@mastra/mcp-docs-server 1.0.0-beta.1 → 1.0.0-beta.10

package/.docs/raw/observability/tracing/overview.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Tracing | Observability | Mastra Docs"
+title: "Tracing | Observability"
 description: "Set up Tracing for Mastra applications"
 ---
 
@@ -97,7 +97,24 @@ In addition to the internal exporters, Mastra supports integration with popular
 - **[Langfuse](/docs/v1/observability/tracing/exporters/langfuse)** - Sends traces to the Langfuse open-source LLM engineering platform
 - **[LangSmith](/docs/v1/observability/tracing/exporters/langsmith)** - Pushes traces into LangSmith's observability and evaluation toolkit
 - **[OpenTelemetry](/docs/v1/observability/tracing/exporters/otel)** - Deliver traces to any OpenTelemetry-compatible observability system
-  - Supports: Dash0, Laminar, New Relic, SigNoz, Traceloop, Zipkin, and others!
+  - Supports: Dash0, Datadog, MLflow, Laminar, New Relic, SigNoz, Traceloop, Zipkin, and others!
+
+## Bridges
+
+Bridges provide bidirectional integration with external tracing systems. Unlike exporters that send trace data to external platforms, bridges create native spans in external systems and inherit context from them. This enables Mastra operations to participate in existing distributed traces.
+
+- **[OpenTelemetry Bridge](/docs/v1/observability/tracing/bridges/otel)** - Integrate with existing OpenTelemetry infrastructure
+
+### Bridges vs Exporters
+
+| Feature | Bridges | Exporters |
+| --- | --- | --- |
+| Creates native spans in external systems | Yes | No |
+| Inherits context from external systems | Yes | No |
+| Sends data to backends | Via external SDK | Directly |
+| Use case | Existing distributed tracing | Standalone Mastra tracing |
+
+You can use both together — a bridge for context propagation and exporters to send traces to additional destinations.
 
