ollama_embed
Generate numerical vector embeddings from text input using Ollama models for semantic analysis and similarity tasks.
Instructions
Generate embeddings for text input. Returns numerical vector representations.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model | Yes | Name of the model to use | |
| input | Yes | Text input. For batch processing, provide a JSON-encoded array of strings, e.g., ["text1", "text2"] | |
| format | No | json |
Implementation Reference
- src/tools/embed.ts:10-22 (handler)Core handler function that calls the Ollama embed API to generate embeddings for the given input and model, then formats the response.export async function embedWithModel( ollama: Ollama, model: string, input: string | string[], format: ResponseFormat ): Promise<string> { const response = await ollama.embed({ model, input, }); return formatResponse(JSON.stringify(response), format); }
- src/tools/embed.ts:24-52 (registration)Tool definition export that registers 'ollama_embed' with name, description, inline input schema reference, and handler function which validates args using EmbedInputSchema and delegates to embedWithModel.export const toolDefinition: ToolDefinition = { name: 'ollama_embed', description: 'Generate embeddings for text input. Returns numerical vector representations.', inputSchema: { type: 'object', properties: { model: { type: 'string', description: 'Name of the model to use', }, input: { type: 'string', description: 'Text input. For batch processing, provide a JSON-encoded array of strings, e.g., ["text1", "text2"]', }, format: { type: 'string', enum: ['json', 'markdown'], default: 'json', }, }, required: ['model', 'input'], }, handler: async (ollama: Ollama, args: Record<string, unknown>, format: ResponseFormat) => { const validated = EmbedInputSchema.parse(args); return embedWithModel(ollama, validated.model, validated.input, format); }, };
- src/schemas.ts:112-144 (schema)Zod input validation schema for ollama_embed tool, with model name validation and special transform for input to handle both single string and JSON-encoded string arrays.* Schema for ollama_embed tool */ export const EmbedInputSchema = z.object({ model: z.string().min(1), input: z.string().transform((val, ctx) => { const trimmed = val.trim(); // If it looks like a JSON array, try to parse it if (trimmed.startsWith('[') && trimmed.endsWith(']')) { try { const parsed = JSON.parse(trimmed); if (Array.isArray(parsed)) { // Validate all elements are strings const allStrings = parsed.every((item) => typeof item === 'string'); if (allStrings) { return parsed as string[]; } else { ctx.addIssue({ code: z.ZodIssueCode.custom, message: 'Input is a JSON array but contains non-string elements', }); return z.NEVER; } } } catch (e) { // Failed to parse as JSON, treat as plain string } } // Return as plain string return trimmed; }), format: ResponseFormatSchema.default('json'), });