@mastra/mcp-docs-server 0.13.31 → 0.13.32-alpha.1

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/cli/create-mastra.mdx

@@ -96,7 +96,7 @@ Instead of an interactive prompt you can also define these CLI flags.
       name: "--components",
       type: "string",
       description:
-        "Comma-separated list of components (agents, tools, workflows)",
+        "Comma-separated list of components (agents, tools, workflows, scorers)",
       isOptional: true,
     },
     {

package/.docs/raw/reference/cli/mastra.mdx

@@ -173,7 +173,7 @@ The directory where Mastra files should be saved to. Defaults to `src`.
 
 #### `--components`
 
-Comma-separated list of components to add. For each component a new folder will be created. Defaults to `['agents', 'tools', 'workflows']`.
+Comma-separated list of components to add. For each component a new folder will be created. Choose from: `"agents" | "tools" | "workflows" | "scorers"`. Defaults to `['agents', 'tools', 'workflows']`.
 
 #### `--llm`
 

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 =

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

@@ -110,10 +110,9 @@ A completeness score between 0 and 1:
 In this example, the response comprehensively addresses all aspects of the query with detailed information covering multiple dimensions.
 
 ```typescript filename="src/example-high-completeness.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { createCompletenessScorer } from "@mastra/evals/scorers/llm";
 
-const scorer = createCompletenessScorer({ model: openai("gpt-4o-mini") });
+const scorer = createCompletenessScorer({ model: 'openai/gpt-4o-mini' });
 
 const query = "Explain the process of photosynthesis, including the inputs, outputs, and stages involved.";
 const response =
@@ -143,10 +142,9 @@ The output receives a high score because it addresses all requested aspects: inp
 In this example, the response addresses some key points but misses important aspects or lacks sufficient detail.
 
 ```typescript filename="src/example-partial-completeness.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { createCompletenessScorer } from "@mastra/evals/scorers/llm";
 
-const scorer = createCompletenessScorer({ model: openai("gpt-4o-mini") });
+const scorer = createCompletenessScorer({ model: 'openai/gpt-4o-mini' });
 
 const query = "What are the benefits and drawbacks of remote work for both employees and employers?";
 const response =
@@ -176,10 +174,9 @@ The output receives a moderate score because it covers employee benefits and som
 In this example, the response only partially addresses the query and misses several important aspects.
 
 ```typescript filename="src/example-low-completeness.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { createCompletenessScorer } from "@mastra/evals/scorers/llm";
 
-const scorer = createCompletenessScorer({ model: openai("gpt-4o-mini") });
+const scorer = createCompletenessScorer({ model: 'openai/gpt-4o-mini' });
 
 const query = "Compare renewable and non-renewable energy sources in terms of cost, environmental impact, and sustainability.";
 const response =

package/.docs/raw/reference/scorers/context-precision.mdx

@@ -31,7 +31,7 @@ Use when optimizing context selection for:
   content={[
     {
       name: "model",
-      type: "MastraLanguageModel",
+      type: "MastraModelConfig",
       description: "The language model to use for evaluating context relevance",
       required: true,
     },
@@ -146,7 +146,7 @@ MAP = (1.0 + 0.67) / 2 = 0.835 ≈ **0.83**
 
 ```typescript
 const scorer = createContextPrecisionScorer({
-  model: openai('gpt-4o-mini'),
+  model: 'openai/gpt-4o-mini',
   options: {
     contextExtractor: (input, output) => {
       // Extract context dynamically based on the query
@@ -165,7 +165,7 @@ const scorer = createContextPrecisionScorer({
 
 ```typescript
 const scorer = createContextPrecisionScorer({
-  model: openai('gpt-4o-mini'), 
+  model: 'openai/gpt-4o-mini', 
   options: {
     context: [
       // Simulate retrieved documents from vector database
@@ -187,11 +187,10 @@ const scorer = createContextPrecisionScorer({
 This example shows perfect context precision where all relevant context appears early:
 
 ```typescript
-import { openai } from '@ai-sdk/openai';
 import { createContextPrecisionScorer } from '@mastra/evals';
 
 const scorer = createContextPrecisionScorer({
-  model: openai('gpt-4o-mini'),
+  model: 'openai/gpt-4o-mini',
   options: {
     context: [
       'Photosynthesis is the process by which plants convert sunlight, carbon dioxide, and water into glucose and oxygen.',
@@ -234,11 +233,10 @@ console.log(result);
 This example shows moderate precision with both relevant and irrelevant context:
 
 ```typescript
-import { openai } from '@ai-sdk/openai';
 import { createContextPrecisionScorer } from '@mastra/evals';
 
 const scorer = createContextPrecisionScorer({
-  model: openai('gpt-4o-mini'),
+  model: 'openai/gpt-4o-mini', 
   options: {
     context: [
       'Regular exercise improves cardiovascular health by strengthening the heart muscle.',
@@ -283,11 +281,10 @@ console.log(result);
 This example shows poor context precision with mostly irrelevant context:
 