 ## Sampling Strategies
 
@@ -200,7 +217,6 @@ Use `configSelector` to choose the appropriate tracing configuration based on re
 ```ts title="src/mastra/index.ts" showLineNumbers copy
 export const mastra = new Mastra({
   observability: new Observability({
-    default: { enabled: true }, // Provides 'default' instance
     configs: {
       langfuse: {
         serviceName: "langfuse-service",
@@ -233,7 +249,7 @@ export const mastra = new Mastra({
         return "langfuse";
       }
 
-      return "default";
+      throw new Error('no config found')
     },
   }),
 });
@@ -448,6 +464,60 @@ requestContext.set("session", { data: { experimentId: "exp-999" } });
 3. **Child Span Extraction**: Child spans can also extract metadata if you pass `requestContext` when creating them
 4. **Metadata Precedence**: Explicit metadata passed to span options always takes precedence over extracted metadata
 
+### Adding Tags to Traces
+
+Tags are string labels that help you categorize and filter traces. Unlike metadata (which contains structured key-value data), tags are simple strings designed for quick filtering and organization.
+
+Use `tracingOptions.tags` to add tags when executing agents or workflows:
+
+```ts showLineNumbers copy
+// With agents
+const result = await agent.generate({
+  messages: [{ role: "user", content: "Hello" }],
+  tracingOptions: {
+    tags: ["production", "experiment-v2", "user-request"],
+  },
+});
+
+// With workflows
+const run = await mastra.getWorkflow("myWorkflow").createRun();
+const result = await run.start({
+  inputData: { data: "process this" },
+  tracingOptions: {
+    tags: ["batch-processing", "priority-high"],
+  },
+});
+```
+
+#### How Tags Work
+
+- **Root span only**: Tags are applied only to the root span of a trace (the agent run or workflow run span)
+- **Widely supported**: Tags are supported by most exporters for filtering and searching traces:
+  - **Braintrust** - Native `tags` field
+  - **Langfuse** - Native `tags` field on traces
+  - **ArizeExporter** - `tag.tags` OpenInference attribute
+  - **OtelExporter** - `mastra.tags` span attribute
+  - **OtelBridge** - `mastra.tags` span attribute
+- **Combinable with metadata**: You can use both `tags` and `metadata` in the same `tracingOptions`
+
+```ts showLineNumbers copy
+const result = await agent.generate({
+  messages: [{ role: "user", content: "Analyze this" }],
+  tracingOptions: {
+    tags: ["production", "analytics"],
+    metadata: { userId: "user-123", experimentId: "exp-456" },
+  },
+});
+```
+
+#### Common Tag Patterns
+
+- **Environment**: `"production"`, `"staging"`, `"development"`
+- **Feature flags**: `"feature-x-enabled"`, `"beta-user"`
+- **Request types**: `"user-request"`, `"batch-job"`, `"scheduled-task"`
+- **Priority levels**: `"priority-high"`, `"priority-low"`
+- **Experiments**: `"experiment-v1"`, `"control-group"`, `"treatment-a"`
+
 #### Child Spans and Metadata Extraction
 
 When creating child spans within tools or workflow steps, you can pass the `requestContext` parameter to enable metadata extraction:
@@ -619,7 +689,7 @@ console.log("Trace ID:", finalState.traceId);
 Once you have a trace ID, you can:
 
 1. **Look up traces in Studio**: Navigate to the traces view and search by ID
-2. **Query traces in external platforms**: Use the ID in Langfuse, Braintrust, or your observability platform
+2. **Query traces in external platforms**: Use the ID in Langfuse, Braintrust, MLflow, or your observability platform
 3. **Correlate with logs**: Include the trace ID in your application logs for cross-referencing
 4. **Share for debugging**: Provide trace IDs to support teams or developers for investigation
 
@@ -751,10 +821,6 @@ Mastra automatically creates spans for:
 
 ## See Also
 
-### Examples
-
-- [Basic Tracing Example](/examples/v1/observability/basic-tracing) - Working implementation
-
 ### Reference Documentation
 
 - [Configuration API](/reference/v1/observability/tracing/configuration) - ObservabilityConfig details
@@ -770,8 +836,13 @@ Mastra automatically creates spans for:
 - [Arize](/reference/v1/observability/tracing/exporters/arize) - Arize Phoenix and Arize AX integration
 - [Braintrust](/reference/v1/observability/tracing/exporters/braintrust) - Braintrust integration
 - [Langfuse](/reference/v1/observability/tracing/exporters/langfuse) - Langfuse integration
+- [MLflow](/reference/v1/observability/tracing/exporters/otel#mlflow) - MLflow OTLP endpoint setup
 - [OpenTelemetry](/reference/v1/observability/tracing/exporters/otel) - OTEL-compatible platforms
 
+### Bridges
+
+- [OpenTelemetry Bridge](/reference/v1/observability/tracing/bridges/otel) - OTEL context integration
+
 ### Processors
 
 - [Sensitive Data Filter](/docs/v1/observability/tracing/processors/sensitive-data-filter) - Data redaction

package/.docs/raw/observability/tracing/processors/sensitive-data-filter.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Sensitive Data Filter | Processors | Observability | Mastra Docs"
+title: "Sensitive Data Filter | Processors | Observability"
 description: "Protect sensitive information in your traces with automatic data redaction"
 ---
 
@@ -293,4 +293,3 @@ This ensures that processing errors don't prevent traces from being exported or
 ## Related
 
 - [SensitiveDataFilter API](/reference/v1/observability/tracing/processors/sensitive-data-filter)
-- [Basic Tracing Example](/examples/v1/observability/basic-tracing)

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

@@ -83,12 +83,8 @@ The simplest way is to use Mastra's model router with `provider/model` strings:
 import { ModelRouterEmbeddingModel } from "@mastra/core/llm";
 import { embedMany } from "ai";
 
-const embeddingModel = new ModelRouterEmbeddingModel(
-  "openai/text-embedding-3-small",
-);
-
 const { embeddings } = await embedMany({
-  model: embeddingModel,
+  model: new ModelRouterEmbeddingModel("openai/text-embedding-3-small"),
   values: chunks.map((chunk) => chunk.text),
 });
 ```
@@ -105,11 +101,11 @@ The model router automatically handles API key detection from environment variab
 You can also use AI SDK embedding models directly:
 
 ```ts showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { embedMany } from "ai";
+import { ModelRouterEmbeddingModel } from "@mastra/core/llm";
 
 const { embeddings } = await embedMany({
-  model: openai.embedding("text-embedding-3-small"),
+  model: new ModelRouterEmbeddingModel("openai/text-embedding-3-small"),
   values: chunks.map((chunk) => chunk.text),
 });
 ```
@@ -129,19 +125,22 @@ Here are some supported models:
 OpenAI (text-embedding-3 models):
 
 ```ts
+import { ModelRouterEmbeddingModel } from "@mastra/core/llm";
+
 const { embeddings } = await embedMany({
-  model: openai.embedding("text-embedding-3-small", {
+  model: new ModelRouterEmbeddingModel("openai/text-embedding-3-small"),
+  options: {
     dimensions: 256, // Only supported in text-embedding-3 and later
-  }),
+  },
   values: chunks.map((chunk) => chunk.text),
 });
 ```
 
