@mastra/mcp-docs-server 0.13.37 → 0.13.38

package/.docs/raw/reference/scorers/keyword-coverage.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Reference: Keyword Coverage | Scorers | Mastra Docs"
+title: "Reference: Keyword Coverage Scorer | Scorers | Mastra Docs"
 description: Documentation for the Keyword Coverage Scorer in Mastra, which evaluates how well LLM outputs cover important keywords from the input.
 ---
 
@@ -25,17 +25,20 @@ This function returns an instance of the MastraScorer class. See the [MastraScor
     {
       name: "preprocessStepResult",
       type: "object",
-      description: "Object with extracted keywords: { referenceKeywords: Set<string>, responseKeywords: Set<string> }",
+      description:
+        "Object with extracted keywords: { referenceKeywords: Set<string>, responseKeywords: Set<string> }",
     },
     {
       name: "analyzeStepResult",
       type: "object",
-      description: "Object with keyword coverage: { totalKeywords: number, matchedKeywords: number }",
+      description:
+        "Object with keyword coverage: { totalKeywords: number, matchedKeywords: number }",
     },
     {
       name: "score",
       type: "number",
-      description: "Coverage score (0-1) representing the proportion of matched keywords.",
+      description:
+        "Coverage score (0-1) representing the proportion of matched keywords.",
     },
   ]}
 />
@@ -105,21 +108,22 @@ The scorer handles several special cases:
 
 In this example, the response fully reflects the key terms from the input. All required keywords are present, resulting in complete coverage with no omissions.
 
-```typescript filename="src/example-full-keyword-coverage.ts" showLineNumbers copy
+```typescript title="src/example-full-keyword-coverage.ts" showLineNumbers copy
 import { createKeywordCoverageScorer } from "@mastra/evals/scorers/code";
 
 const scorer = createKeywordCoverageScorer();
 
-const input = 'JavaScript frameworks like React and Vue';
-const output = 'Popular JavaScript frameworks include React and Vue for web development';
+const input = "JavaScript frameworks like React and Vue";
+const output =
+  "Popular JavaScript frameworks include React and Vue for web development";
 
 const result = await scorer.run({
-  input: [{ role: 'user', content: input }],
-  output: { role: 'assistant', text: output },
+  input: [{ role: "user", content: input }],
+  output: { role: "assistant", text: output },
 });
 
-console.log('Score:', result.score);
-console.log('AnalyzeStepResult:', result.analyzeStepResult);
+console.log("Score:", result.score);
+console.log("AnalyzeStepResult:", result.analyzeStepResult);
 ```
 
 #### Full coverage output
@@ -140,21 +144,21 @@ A score of 1 indicates that all expected keywords were found in the response. Th
 
 In this example, the response includes some, but not all, of the important keywords from the input. The score reflects partial coverage, with key terms either missing or only partially matched.
 
-```typescript filename="src/example-partial-keyword-coverage.ts" showLineNumbers copy
+```typescript title="src/example-partial-keyword-coverage.ts" showLineNumbers copy
 import { createKeywordCoverageScorer } from "@mastra/evals/scorers/code";
 
 const scorer = createKeywordCoverageScorer();
 
-const input = 'TypeScript offers interfaces, generics, and type inference';
-const output = 'TypeScript provides type inference and some advanced features';
+const input = "TypeScript offers interfaces, generics, and type inference";
+const output = "TypeScript provides type inference and some advanced features";
 
 const result = await scorer.run({
-  input: [{ role: 'user', content: input }],
-  output: { role: 'assistant', text: output },
+  input: [{ role: "user", content: input }],
+  output: { role: "assistant", text: output },
 });
 
-console.log('Score:', result.score);
-console.log('AnalyzeStepResult:', result.analyzeStepResult);
+console.log("Score:", result.score);
+console.log("AnalyzeStepResult:", result.analyzeStepResult);
 ```
 
 #### Partial coverage output
@@ -175,21 +179,22 @@ A score of 0.5 indicates that only half of the expected keywords were found in t
 
 In this example, the response includes very few of the important keywords from the input. The score reflects minimal coverage, with most key terms missing or unaccounted for.
 
-```typescript filename="src/example-minimal-keyword-coverage.ts" showLineNumbers copy
+```typescript title="src/example-minimal-keyword-coverage.ts" showLineNumbers copy
 import { createKeywordCoverageScorer } from "@mastra/evals/scorers/code";
 
 const scorer = createKeywordCoverageScorer();
 
-const input = 'Machine learning models require data preprocessing, feature engineering, and hyperparameter tuning';
-const output = 'Data preparation is important for models';
+const input =
+  "Machine learning models require data preprocessing, feature engineering, and hyperparameter tuning";
+const output = "Data preparation is important for models";
 
 const result = await scorer.run({
-  input: [{ role: 'user', content: input }],
-  output: { role: 'assistant', text: output },
+  input: [{ role: "user", content: input }],
+  output: { role: "assistant", text: output },
 });
 
-console.log('Score:', result.score);
-console.log('AnalyzeStepResult:', result.analyzeStepResult);
+console.log("Score:", result.score);
+console.log("AnalyzeStepResult:", result.analyzeStepResult);
 ```
 
 #### Minimal coverage output
@@ -214,11 +219,11 @@ You can create a `KeywordCoverageMetric` instance with default settings. No addi
 const metric = new KeywordCoverageMetric();
 ```
 
-> See [KeywordCoverageScorer](/reference/scorers/keyword-coverage.mdx) for a full list of configuration options.
+> See [KeywordCoverageScorer](/reference/scorers/keyword-coverage) for a full list of configuration options.
 