 ```typescript
-import { openai } from '@ai-sdk/openai';
 import { createContextPrecisionScorer } from '@mastra/evals';
 
 const scorer = createContextPrecisionScorer({
-  model: openai('gpt-4o-mini'),
+  model: 'openai/gpt-4o-mini',
   options: {
     context: [
       'The weather forecast shows sunny skies this weekend.',

package/.docs/raw/reference/scorers/context-relevance.mdx

@@ -31,7 +31,7 @@ Use when optimizing for:
   content={[
     {
       name: "model",
-      type: "MastraLanguageModel",
+      type: "MastraModelConfig",
       description: "The language model to use for evaluating context relevance",
       required: true,
     },
@@ -185,12 +185,11 @@ Use results to improve your system:
 Control how penalties are applied for unused and missing context:
 
 ```typescript
-import { openai } from '@ai-sdk/openai';
 import { createContextRelevanceScorerLLM } from '@mastra/evals';
 
 // Stricter penalty configuration
 const strictScorer = createContextRelevanceScorerLLM({
-  model: openai('gpt-4o-mini'),
+  model: 'openai/gpt-4o-mini',
   options: {
     context: [
       'Einstein won the Nobel Prize for photoelectric effect',
@@ -208,7 +207,7 @@ const strictScorer = createContextRelevanceScorerLLM({
 
 // Lenient penalty configuration
 const lenientScorer = createContextRelevanceScorerLLM({
-  model: openai('gpt-4o-mini'),
+  model: 'openai/gpt-4o-mini',
   options: {
     context: [
       'Einstein won the Nobel Prize for photoelectric effect',
@@ -254,7 +253,7 @@ console.log('Lenient penalties:', lenientResult.score); // Higher score, less pe
 
 ```typescript
 const scorer = createContextRelevanceScorerLLM({
-  model: openai('gpt-4o'),
+  model: 'openai/gpt-4o',
   options: {
     contextExtractor: (input, output) => {
       // Extract context based on the query
@@ -278,7 +277,7 @@ const scorer = createContextRelevanceScorerLLM({
 
 ```typescript
 const scorer = createContextRelevanceScorerLLM({
-  model: openai('gpt-4o-mini'),
+  model: 'openai/gpt-4o-mini',
   options: {
     context: [
       'Relevant information...',
@@ -295,7 +294,7 @@ const scorer = createContextRelevanceScorerLLM({
 
 ```typescript
 const scorer = createContextRelevanceScorerLLM({
-  model: openai('gpt-4o-mini'),
+  model: 'openai/gpt-4o-mini',
   options: {
     contextExtractor: (input, output) => {
       const query = input?.inputMessages?.[0]?.content || '';
@@ -323,11 +322,10 @@ const scorer = createContextRelevanceScorerLLM({
 This example shows excellent context relevance where all context directly supports the response:
 
 ```typescript
-import { openai } from '@ai-sdk/openai';
 import { createContextRelevanceScorerLLM } from '@mastra/evals';
 
 const scorer = createContextRelevanceScorerLLM({
-  model: openai('gpt-4o-mini'),
+  model: 'openai/gpt-4o-mini',
   options: {
     context: [
       'Einstein won the Nobel Prize for his discovery of the photoelectric effect in 1921.',
@@ -370,11 +368,10 @@ console.log(result);
 This example shows moderate relevance with some context being irrelevant or unused:
 
 ```typescript
-import { openai } from '@ai-sdk/openai';
 import { createContextRelevanceScorerLLM } from '@mastra/evals';
 
 const scorer = createContextRelevanceScorerLLM({
-  model: openai('gpt-4o-mini'),
+  model: 'openai/gpt-4o-mini',
   options: {
     context: [
       'Solar eclipses occur when the Moon blocks the Sun.',
@@ -415,7 +412,7 @@ console.log(result);
 
 // With custom penalty configuration
 const customScorer = createContextRelevanceScorerLLM({
-  model: openai('gpt-4o-mini'),
+  model: 'openai/gpt-4o-mini',
   options: {
     context: [
       'Solar eclipses occur when the Moon blocks the Sun.',
@@ -450,11 +447,10 @@ console.log(customResult);
 This example shows poor context relevance with mostly irrelevant information:
 
 ```typescript
-import { openai } from '@ai-sdk/openai';
 import { createContextRelevanceScorerLLM } from '@mastra/evals';
 
 const scorer = createContextRelevanceScorerLLM({
-  model: openai('gpt-4o-mini'),
+  model: 'openai/gpt-4o-mini',
   options: {
     context: [
       'The Great Barrier Reef is located in Australia.',
@@ -499,11 +495,10 @@ console.log(result);
 Extract context dynamically based on the run input:
 