-Google (text-embedding-004):
+Google (text-embedding-001):
 
 ```ts
 const { embeddings } = await embedMany({
-  model: google.textEmbeddingModel("text-embedding-004", {
+  model: "google/gemini-embedding-001", {
     outputDimensionality: 256, // Truncates excessive values from the end
   }),
   values: chunks.map((chunk) => chunk.text),
@@ -158,8 +157,6 @@ Here's an example showing document processing and embedding generation with both
 
 ```ts showLineNumbers copy
 import { embedMany } from "ai";
-import { openai } from "@ai-sdk/openai";
-import { cohere } from "@ai-sdk/cohere";
 
 import { MDocument } from "@mastra/rag";
 
@@ -177,16 +174,18 @@ const chunks = await doc.chunk({
 });
 
 // Generate embeddings with OpenAI
-const { embeddings: openAIEmbeddings } = await embedMany({
-  model: openai.embedding("text-embedding-3-small"),
+import { ModelRouterEmbeddingModel } from "@mastra/core/llm";
+
+const { embeddings } = await embedMany({
+  model: new ModelRouterEmbeddingModel("openai/text-embedding-3-small"),
   values: chunks.map((chunk) => chunk.text),
 });
 
 // OR
 
 // Generate embeddings with Cohere
-const { embeddings: cohereEmbeddings } = await embedMany({
-  model: cohere.embedding("embed-english-v3.0"),
+const { embeddings } = await embedMany({
+  model: "cohere/embed-english-v3.0",
   values: chunks.map((chunk) => chunk.text),
 });
 

package/.docs/raw/rag/overview.mdx

@@ -1,5 +1,5 @@
 ---
-title: "RAG (Retrieval-Augmented Generation) in Mastra | RAG | Mastra Docs"
+title: "RAG (Retrieval-Augmented Generation) in Mastra | RAG"
 description: Overview of Retrieval-Augmented Generation (RAG) in Mastra, detailing its capabilities for enhancing LLM outputs with relevant context.
 ---
 
@@ -20,7 +20,6 @@ To implement RAG, you process your documents into chunks, create embeddings, sto
 
 ```ts showLineNumbers copy
 import { embedMany } from "ai";
-import { openai } from "@ai-sdk/openai";
 import { PgVector } from "@mastra/pg";
 import { MDocument } from "@mastra/rag";
 import { z } from "zod";
@@ -36,9 +35,11 @@ const chunks = await doc.chunk({
 });
 
 // 3. Generate embeddings; we need to pass the text of each chunk
+import { ModelRouterEmbeddingModel } from "@mastra/core/llm";
+
 const { embeddings } = await embedMany({
   values: chunks.map((chunk) => chunk.text),
-  model: openai.embedding("text-embedding-3-small"),
+  model: new ModelRouterEmbeddingModel("openai/text-embedding-3-small")
 });
 
 // 4. Store in vector database

package/.docs/raw/rag/retrieval.mdx

@@ -1,5 +1,5 @@
 ---
-title: "Retrieval, Semantic Search, Reranking | RAG | Mastra Docs"
+title: "Retrieval, Semantic Search, Reranking | RAG"
 description: Guide on retrieval processes in Mastra's RAG systems, including semantic search, filtering, and re-ranking.
 ---
 
@@ -27,14 +27,14 @@ Mastra provides flexible retrieval options with support for semantic search, fil
 The simplest approach is direct semantic search. This method uses vector similarity to find chunks that are semantically similar to the query:
 
