embed_text
Generate text embeddings using Gemini models to convert text into numerical vectors for analysis and processing.
Instructions
Generate embeddings for text using Gemini embedding models
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Text to generate embeddings for | |
| model | No | Embedding model to use | text-embedding-004 |
Implementation Reference
- src/enhanced-stdio-server.ts:830-868 (handler)The main handler function for the embed_text tool. It calls the Gemini API to generate text embeddings and returns the embedding vector as JSON.
private async embedText(id: any, args: any): Promise<MCPResponse> { try { const model = args.model || 'text-embedding-004'; const result = await this.genAI.models.embedContent({ model, contents: args.text }); return { jsonrpc: '2.0', id, result: { content: [ { type: 'text', text: JSON.stringify({ embedding: result.embeddings?.[0]?.values || [], model }) } ], metadata: { model, dimensions: result.embeddings?.[0]?.values?.length || 0 } } }; } catch (error) { return { jsonrpc: '2.0', id, error: { code: -32603, message: error instanceof Error ? error.message : 'Internal error' } }; } } - src/utils/validation.ts:102-105 (schema)Zod schema defining the input parameters for the embed_text tool: required 'text' string and optional 'model' enum.
embedText: z.object({ text: z.string().min(1, 'Text is required'), model: z.enum(['text-embedding-004', 'text-multilingual-embedding-002']).optional() }), - src/enhanced-stdio-server.ts:352-371 (registration)Tool registration entry in the getAvailableTools() method, defining the tool's name, description, and input schema for MCP protocol.
{ name: 'embed_text', description: 'Generate embeddings for text using Gemini embedding models', inputSchema: { type: 'object', properties: { text: { type: 'string', description: 'Text to generate embeddings for' }, model: { type: 'string', description: 'Embedding model to use', enum: ['text-embedding-004', 'text-multilingual-embedding-002'], default: 'text-embedding-004' } }, required: ['text'] } }, - src/enhanced-stdio-server.ts:499-500 (registration)Dispatch case in handleToolCall switch statement that routes embed_text calls to the handler method.
case 'embed_text': return await this.embedText(request.id, args);