 ```typescript
-import { openai } from '@ai-sdk/openai';
 import { createContextRelevanceScorerLLM } from '@mastra/evals';
 
 const scorer = createContextRelevanceScorerLLM({
-  model: openai('gpt-4o-mini'),
+  model: 'openai/gpt-4o-mini',
   options: {
     contextExtractor: (input, output) => {
       // Extract query from input
@@ -543,11 +538,10 @@ const scorer = createContextRelevanceScorerLLM({
 Integrate with RAG pipelines to evaluate retrieved context:
 
 ```typescript
-import { openai } from '@ai-sdk/openai';
 import { createContextRelevanceScorerLLM } from '@mastra/evals';
 
 const scorer = createContextRelevanceScorerLLM({
-  model: openai('gpt-4o-mini'),
+  model: 'openai/gpt-4o-mini',
   options: {
     contextExtractor: (input, output) => {
       // Extract from RAG retrieval results

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

@@ -121,10 +121,9 @@ A faithfulness score between 0 and 1:
 In this example, the response closely aligns with the context. Each statement in the output is verifiable and supported by the provided context entries, resulting in a high score.
 
 ```typescript filename="src/example-high-faithfulness.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { createFaithfulnessScorer } from "@mastra/evals/scorers/llm";
 
-const scorer = createFaithfulnessScorer({ model: openai("gpt-4o-mini"), options: {
+const scorer = createFaithfulnessScorer({ model: 'openai/gpt-4o-mini', options: {
   context: [
     "The Tesla Model 3 was launched in 2017.",
     "It has a range of up to 358 miles.",
@@ -159,10 +158,9 @@ The output receives a score of 1 because all the information it provides can be
 In this example, there are a mix of supported and unsupported claims. Some parts of the response are backed by the context, while others introduce new information not found in the source material.
 
 ```typescript filename="src/example-mixed-faithfulness.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { createFaithfulnessScorer } from "@mastra/evals/scorers/llm";
 
-const scorer = createFaithfulnessScorer({ model: openai("gpt-4o-mini"), options: {
+const scorer = createFaithfulnessScorer({ model: 'openai/gpt-4o-mini', options: {
   context: [
     "Python was created by Guido van Rossum.",
     "The first version was released in 1991.",
@@ -197,10 +195,9 @@ The score is lower because only a portion of the response is verifiable. While s
 In this example, the response directly contradicts the context. None of the claims are supported, and several conflict with the facts provided.
 
 ```typescript filename="src/example-low-faithfulness.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { createFaithfulnessScorer } from "@mastra/evals/scorers/llm";
 
-const scorer = createFaithfulnessScorer({ model: openai("gpt-4o-mini"), options: {
+const scorer = createFaithfulnessScorer({ model: 'openai/gpt-4o-mini', options: {
   context: [
     "Mars is the fourth planet from the Sun.",
     "It has a thin atmosphere of mostly carbon dioxide.",

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

@@ -132,10 +132,9 @@ A hallucination score between 0 and 1:
 In this example, the response is fully aligned with the provided context. All claims are factually correct and directly supported by the source material, resulting in a low hallucination score.
 
 ```typescript filename="src/example-no-hallucination.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { createHallucinationScorer } from "@mastra/evals/scorers/llm";
 
-const scorer = createHallucinationScorer({ model: openai("gpt-4o-mini"), options: {
+const scorer = createHallucinationScorer({ model: 'openai/gpt-4o-mini', options: {
   context: [
     "The iPhone was first released in 2007.",
     "Steve Jobs unveiled it at Macworld.",
@@ -170,10 +169,9 @@ The response receives a score of 0 because there are no contradictions. Every st
 In this example, the response includes both accurate and inaccurate claims. Some details align with the context, while others directly contradict it—such as inflated numbers or incorrect locations. These contradictions increase the hallucination score.
 
 ```typescript filename="src/example-mixed-hallucination.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { createHallucinationScorer } from "@mastra/evals/scorers/llm";
 
-const scorer = createHallucinationScorer({ model: openai("gpt-4o-mini"), options: {
+const scorer = createHallucinationScorer({ model: 'openai/gpt-4o-mini', options: {
   context: [
     "The first Star Wars movie was released in 1977.",
     "It was directed by George Lucas.",
@@ -209,10 +207,9 @@ The Scorer assigns a mid-range score because parts of the response conflict with
 In this example, the response contradicts every key fact in the context. None of the claims can be verified, and all presented details are factually incorrect.
 
 ```typescript filename="src/example-complete-hallucination.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { createHallucinationScorer } from "@mastra/evals/scorers/llm";
 
-const scorer = createHallucinationScorer({ model: openai("gpt-4o-mini"), options: {
+const scorer = createHallucinationScorer({ model: 'openai/gpt-4o-mini', options: {
   context: [
     "The Wright brothers made their first flight in 1903.",
     "The flight lasted 12 seconds.",