 ```ts showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { embed } from "ai";
 import { PgVector } from "@mastra/pg";
+import { ModelRouterEmbeddingModel } from "@mastra/core/llm";
 
 // Convert query to embedding
 const { embedding } = await embed({
   value: "What are the main points in the article?",
-  model: openai.embedding("text-embedding-3-small"),
+  model: new ModelRouterEmbeddingModel("openai/text-embedding-3-small"),
 });
 
 // Query vector store
@@ -52,6 +52,8 @@ const results = await pgVector.query({
 console.log(results);
 ```
 
+The `topK` parameter specifies the maximum number of most similar results to return from the vector search.
+
 Results include both the text content and a similarity score:
 
 ```ts showLineNumbers copy
@@ -70,8 +72,6 @@ Results include both the text content and a similarity score:
 ];
 ```
 
-For an example of how to use the basic retrieval method, see the [Retrieve Results](/examples/v1/rag/query/retrieve-results) example.
-
 ## Advanced Retrieval options
 
 ### Metadata Filtering
@@ -156,7 +156,7 @@ Sometimes you want to give your agent the ability to query a vector database dir
 const vectorQueryTool = createVectorQueryTool({
   vectorStoreName: "pgVector",
   indexName: "embeddings",
-  model: openai.embedding("text-embedding-3-small"),
+  model: new ModelRouterEmbeddingModel("openai/text-embedding-3-small"),
 });
 ```
 
@@ -170,14 +170,21 @@ This is particularly useful when:
 
 #### Database-Specific Configurations
 
-The Vector Query Tool supports database-specific configurations that enable you to leverage unique features and optimizations of different vector stores:
+The Vector Query Tool supports database-specific configurations that enable you to leverage unique features and optimizations of different vector stores.
+
+:::note
+These configurations are for **query-time options** like namespaces, performance tuning, and filtering—not for database connection setup. 
+
+
+Connection credentials (URLs, auth tokens) are configured when you instantiate the vector store class (e.g., `new LibSQLVector({ connectionUrl: '...' })`).
+:::
 
 ```ts showLineNumbers copy
 // Pinecone with namespace
 const pineconeQueryTool = createVectorQueryTool({
   vectorStoreName: "pinecone",
   indexName: "docs",
-  model: openai.embedding("text-embedding-3-small"),
+  model: new ModelRouterEmbeddingModel("openai/text-embedding-3-small"),
   databaseConfig: {
     pinecone: {
       namespace: "production", // Isolate data by environment
@@ -189,7 +196,7 @@ const pineconeQueryTool = createVectorQueryTool({
 const pgVectorQueryTool = createVectorQueryTool({
   vectorStoreName: "postgres",
   indexName: "embeddings",
-  model: openai.embedding("text-embedding-3-small"),
+  model: new ModelRouterEmbeddingModel("openai/text-embedding-3-small"),
   databaseConfig: {
     pgvector: {
       minScore: 0.7, // Filter low-quality results
@@ -203,7 +210,7 @@ const pgVectorQueryTool = createVectorQueryTool({
 const chromaQueryTool = createVectorQueryTool({
   vectorStoreName: "chroma",
   indexName: "documents",
-  model: openai.embedding("text-embedding-3-small"),
+  model: new ModelRouterEmbeddingModel("openai/text-embedding-3-small"),
   databaseConfig: {
     chroma: {
       where: { category: "technical" },
@@ -216,7 +223,7 @@ const chromaQueryTool = createVectorQueryTool({
 const lanceQueryTool = createVectorQueryTool({
   vectorStoreName: "lance",
   indexName: "documents",
-  model: openai.embedding("text-embedding-3-small"),
+  model: new ModelRouterEmbeddingModel("openai/text-embedding-3-small"),
   databaseConfig: {
     lance: {
       tableName: "myVectors", // Specify which table to query
@@ -272,13 +279,12 @@ When implementing filtering, these prompts are required in the agent's instructi
   <TabItem value="pgvector" label="pgVector">
 
