@mastra/mcp-docs-server 1.0.0-beta.13 → 1.0.0-beta.14

package/.docs/raw/reference/vectors/pg.mdx

@@ -374,7 +374,7 @@ Returns an array of index names as strings.
 
 Returns:
 
-```typescript copy
+```typescript
 interface PGIndexStats {
   dimension: number;
   count: number;
@@ -434,7 +434,7 @@ Update a single vector by ID or by metadata filter. Either `id` or `filter` must
 
 Updates an existing vector by ID or filter. At least one of vector or metadata must be provided in the update object.
 
-```typescript copy
+```typescript
 // Update by ID
 await pgVector.updateVector({
   indexName: "my_vectors",
@@ -474,7 +474,7 @@ await pgVector.updateVector({
 
 Deletes a single vector by ID from the specified index.
 
-```typescript copy
+```typescript
 await pgVector.deleteVector({ indexName: "my_vectors", id: "vector123" });
 ```
 
@@ -534,7 +534,7 @@ Closes the database connection pool. Should be called when done using the store.
 
 Builds or rebuilds an index with specified metric and configuration. Will drop any existing index before creating the new one.
 
-```typescript copy
+```typescript
 // Define HNSW index
 await pgVector.buildIndex("my_vectors", "cosine", {
   type: "hnsw",
@@ -562,7 +562,7 @@ await pgVector.buildIndex("my_vectors", "cosine", {
 
 Query results are returned in this format:
 
-```typescript copy
+```typescript
 interface QueryResult {
   id: string;
   score: number;
@@ -575,7 +575,7 @@ interface QueryResult {
 
 The store throws typed errors that can be caught:
 
-```typescript copy
+```typescript
 try {
   await store.query({
     indexName: "index_name",
@@ -641,6 +641,53 @@ This enables advanced usage such as running direct SQL queries, managing transac
 
 This design supports advanced use cases but requires careful resource management by the user.
 
+## Usage Example
+
+### Local embeddings with fastembed
+
+Embeddings are numeric vectors used by memory's `semanticRecall` to retrieve related messages by meaning (not keywords). This setup uses `@mastra/fastembed` to generate vector embeddings.
+
+Install `fastembed` to get started:
+
+```bash
+npm install @mastra/fastembed@beta
+```
+
+Add the following to your agent:
+
+```typescript title="src/mastra/agents/example-pg-agent.ts"
+import { Memory } from "@mastra/memory";
+import { Agent } from "@mastra/core/agent";
+import { PostgresStore, PgVector } from "@mastra/pg";
+import { fastembed } from "@mastra/fastembed";
+
+export const pgAgent = new Agent({
+  id: "pg-agent",
+  name: "PG Agent",
+  instructions:
+    "You are an AI agent with the ability to automatically recall memories from previous interactions.",
+  model: "openai/gpt-5.1",
+  memory: new Memory({
+    storage: new PostgresStore({
+      id: 'pg-agent-storage',
+      connectionString: process.env.DATABASE_URL!,
+    }),
+    vector: new PgVector({
+      id: 'pg-agent-vector',
+      connectionString: process.env.DATABASE_URL!,
+    }),
+    embedder: fastembed,
+    options: {
+      lastMessages: 10,
+      semanticRecall: {
+        topK: 3,
+        messageRange: 2,
+      },
+    },
+  }),
+});
+```
+
 ## Related
 
 - [Metadata Filters](../rag/metadata-filters)

package/.docs/raw/reference/vectors/pinecone.mdx

@@ -184,7 +184,7 @@ Returns an array of index names as strings.
 
 Returns:
 
-```typescript copy
+```typescript
 interface IndexStats {
   dimension: number;
   count: number;
@@ -306,7 +306,7 @@ Delete multiple vectors by IDs or by metadata filter. Either `ids` or `filter` m
 
 Query results are returned in this format:
 
-```typescript copy
+```typescript
 interface QueryResult {
   id: string;
   score: number;
@@ -319,7 +319,7 @@ interface QueryResult {
 
 The store throws typed errors that can be caught:
 
-```typescript copy
+```typescript
 try {
   await store.query({
     indexName: "index_name",

package/.docs/raw/reference/vectors/qdrant.mdx

@@ -137,7 +137,7 @@ Returns an array of index names as strings.
 
 Returns:
 
-```typescript copy
+```typescript
 interface IndexStats {
   dimension: number;
   count: number;
@@ -239,7 +239,7 @@ Delete multiple vectors by IDs or by metadata filter. Either `ids` or `filter` m
 
 Query results are returned in this format:
 
-```typescript copy
+```typescript
 interface QueryResult {
   id: string;
   score: number;
@@ -252,7 +252,7 @@ interface QueryResult {
 
 The store throws typed errors that can be caught:
 
-```typescript copy
+```typescript
 try {
   await store.query({
     indexName: "index_name",

package/.docs/raw/reference/vectors/s3vectors.mdx

@@ -14,13 +14,13 @@ The `S3Vectors` class provides vector search using [Amazon S3 Vectors (Preview)]
 
 ## Installation
 
-```bash copy
+```bash
 npm install @mastra/s3vectors@beta
 ```
 