 ## Related
 
 - [Completeness Scorer](./completeness)
 - [Content Similarity Scorer](./content-similarity)
 - [Answer Relevancy Scorer](./answer-relevancy)
-- [Textual Difference Scorer](./textual-difference)
+- [Textual Difference Scorer](./textual-difference)

package/.docs/raw/reference/scorers/mastra-scorer.mdx

@@ -16,9 +16,8 @@ Use the `createScorer` factory function, which returns a `MastraScorer` instance
 ```typescript
 const scorer = createScorer({
   name: "My Custom Scorer",
-  description: "Evaluates responses based on custom criteria"
-})
-.generateScore(({ run, results }) => {
+  description: "Evaluates responses based on custom criteria",
+}).generateScore(({ run, results }) => {
   // scoring logic
   return 0.85;
 });
@@ -35,7 +34,9 @@ const result = await scorer.run({
   input: "What is machine learning?",
   output: "Machine learning is a subset of artificial intelligence...",
   runId: "optional-run-id",
-  runtimeContext: { /* optional context */ }
+  runtimeContext: {
+    /* optional context */
+  },
 });
 ```
 
@@ -47,13 +48,15 @@ const result = await scorer.run({
       name: "input",
       type: "any",
       required: true,
-      description: "Input data to be evaluated. Can be any type depending on your scorer's requirements.",
+      description:
+        "Input data to be evaluated. Can be any type depending on your scorer's requirements.",
     },
     {
       name: "output",
       type: "any",
       required: true,
-      description: "Output data to be evaluated. Can be any type depending on your scorer's requirements.",
+      description:
+        "Output data to be evaluated. Can be any type depending on your scorer's requirements.",
     },
     {
       name: "runId",
@@ -65,13 +68,15 @@ const result = await scorer.run({
       name: "runtimeContext",
       type: "any",
       required: false,
-      description: "Optional runtime context from the agent or workflow step being evaluated.",
+      description:
+        "Optional runtime context from the agent or workflow step being evaluated.",
     },
     {
       name: "groundTruth",
       type: "any",
       required: false,
-      description: "Optional expected or reference output for comparison during scoring. Automatically passed when using runExperiment.",
+      description:
+        "Optional expected or reference output for comparison during scoring. Automatically passed when using runExperiment.",
     },
   ]}
 />
@@ -93,7 +98,8 @@ const result = await scorer.run({
     {
       name: "reason",
       type: "string",
-      description: "Explanation for the score, if generateReason step was defined (optional).",
+      description:
+        "Explanation for the score, if generateReason step was defined (optional).",
     },
     {
       name: "preprocessStepResult",
@@ -120,7 +126,7 @@ const result = await scorer.run({
       type: "string",
       description: "Generate score prompt, if defined (optional).",
     },
-        {
+    {
       name: "generateReasonPrompt",
       type: "string",
       description: "Generate reason prompt, if defined (optional).",
@@ -133,7 +139,7 @@ const result = await scorer.run({
 When you call `.run()`, the MastraScorer executes the defined steps in this order:
 
 1. **preprocess** (optional) - Extracts or transforms data
-2. **analyze** (optional) - Processes the input/output and preprocessed data  
+2. **analyze** (optional) - Processes the input/output and preprocessed data
 3. **generateScore** (required) - Computes the numerical score
 4. **generateReason** (optional) - Provides explanation for the score
 
@@ -144,34 +150,34 @@ Each step receives the results from previous steps, allowing you to build comple
 ```typescript
 const scorer = createScorer({
   name: "Quality Scorer",
-  description: "Evaluates response quality"
-})
-.preprocess(({ run }) => {
-  // Extract key information
-  return { wordCount: run.output.split(' ').length };
-})
-.analyze(({ run, results }) => {
-  // Analyze the response
-  const hasSubstance = results.preprocessStepResult.wordCount > 10;
-  return { hasSubstance };
+  description: "Evaluates response quality",
 })
-.generateScore(({ results }) => {
-  // Calculate score
-  return results.analyzeStepResult.hasSubstance ? 1.0 : 0.0;
-})
-.generateReason(({ score, results }) => {
-  // Explain the score
-  const wordCount = results.preprocessStepResult.wordCount;
-  return `Score: ${score}. Response has ${wordCount} words.`;
-});
+  .preprocess(({ run }) => {
+    // Extract key information
+    return { wordCount: run.output.split(" ").length };
+  })
+  .analyze(({ run, results }) => {
+    // Analyze the response
+    const hasSubstance = results.preprocessStepResult.wordCount > 10;
+    return { hasSubstance };
+  })
+  .generateScore(({ results }) => {
+    // Calculate score
+    return results.analyzeStepResult.hasSubstance ? 1.0 : 0.0;
+  })
+  .generateReason(({ score, results }) => {
+    // Explain the score
+    const wordCount = results.preprocessStepResult.wordCount;
+    return `Score: ${score}. Response has ${wordCount} words.`;
+  });
 
 // Use the scorer
 const result = await scorer.run({
   input: "What is machine learning?",
-  output: "Machine learning is a subset of artificial intelligence..."
+  output: "Machine learning is a subset of artificial intelligence...",
 });
 
-console.log(result.score);  // 1.0
+console.log(result.score); // 1.0
 console.log(result.reason); // "Score: 1.0. Response has 12 words."
 ```
 
@@ -179,4 +185,4 @@ console.log(result.reason); // "Score: 1.0. Response has 12 words."
 
 MastraScorer instances can be used for agents and workflow steps
 
-See the [createScorer reference](./create-scorer) for detailed information on defining custom scoring logic.
+See the [createScorer reference](./create-scorer) for detailed information on defining custom scoring logic.