reset-embedders
Reset the embedders configuration for a specified Meilisearch index to manage document embeddings and improve search accuracy via the Model Context Protocol.
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)The handler function for the 'reset-embedders' tool that deletes the embedders settings via API for the specified index.async ({ indexUid }) => { try { const response = await apiClient.delete(`/indexes/${indexUid}/settings/embedders`); return { content: [{ type: "text", text: JSON.stringify(response.data, null, 2) }], }; } catch (error) { return createErrorResponse(error); } }
- src/tools/vector-tools.ts:110-112 (schema)Zod input schema defining the required 'indexUid' parameter.{ indexUid: z.string().describe("Unique identifier of the index"), },
- src/tools/vector-tools.ts:107-123 (registration)The server.tool() call that registers the 'reset-embedders' tool with name, description, schema, and inline handler function.server.tool( "reset-embedders", "Reset the embedders configuration for an index", { indexUid: z.string().describe("Unique identifier of the index"), }, async ({ indexUid }) => { try { const response = await apiClient.delete(`/indexes/${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)Invocation of registerVectorTools which includes the registration of 'reset-embedders' among other vector tools.registerVectorTools(server);