 ## Usage Example
 
-```typescript copy showLineNumbers
+```typescript
 import { S3Vectors } from "@mastra/s3vectors";
 
 const store = new S3Vectors({
@@ -214,7 +214,7 @@ Returns information about the index.
 
 Returns:
 
-```typescript copy
+```typescript
 interface IndexStats {
   dimension: number;
   count: number; // computed via ListVectors pagination (O(n))
@@ -305,7 +305,7 @@ Closes the underlying AWS SDK HTTP handler to free sockets.
 
 Query results are returned in this format:
 
-```typescript copy
+```typescript
 interface QueryResult {
   id: string;
   score: number; // 1/(1 + distance)
@@ -337,7 +337,7 @@ S3 Vectors supports a strict subset of operators and value types. The Mastra fil
 
 **Examples:**
 
-```typescript copy
+```typescript
 // Implicit AND
 { genre: { $in: ["documentary", "comedy"] }, year: { $gte: 2020 } }
 
@@ -359,7 +359,7 @@ S3 Vectors supports a strict subset of operators and value types. The Mastra fil
 
 The store throws typed errors that can be caught:
 
-```typescript copy
+```typescript
 try {
   await store.query({
     indexName: "index-name",

package/.docs/raw/reference/vectors/turbopuffer.mdx

@@ -170,7 +170,7 @@ Returns an array of index names as strings.
 
 Returns:
 
-```typescript copy
+```typescript
 interface IndexStats {
   dimension: number;
   count: number;
@@ -268,7 +268,7 @@ Delete multiple vectors by IDs or by metadata filter. Either `ids` or `filter` m
 
 Query results are returned in this format:
 
-```typescript copy
+```typescript
 interface QueryResult {
   id: string;
   score: number;
@@ -281,7 +281,7 @@ interface QueryResult {
 
 The `schemaConfigForIndex` option allows you to define explicit schemas for different indexes:
 
-```typescript copy
+```typescript
 schemaConfigForIndex: (indexName: string) => {
   // Mastra's default embedding model and index for memory messages:
   if (indexName === "memory_messages_384") {
@@ -304,7 +304,7 @@ schemaConfigForIndex: (indexName: string) => {
 
 The store throws typed errors that can be caught:
 
-```typescript copy
+```typescript
 try {
   await store.query({
     indexName: "index_name",

package/.docs/raw/reference/vectors/upstash.mdx

@@ -164,7 +164,7 @@ Returns an array of index names (namespaces) as strings.
 
 Returns:
 
-```typescript copy
+```typescript
 interface IndexStats {
   dimension: number;
   count: number;
@@ -238,7 +238,7 @@ Upstash Vector supports hybrid search that combines semantic search (dense vecto
 
 ### Basic Hybrid Usage
 
-```typescript copy
+```typescript
 import { UpstashVector } from "@mastra/upstash";
 
 const vectorStore = new UpstashVector({
@@ -275,7 +275,7 @@ const results = await vectorStore.query({
 
 ### Advanced Hybrid Search Options
 
-```typescript copy
+```typescript
 import { FusionAlgorithm, QueryMode } from "@upstash/vector";
 
 // Query with specific fusion algorithm
@@ -307,7 +307,7 @@ const sparseResults = await vectorStore.query({
 
 ### Updating Hybrid Vectors
 
-```typescript copy
+```typescript
 // Update both dense and sparse components
 await vectorStore.updateVector({
   indexName: "hybrid-index",
@@ -324,7 +324,7 @@ await vectorStore.updateVector({
 
 Query results are returned in this format:
 
