment({
   data: [
@@ -332,13 +328,12 @@ Use the scorer in your test suites to ensure agent consistency over time:
 
 ```typescript filename="src/ci-integration.test.ts" showLineNumbers copy
 import { describe, it, expect } from 'vitest';
-import { openai } from "@ai-sdk/openai";
 import { runExperiment } from "@mastra/core/scores";
 import { createAnswerSimilarityScorer } from "@mastra/evals/scorers/llm";
 import { myAgent } from "./agent";
 
 describe('Agent Consistency Tests', () => {
-  const scorer = createAnswerSimilarityScorer({ model: openai("gpt-4o-mini") });
+  const scorer = createAnswerSimilarityScorer({ model: 'openai/gpt-4o-mini' });
 
   it('should provide accurate factual answers', async () => {
     const result = await runExperiment({
@@ -386,14 +381,13 @@ describe('Agent Consistency Tests', () => {
 Customize the scorer behavior for specific use cases:
 
 ```typescript filename="src/custom-config.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { runExperiment } from "@mastra/core/scores";
 import { createAnswerSimilarityScorer } from "@mastra/evals/scorers/llm";
 import { myAgent } from "./agent";
 
 // Configure for strict exact matching with high scale
 const strictScorer = createAnswerSimilarityScorer({ 
-  model: openai("gpt-4o-mini"),
+  model: 'openai/gpt-4o-mini',
   options: {
     exactMatchBonus: 0.5,        // Higher bonus for exact matches
     contradictionPenalty: 2.0,   // Very strict on contradictions
@@ -404,7 +398,7 @@ const strictScorer = createAnswerSimilarityScorer({
 
 // Configure for lenient semantic matching
 const lenientScorer = createAnswerSimilarityScorer({ 
-  model: openai("gpt-4o-mini"),
+  model: 'openai/gpt-4o-mini',
   options: {
     semanticThreshold: 0.6,      // Lower threshold for semantic matches
     contradictionPenalty: 0.5,   // More forgiving on minor contradictions

package/.docs/raw/reference/scorers/bias.mdx

@@ -127,10 +127,9 @@ A bias score between 0 and 1:
 In this example, the response contains overtly biased language and generalizations. The assumptions are explicit and strongly reinforce stereotypes or discriminatory views.
 
 ```typescript filename="src/example-high-bias.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { createBiasScorer } from "@mastra/evals/scorers/llm";
 
-const scorer = createBiasScorer({ model: openai("gpt-4o-mini") });
+const scorer = createBiasScorer({ model: 'openai/gpt-4o-mini' });
 
 const query = "What makes someone a good leader?";
 const response =
@@ -160,10 +159,9 @@ The output receives a high score because it's a clear example of discriminatory
 In this example, the response contains a mix of reasonable points with subtle bias. While parts of the response are fair, underlying bias is still present.
 
 ```typescript filename="src/example-mixed-bias.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { createBiasScorer } from "@mastra/evals/scorers/llm";
 
-const scorer = createBiasScorer({ model: openai("gpt-4o-mini") });
+const scorer = createBiasScorer({ model: 'openai/gpt-4o-mini' });
 
 const query = "How do different age groups perform at work?";
 const response =
@@ -193,10 +191,9 @@ The output receives a lower score because the response introduces bias in a more
 In this example, the response focuses on objective and neutral criteria without introducing biased assumptions.
 
 ```typescript filename="src/example-low-bias.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { createBiasScorer } from "@mastra/evals/scorers/llm";
 
-const scorer = createBiasScorer({ model: openai("gpt-4o-mini") });
+const scorer = createBiasScorer({ model: 'openai/gpt-4o-mini' });
 
 const query = "What is the best hiring practice?";
 const response =