 ```ts showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { PGVECTOR_PROMPT } from "@mastra/pg";
 
 export const ragAgent = new Agent({
   id: "rag-agent",
   name: "RAG Agent",
-  model: openai("gpt-4o-mini"),
+  model: "openai/gpt-5.1",
   instructions: `
   Process queries using the provided context. Structure responses to be concise and relevant.
   ${PGVECTOR_PROMPT}
@@ -292,13 +298,12 @@ export const ragAgent = new Agent({
   <TabItem value="pinecone" label="Pinecone">
 
 ```ts title="vector-store.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { PINECONE_PROMPT } from "@mastra/pinecone";
 
 export const ragAgent = new Agent({
   id: "rag-agent",
   name: "RAG Agent",
-  model: openai("gpt-4o-mini"),
+  model: "openai/gpt-5.1",
   instructions: `
   Process queries using the provided context. Structure responses to be concise and relevant.
   ${PINECONE_PROMPT}
@@ -312,13 +317,12 @@ export const ragAgent = new Agent({
   <TabItem value="qdrant" label="Qdrant">
 
 ```ts title="vector-store.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { QDRANT_PROMPT } from "@mastra/qdrant";
 
 export const ragAgent = new Agent({
   id: "rag-agent",
   name: "RAG Agent",
-  model: openai("gpt-4o-mini"),
+  model: "openai/gpt-5.1",
   instructions: `
   Process queries using the provided context. Structure responses to be concise and relevant.
   ${QDRANT_PROMPT}
@@ -332,13 +336,12 @@ export const ragAgent = new Agent({
   <TabItem value="chroma" label="Chroma">
 
 ```ts title="vector-store.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { CHROMA_PROMPT } from "@mastra/chroma";
 
 export const ragAgent = new Agent({
   id: "rag-agent",
   name: "RAG Agent",
-  model: openai("gpt-4o-mini"),
+  model: "openai/gpt-5.1",
   instructions: `
   Process queries using the provided context. Structure responses to be concise and relevant.
   ${CHROMA_PROMPT}
@@ -352,13 +355,12 @@ export const ragAgent = new Agent({
   <TabItem value="astra" label="Astra">
 
 ```ts title="vector-store.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { ASTRA_PROMPT } from "@mastra/astra";
 
 export const ragAgent = new Agent({
   id: "rag-agent",
   name: "RAG Agent",
-  model: openai("gpt-4o-mini"),
+  model: "openai/gpt-5.1",
   instructions: `
   Process queries using the provided context. Structure responses to be concise and relevant.
   ${ASTRA_PROMPT}
@@ -372,13 +374,12 @@ export const ragAgent = new Agent({
   <TabItem value="libsql" label="LibSQL">
 
 ```ts title="vector-store.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { LIBSQL_PROMPT } from "@mastra/libsql";
 
 export const ragAgent = new Agent({
   id: "rag-agent",
   name: "RAG Agent",
-  model: openai("gpt-4o-mini"),
+  model: "openai/gpt-5.1",
   instructions: `
   Process queries using the provided context. Structure responses to be concise and relevant.
   ${LIBSQL_PROMPT}
@@ -392,13 +393,12 @@ export const ragAgent = new Agent({
   <TabItem value="upstash" label="Upstash">
 
 ```ts title="vector-store.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { UPSTASH_PROMPT } from "@mastra/upstash";
 
 export const ragAgent = new Agent({
   id: "rag-agent",
   name: "RAG Agent",
-  model: openai("gpt-4o-mini"),
+  model: "openai/gpt-5.1",
   instructions: `
   Process queries using the provided context. Structure responses to be concise and relevant.
   ${UPSTASH_PROMPT}
@@ -412,13 +412,12 @@ export const ragAgent = new Agent({
   <TabItem value="vectorize" label="Vectorize">
 
 ```ts title="vector-store.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { VECTORIZE_PROMPT } from "@mastra/vectorize";
 
 export const ragAgent = new Agent({
   id: "rag-agent",
   name: "RAG Agent",
-  model: openai("gpt-4o-mini"),
+  model: "openai/gpt-5.1",
   instructions: `
   Process queries using the provided context. Structure responses to be concise and relevant.
   ${VECTORIZE_PROMPT}
@@ -432,13 +431,12 @@ export const ragAgent = new Agent({
   <TabItem value="mongodb" label="MongoDB">
 