-```typescript copy
+```typescript
 interface QueryResult {
   id: string;
   score: number;
@@ -337,7 +337,7 @@ interface QueryResult {
 
 The store throws typed errors that can be caught:
 
-```typescript copy
+```typescript
 try {
   await store.query({
     indexName: "index_name",
@@ -358,6 +358,55 @@ Required environment variables:
 - `UPSTASH_VECTOR_URL`: Your Upstash Vector database URL
 - `UPSTASH_VECTOR_TOKEN`: Your Upstash Vector API token
 
+## Usage Example
+
+### Local embeddings with fastembed
+
+Embeddings are numeric vectors used by memory's `semanticRecall` to retrieve related messages by meaning (not keywords). This setup uses `@mastra/fastembed` to generate vector embeddings.
+
+Install `fastembed` to get started:
+
+```bash
+npm install @mastra/fastembed@beta
+```
+
+Add the following to your agent:
+
+```typescript title="src/mastra/agents/example-upstash-agent.ts"
+import { Memory } from "@mastra/memory";
+import { Agent } from "@mastra/core/agent";
+import { UpstashStore, UpstashVector } from "@mastra/upstash";
+import { fastembed } from "@mastra/fastembed";
+
+export const upstashAgent = new Agent({
+  id: "upstash-agent",
+  name: "Upstash Agent",
+  instructions:
+    "You are an AI agent with the ability to automatically recall memories from previous interactions.",
+  model: "openai/gpt-5.1",
+  memory: new Memory({
+    storage: new UpstashStore({
+      id: 'upstash-agent-storage',
+      url: process.env.UPSTASH_REDIS_REST_URL!,
+      token: process.env.UPSTASH_REDIS_REST_TOKEN!,
+    }),
+    vector: new UpstashVector({
+      id: 'upstash-agent-vector',
+      url: process.env.UPSTASH_VECTOR_REST_URL!,
+      token: process.env.UPSTASH_VECTOR_REST_TOKEN!,
+    }),
+    embedder: fastembed,
+    options: {
+      lastMessages: 10,
+      semanticRecall: {
+        topK: 3,
+        messageRange: 2,
+      },
+    },
+  }),
+});
+```
+
 ## Related
 
 - [Metadata Filters](../rag/metadata-filters)

package/.docs/raw/reference/vectors/vectorize.mdx

@@ -135,7 +135,7 @@ Returns an array of index names as strings.
 
 Returns:
 
-```typescript copy
+```typescript
 interface IndexStats {
   dimension: number;
   count: number;
@@ -259,7 +259,7 @@ Deletes a vector and its associated metadata for a specific ID within an index.
 
 Query results are returned in this format:
 
-```typescript copy
+```typescript
 interface QueryResult {
   id: string;
   score: number;
@@ -272,7 +272,7 @@ interface QueryResult {
 
 The store throws typed errors that can be caught:
 
-```typescript copy
+```typescript
 try {
   await store.query({
     indexName: "index_name",

package/.docs/raw/reference/workflows/run-methods/cancel.mdx

@@ -9,7 +9,7 @@ The `.cancel()` method cancels a workflow run, stopping execution and cleaning u
 
 ## Usage example
 
-```typescript showLineNumbers copy
+```typescript
 const run = await workflow.createRun();
 
 await run.cancel();
@@ -43,7 +43,7 @@ await run.cancel();
 
 ## Extended usage example
 
-```typescript showLineNumbers copy
+```typescript
 const run = await workflow.createRun();
 
 try {

package/.docs/raw/reference/workflows/run-methods/restart.mdx

@@ -9,13 +9,11 @@ The `.restart()` method restarts an active workflow run that lost connection to
 
 ## Usage example
 
-```typescript showLineNumbers copy
+```typescript
 const run = await workflow.createRun();
 
 const result = await run.start({ inputData: { value: "initial data" } });
 
