@mastra/mcp-docs-server 0.0.0-commonjs-20250414101718

package/.docs/raw/reference/rag/extract-params.mdx

@@ -0,0 +1,226 @@
+---
+title: "Reference: ExtractParams | Document Processing | RAG | Mastra Docs"
+description: Documentation for metadata extraction configuration in Mastra.
+---
+
+# ExtractParams
+
+ExtractParams configures metadata extraction from document chunks using LLM analysis.
+
+## Example
+
+```typescript showLineNumbers copy
+import { MDocument } from "@mastra/rag";
+
+const doc = MDocument.fromText(text);
+const chunks = await doc.chunk({
+  extract: {
+    title: true,    // Extract titles using default settings
+    summary: true,  // Generate summaries using default settings
+    keywords: true  // Extract keywords using default settings
+  }
+});
+
+// Example output:
+// chunks[0].metadata = {
+//   documentTitle: "AI Systems Overview",
+//   sectionSummary: "Overview of artificial intelligence concepts and applications",
+//   excerptKeywords: "KEYWORDS: AI, machine learning, algorithms"
+// }
+```
+
+## Parameters
+
+The `extract` parameter accepts the following fields:
+
+<PropertiesTable
+  content={[
+    {
+      name: "title",
+      type: "boolean | TitleExtractorsArgs",
+      isOptional: true,
+      description:
+        "Enable title extraction. Set to true for default settings, or provide custom configuration.",
+    },
+    {
+      name: "summary",
+      type: "boolean | SummaryExtractArgs",
+      isOptional: true,
+      description:
+        "Enable summary extraction. Set to true for default settings, or provide custom configuration.",
+    },
+    {
+      name: "questions",
+      type: "boolean | QuestionAnswerExtractArgs",
+      isOptional: true,
+      description:
+        "Enable question generation. Set to true for default settings, or provide custom configuration.",
+    },
+    {
+      name: "keywords",
+      type: "boolean | KeywordExtractArgs",
+      isOptional: true,
+      description:
+        "Enable keyword extraction. Set to true for default settings, or provide custom configuration.",
+    },
+  ]}
+/>
+
+## Extractor Arguments
+
+### TitleExtractorsArgs
+
+<PropertiesTable
+  content={[
+    {
+      name: "llm",
+      type: "LLM",
+      isOptional: true,
+      description: "Custom LLM instance to use for title extraction"
+    },
+    {
+      name: "nodes",
+      type: "number",
+      isOptional: true,
+      description: "Number of title nodes to extract"
+    },
+    {
+      name: "nodeTemplate",
+      type: "string",
+      isOptional: true,
+      description: "Custom prompt template for title node extraction. Must include {context} placeholder"
+    },
+    {
+      name: "combineTemplate",
+      type: "string",
+      isOptional: true,
+      description: "Custom prompt template for combining titles. Must include {context} placeholder"
+    }
+  ]}
+/>
+
+### SummaryExtractArgs
+
+<PropertiesTable
+  content={[
+    {
+      name: "llm",
+      type: "LLM",
+      isOptional: true,
+      description: "Custom LLM instance to use for summary extraction"
+    },
+    {
+      name: "summaries",
+      type: "('self' | 'prev' | 'next')[]",
+      isOptional: true,
+      description: "List of summary types to generate. Can only include 'self' (current chunk), 'prev' (previous chunk), or 'next' (next chunk)"
+    },
+    {
+      name: "promptTemplate",
+      type: "string",
+      isOptional: true,
+      description: "Custom prompt template for summary generation. Must include {context} placeholder"
+    }
+  ]}
+/>
+
+### QuestionAnswerExtractArgs
+
+<PropertiesTable
+  content={[
+    {
+      name: "llm",
+      type: "LLM",
+      isOptional: true,
+      description: "Custom LLM instance to use for question generation"
+    },
+    {
+      name: "questions",
+      type: "number",
+      isOptional: true,
+      description: "Number of questions to generate"
+    },
+    {
+      name: "promptTemplate",
+      type: "string",
+      isOptional: true,
+      description: "Custom prompt template for question generation. Must include both {context} and {numQuestions} placeholders"
+    },
+    {
+      name: "embeddingOnly",
+      type: "boolean",
+      isOptional: true,
+      description: "If true, only generate embeddings without actual questions"
+    }
+  ]}
+/>
+
+### KeywordExtractArgs
+
+<PropertiesTable
+  content={[
+    {
+      name: "llm",
+      type: "LLM",
+      isOptional: true,
+      description: "Custom LLM instance to use for keyword extraction"
+    },
+    {
+      name: "keywords",
+      type: "number",
+      isOptional: true,
+      description: "Number of keywords to extract"
+    },
+    {
+      name: "promptTemplate",
+      type: "string",
+      isOptional: true,
+      description: "Custom prompt template for keyword extraction. Must include both {context} and {maxKeywords} placeholders"
+    }
+  ]}
+/>
+
+## Advanced Example
+
+```typescript showLineNumbers copy
+import { MDocument } from "@mastra/rag";
+
+const doc = MDocument.fromText(text);
+const chunks = await doc.chunk({
+  extract: {
+    // Title extraction with custom settings
+    title: {
+      nodes: 2,  // Extract 2 title nodes
+      nodeTemplate: "Generate a title for this: {context}",
+      combineTemplate: "Combine these titles: {context}"
+    },
+
+    // Summary extraction with custom settings
+    summary: {
+      summaries: ["self"],  // Generate summaries for current chunk
+      promptTemplate: "Summarize this: {context}"
+    },
+
+    // Question generation with custom settings
+    questions: {
+      questions: 3,  // Generate 3 questions
+      promptTemplate: "Generate {numQuestions} questions about: {context}",
+      embeddingOnly: false
+    },
+
+    // Keyword extraction with custom settings
+    keywords: {
+      keywords: 5,  // Extract 5 keywords
+      promptTemplate: "Extract {maxKeywords} key terms from: {context}"
+    }
+  }
+});
+
+// Example output:
+// chunks[0].metadata = {
+//   documentTitle: "AI in Modern Computing",
+//   sectionSummary: "Overview of AI concepts and their applications in computing",
+//   questionsThisExcerptCanAnswer: "1. What is machine learning?\n2. How do neural networks work?",
+//   excerptKeywords: "1. Machine learning\n2. Neural networks\n3. Training data"
+// }
+```

