reset-embedders
Reset embedder configurations for a Meilisearch index to restore default vector search settings and resolve embedding-related issues.
Instructions
Reset the embedders configuration for an index
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| indexUid | Yes | Unique identifier of the index |
Implementation Reference
- src/tools/vector-tools.ts:113-122 (handler)Executes the reset-embedders tool by deleting the embedders configuration for the given indexUid via the API client.async ({ indexUid }) => { try { const response = await apiClient.delete(`/indexes/${indexUid}/settings/embedders`); return { content: [{ type: "text", text: JSON.stringify(response.data, null, 2) }], }; } catch (error) { return createErrorResponse(error); } }
- src/tools/vector-tools.ts:110-112 (schema)Zod schema defining the input parameters for the reset-embedders tool.{ indexUid: z.string().describe("Unique identifier of the index"), },
- src/tools/vector-tools.ts:108-123 (registration)Registers the reset-embedders tool on the MCP server with its name, description, input schema, and handler function."reset-embedders", "Reset the embedders configuration for an index", { indexUid: z.string().describe("Unique identifier of the index"), }, async ({ indexUid }) => { try { const response = await apiClient.delete(`/indexes/${indexUid}/settings/embedders`); return { content: [{ type: "text", text: JSON.stringify(response.data, null, 2) }], }; } catch (error) { return createErrorResponse(error); } } );
- src/index.ts:68-68 (registration)Registers the vector tools module (including reset-embedders) on the main MCP server instance.registerVectorTools(server);