-//.. server connection lost,
-
 const restartedResult = await run.restart();
 ```
 

package/.docs/raw/reference/workflows/run-methods/resume.mdx

@@ -9,7 +9,7 @@ The `.resume()` method resumes a suspended workflow run with new data, allowing
 
 ## Usage example
 
-```typescript showLineNumbers copy
+```typescript
 const run = await workflow.createRun();
 
 const result = await run.start({ inputData: { value: "initial data" } });
@@ -177,7 +177,7 @@ if (result.status === "suspended") {
 
 ## Extended usage example
 
-```typescript showLineNumbers copy
+```typescript
 if (result.status === "suspended") {
   const resumedResults = await run.resume({
     step: result.suspended[0],

package/.docs/raw/reference/workflows/run-methods/start.mdx

@@ -9,7 +9,7 @@ The `.start()` method starts a workflow run with input data, allowing you to exe
 
 ## Usage example
 
-```typescript showLineNumbers copy
+```typescript
 const run = await workflow.createRun();
 
 const result = await run.start({
@@ -168,7 +168,7 @@ const result = await run.start({
 
 ## Extended usage example
 
-```typescript showLineNumbers copy
+```typescript
 import { RequestContext } from "@mastra/core/request-context";
 
 const run = await workflow.createRun();

package/.docs/raw/reference/workflows/run-methods/startAsync.mdx

@@ -9,7 +9,7 @@ The `.startAsync()` method starts a workflow run without waiting for completion.
 
 ## Usage example
 
-```typescript showLineNumbers copy
+```typescript
 const run = await workflow.createRun();
 
 // Fire-and-forget - returns immediately
@@ -123,7 +123,7 @@ Use `startAsync()` instead of `start()` when:
 
 After calling `startAsync()`, you can check the workflow status using:
 
-```typescript showLineNumbers copy
+```typescript
 // Get the execution result (including step outputs)
 const result = await workflow.getWorkflowRunExecutionResult(runId);
 

package/.docs/raw/reference/workflows/run-methods/timeTravel.mdx

@@ -9,7 +9,7 @@ The `.timeTravel()` method re-executes a workflow starting from any specific ste
 
 ## Usage example
 
-```typescript showLineNumbers copy
+```typescript
 const run = await workflow.createRun();
 
 const result = await run.timeTravel({
@@ -213,7 +213,7 @@ const result = await run.timeTravel({
 
 ### Time travel with custom context
 
-```typescript showLineNumbers copy
+```typescript
 const result = await run.timeTravel({
   step: "step2",
   context: {
@@ -230,7 +230,7 @@ const result = await run.timeTravel({
 
 ### Time travel to nested workflow step
 
-```typescript showLineNumbers copy
+```typescript
 // Using dot notation
 const result = await run.timeTravel({
   step: "nestedWorkflow.step3",
@@ -246,7 +246,7 @@ const result = await run.timeTravel({
 
 ### Time travel with initial state
 
-```typescript showLineNumbers copy
+```typescript
 const result = await run.timeTravel({
   step: "step2",
   inputData: { value: 10 },
@@ -259,7 +259,7 @@ const result = await run.timeTravel({
 
 ### Time travel with nested workflows context
 
-```typescript showLineNumbers copy
+```typescript
 const result = await run.timeTravel({
   step: "nestedWorkflow.step3",
   context: {

package/.docs/raw/reference/workflows/run.mdx

@@ -9,7 +9,7 @@ The `Run` class represents a workflow execution instance, providing methods to s
 
 ## Usage example
 
-```typescript showLineNumbers copy
+```typescript
 const run = await workflow.createRun();
 
 const result = await run.start({

package/.docs/raw/reference/workflows/step.mdx

@@ -10,7 +10,7 @@ It can take either a tool or an agent as a parameter to automatically create a s
 
 ## Usage example
 
-```typescript title="src/mastra/workflows/test-workflow.ts" showLineNumbers copy
+```typescript title="src/mastra/workflows/test-workflow.ts"
 import { createWorkflow, createStep } from "@mastra/core/workflows";
 import { z } from "zod";
 
@@ -38,7 +38,7 @@ You can create a step directly from an agent. The step will use the agent's name
 
 ### Basic agent step
 
-```typescript title="src/mastra/workflows/test-workflow.ts" showLineNumbers copy
+```typescript title="src/mastra/workflows/test-workflow.ts"
 import { testAgent } from "../agents/test-agent";
 
 const agentStep = createStep(testAgent);
@@ -50,7 +50,7 @@ const agentStep = createStep(testAgent);
 
 Pass `structuredOutput` to have the agent return typed structured data:
 
-```typescript title="src/mastra/workflows/test-workflow.ts" showLineNumbers copy
+```typescript title="src/mastra/workflows/test-workflow.ts"
 const articleSchema = z.object({
   title: z.string(),
   summary: z.string(),

package/.docs/raw/reference/workflows/workflow-methods/branch.mdx

@@ -9,7 +9,7 @@ The `.branch()` method creates conditional branches between workflow steps, allo
 
 ## Usage example
 
-```typescript copy
+```typescript
 workflow.branch([
   [async ({ context }) => true, step1],
   [async ({ context }) => false, step2],

package/.docs/raw/reference/workflows/workflow-methods/commit.mdx

@@ -9,7 +9,7 @@ The `.commit()` method finalizes the workflow and returns the final result.
 
 ## Usage example
 
-```typescript copy
+```typescript
 workflow.then(step1).commit();
 ```
 