package/.docs/raw/reference/rag/graph-rag.mdx

@@ -0,0 +1,182 @@
+---
+title: "Reference: GraphRAG | Graph-based RAG | RAG | Mastra Docs"
+description: Documentation for the GraphRAG class in Mastra, which implements a graph-based approach to retrieval augmented generation.
+---
+
+# GraphRAG
+
+The `GraphRAG` class implements a graph-based approach to retrieval augmented generation. It creates a knowledge graph from document chunks where nodes represent documents and edges represent semantic relationships, enabling both direct similarity matching and discovery of related content through graph traversal.
+
+## Basic Usage
+
+```typescript
+import { GraphRAG } from "@mastra/rag";
+
+const graphRag = new GraphRAG({
+  dimension: 1536,
+  threshold: 0.7
+});
+
+// Create the graph from chunks and embeddings
+graphRag.createGraph(documentChunks, embeddings);
+
+// Query the graph with embedding
+const results = await graphRag.query({
+  query: queryEmbedding,
+  topK: 10,
+  randomWalkSteps: 100,
+  restartProb: 0.15
+});
+```
+
+## Constructor Parameters
+
+<PropertiesTable
+  content={[
+    {
+      name: "dimension",
+      type: "number",
+      description: "Dimension of the embedding vectors",
+      isOptional: true,
+      defaultValue: "1536",
+    },
+    {
+      name: "threshold",
+      type: "number",
+      description: "Similarity threshold for creating edges between nodes (0-1)",
+      isOptional: true,
+      defaultValue: "0.7",
+    }
+  ]}
+/>
+
+## Methods
+
+### createGraph
+
+Creates a knowledge graph from document chunks and their embeddings.
+
+```typescript
+createGraph(chunks: GraphChunk[], embeddings: GraphEmbedding[]): void
+```
+
+#### Parameters
+<PropertiesTable
+  content={[
+    {
+      name: "chunks",
+      type: "GraphChunk[]",
+      description: "Array of document chunks with text and metadata",
+      isOptional: false,
+    },
+    {
+      name: "embeddings",
+      type: "GraphEmbedding[]",
+      description: "Array of embeddings corresponding to chunks",
+      isOptional: false,
+    }
+  ]}
+/>
+
+### query
+
+Performs a graph-based search combining vector similarity and graph traversal.
+
+```typescript
+query({
+  query,
+  topK = 10,
+  randomWalkSteps = 100,
+  restartProb = 0.15
+}: {
+  query: number[];
+  topK?: number;
+  randomWalkSteps?: number;
+  restartProb?: number;
+}): RankedNode[]
+```
+
+#### Parameters
+<PropertiesTable
+  content={[
+    {
+      name: "query",
+      type: "number[]",
+      description: "Query embedding vector",
+      isOptional: false,
+    },
+    {
+      name: "topK",
+      type: "number",
+      description: "Number of results to return",
+      isOptional: true,
+      defaultValue: "10",
+    },
+    {
+      name: "randomWalkSteps",
+      type: "number",
+      description: "Number of steps in random walk",
+      isOptional: true,
+      defaultValue: "100",
+    },
+    {
+      name: "restartProb",
+      type: "number",
+      description: "Probability of restarting walk from query node",
+      isOptional: true,
+      defaultValue: "0.15",
+    }
+  ]}
+/>
+
+#### Returns
+Returns an array of `RankedNode` objects, where each node contains:
+
+<PropertiesTable
+  content={[
+    {
+      name: "id",
+      type: "string",
+      description: "Unique identifier for the node",
+    },
+    {
+      name: "content",
+      type: "string",
+      description: "Text content of the document chunk",
+    },
+    {
+      name: "metadata",
+      type: "Record<string, any>",
+      description: "Additional metadata associated with the chunk",
+    },
+    {
+      name: "score",
+      type: "number",
+      description: "Combined relevance score from graph traversal",
+    }
+  ]}
+/>
+
+## Advanced Example
+
+```typescript
+const graphRag = new GraphRAG({
+  dimension: 1536,
+  threshold: 0.8  // Stricter similarity threshold
+});
+
+// Create graph from chunks and embeddings
+graphRag.createGraph(documentChunks, embeddings);
+
+// Query with custom parameters
+const results = await graphRag.query({
+  query: queryEmbedding,
+  topK: 5,
+  randomWalkSteps: 200,
+  restartProb: 0.2
+});
+```
+
+## Related
+
+- [createGraphRAGTool](../tools/graph-rag-tool)