 ```ts title="vector-store.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { MONGODB_PROMPT } from "@mastra/mongodb";
 
 export const ragAgent = new Agent({
   id: "rag-agent",
   name: "RAG Agent",
-  model: openai("gpt-4o-mini"),
+  model: "openai/gpt-5.1",
   instructions: `
   Process queries using the provided context. Structure responses to be concise and relevant.
   ${MONGODB_PROMPT}
@@ -452,13 +450,12 @@ export const ragAgent = new Agent({
   <TabItem value="opensearch" label="OpenSearch">
 
 ```ts title="vector-store.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { OPENSEARCH_PROMPT } from "@mastra/opensearch";
 
 export const ragAgent = new Agent({
   id: "rag-agent",
   name: "RAG Agent",
-  model: openai("gpt-4o-mini"),
+  model: "openai/gpt-5.1",
   instructions: `
   Process queries using the provided context. Structure responses to be concise and relevant.
   ${OPENSEARCH_PROMPT}
@@ -472,13 +469,12 @@ export const ragAgent = new Agent({
   <TabItem value="s3vectors" label="S3Vectors">
 
 ```ts title="vector-store.ts" showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import { S3VECTORS_PROMPT } from "@mastra/s3vectors";
 
 export const ragAgent = new Agent({
   id: "rag-agent",
   name: "RAG Agent",
-  model: openai("gpt-4o-mini"),
+  model: "openai/gpt-5.1",
   instructions: `
   Process queries using the provided context. Structure responses to be concise and relevant.
   ${S3VECTORS_PROMPT}
@@ -502,7 +498,6 @@ Initial vector similarity search can sometimes miss nuanced relevance. Re-rankin
 Here's how to use re-ranking:
 
 ```ts showLineNumbers copy
-import { openai } from "@ai-sdk/openai";
 import {
   rerankWithScorer as rerank,
   MastraAgentRelevanceScorer
@@ -516,19 +511,31 @@ const initialResults = await pgVector.query({
 });
 
 // Create a relevance scorer
-const relevanceProvider = new MastraAgentRelevanceScorer('relevance-scorer', openai("gpt-4o-mini"));
+const relevanceProvider = new MastraAgentRelevanceScorer('relevance-scorer', "openai/gpt-5.1");
 
 // Re-rank the results
 const rerankedResults = await rerank({
   results: initialResults,
   query,
-  provider: relevanceProvider,
+  scorer: relevanceProvider,
   options: {
+    weights: {
+      semantic: 0.5, // How well the content matches the query semantically
+      vector: 0.3, // Original vector similarity score
+      position: 0.2, // Preserves original result ordering
+    },
     topK: 10,
   },
 );
 ```
 
+The weights control how different factors influence the final ranking:
+
+- `semantic`: Higher values prioritize semantic understanding and relevance to the query
+- `vector`: Higher values favor the original vector similarity scores
+- `position`: Higher values help maintain the original ordering of results
+
+
 > **Note:** For semantic scoring to work properly during re-ranking, each result must include the text content in its `metadata.text` field.
 
 You can also use other relevance score providers like Cohere or ZeroEntropy:
@@ -545,8 +552,6 @@ The re-ranked results combine vector similarity with semantic understanding to i
 
 For more details about re-ranking, see the [rerank()](/reference/v1/rag/rerankWithScorer) method.
 
-For an example of how to use the re-ranking method, see the Re-ranking Results example in the examples section.
-
 ### Graph-based Retrieval
 
 For documents with complex relationships, graph-based retrieval can follow connections between chunks. This helps when:
@@ -561,7 +566,7 @@ Example setup:
 const graphQueryTool = createGraphQueryTool({
   vectorStoreName: "pgVector",
   indexName: "embeddings",
-  model: openai.embedding("text-embedding-3-small"),
+  model: new ModelRouterEmbeddingModel("openai/text-embedding-3-small"),
   graphOptions: {
     threshold: 0.7,
   },