package/.docs/raw/reference/workflows/workflow-methods/create-run.mdx

@@ -9,7 +9,7 @@ The `.createRun()` method creates a new workflow run instance, allowing you to e
 
 ## Usage example
 
-```typescript copy
+```typescript
 await workflow.createRun();
 ```
 
@@ -53,7 +53,7 @@ await workflow.createRun();
 
 ## Extended usage example
 
-```typescript showLineNumbers copy
+```typescript
 const workflow = mastra.getWorkflow("workflow");
 
 const run = await workflow.createRun();
@@ -69,7 +69,7 @@ const result = await run.start({
 
 The `resourceId` parameter associates a workflow run with a specific resource, such as a user or tenant. This is useful for multi-tenant applications or when you need to track which user initiated a workflow.
 
-```typescript showLineNumbers copy
+```typescript
 const workflow = mastra.getWorkflow("workflow");
 
 // Create a run associated with a specific user

package/.docs/raw/reference/workflows/workflow-methods/dountil.mdx

@@ -9,7 +9,7 @@ The `.dountil()` method executes a step until a condition is met. It always runs
 
 ## Usage example
 
-```typescript copy
+```typescript
 workflow.dountil(step1, async ({ inputData }) => true);
 ```
 

package/.docs/raw/reference/workflows/workflow-methods/dowhile.mdx

@@ -9,7 +9,7 @@ The `.dowhile()` method executes a step while a condition is met. It always runs
 
 ## Usage example
 
-```typescript copy
+```typescript
 workflow.dowhile(step1, async ({ inputData }) => true);
 ```
 

package/.docs/raw/reference/workflows/workflow-methods/foreach.mdx

@@ -9,7 +9,7 @@ The `.foreach()` method creates a loop that executes a step for each item in an
 
 ## Usage example
 
-```typescript copy
+```typescript
 workflow.foreach(step1, { concurrency: 2 });
 ```
 
@@ -67,7 +67,7 @@ If you need to run multiple operations per item, use a nested workflow as the st
 
 `.foreach()` always outputs an array. Each element in the output array corresponds to the result of processing the element at the same index in the input array.
 
-```typescript copy
+```typescript
 // Input: [{ value: 1 }, { value: 2 }, { value: 3 }]
 // Step adds 10 to each value
 // Output: [{ value: 11 }, { value: 12 }, { value: 13 }]
@@ -77,7 +77,7 @@ If you need to run multiple operations per item, use a nested workflow as the st
 
 When you chain `.then()` after `.foreach()`, the next step receives the entire output array as its input. This allows you to aggregate or process all results together.
 
-```typescript copy
+```typescript
 workflow
   .foreach(processItemStep)    // Output: array of processed items
   .then(aggregateStep)         // Input: the entire array
@@ -88,7 +88,7 @@ workflow
 
 Use `.map()` to transform the array output before passing it to the next step:
 
-```typescript copy
+```typescript
 workflow
   .foreach(processItemStep)
   .map(async ({ inputData }) => ({
@@ -103,7 +103,7 @@ workflow
 
 When you chain `.foreach()` calls, each operates on the array from the previous step:
 
-```typescript copy
+```typescript
 workflow
   .foreach(stepA)    // If input is [a, b, c], output is [A, B, C]
   .foreach(stepB)    // Operates on [A, B, C], output is [A', B', C']
@@ -112,7 +112,7 @@ workflow
 
 If a step inside `.foreach()` returns an array, the output becomes an array of arrays. Use `.map()` with `.flat()` to flatten:
 
-```typescript copy
+```typescript
 workflow
   .foreach(chunkStep)           // Output: [[chunk1, chunk2], [chunk3, chunk4]]
   .map(async ({ inputData }) => inputData.flat())  // Output: [chunk1, chunk2, chunk3, chunk4]