> ## Documentation Index > Fetch the complete documentation index at: https://supermemory.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Forget memories semantically > Describe what should be forgotten in natural language, then preview or apply the matching set. Use dry-run results with the exact-ID endpoint when you need a reviewable, drift-free workflow. ## OpenAPI ````yaml https://api.supermemory.ai/v5/openapi delete /ns/{namespace}/memories/semantic openapi: 3.1.0 info: title: supermemory API description: >- The Memory API for the AI era. OpenAPI operations include x-codeSamples for the official TypeScript and Python SDKs (Mintlify-compatible). version: 5.0.0 servers: - description: Production Server url: https://api.supermemory.ai security: - bearerAuth: [] tags: - name: Ingest description: Ingest documents, files, URLs, conversations, and other content - name: Recall (Search) description: >- Semantic recall across your content — supports memories, hybrid, and documents modes - name: Profiles description: Maintained static, dynamic, and custom-bucket profiles scoped by namespace - name: Content Management description: List, get, update, and delete content and memories - name: Namespaces description: List and manage isolated namespaces and their settings - name: Connectors description: >- Sync external sources such as Google Drive, Notion and GitHub into a namespace - name: Organization description: Read and update organization-wide settings paths: /ns/{namespace}/memories/semantic: delete: tags: - Content Management summary: Forget memories semantically description: >- Describe what should be forgotten in natural language, then preview or apply the matching set. Use dry-run results with the exact-ID endpoint when you need a reviewable, drift-free workflow. operationId: deleteNsByNamespaceMemoriesSemantic parameters: - in: path name: namespace schema: type: string maxLength: 100 pattern: ^[a-zA-Z0-9_:-]+$ example: user_alex required: true description: >- Namespace containing the memories to forget. This can be an ID for your user, a project ID, or any other identifier you wish to use to scope memories. requestBody: required: true content: application/json: schema: type: object properties: query: type: string minLength: 1 maxLength: 2000 description: >- Natural-language description of the memories that should be forgotten example: everything about the old pricing plans dryRun: type: boolean description: >- When true, preview matching memories without changing their recall state example: true required: - query - dryRun additionalProperties: false responses: '200': content: application/json: schema: type: object properties: count: type: integer minimum: 0 maximum: 9007199254740991 description: Number of memories matched by this operation errors: type: array items: type: object properties: id: type: string description: Requested memory identifier error: type: string description: Why the memory could not be forgotten required: - id - error additionalProperties: false description: Per-memory failures for exact-ID requests matches: type: array items: type: object properties: id: type: string description: Stable identifier of the matched memory memory: type: string description: Matched memory text required: - id - memory additionalProperties: false description: >- Memories selected by the operation, whether previewed or forgotten required: - count - errors - matches additionalProperties: false description: Semantic memory forget completed or previewed '400': description: Invalid request content: application/json: schema: oneOf: - $ref: '#/components/schemas/ErrorResponse' - $ref: '#/components/schemas/ValidationErrorResponse' '401': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Unauthorized '403': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Namespace write access denied '500': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Server error x-codeSamples: - lang: typescript label: TypeScript SDK source: |- import { Supermemory } from "supermemory"; const client = new Supermemory(); // reads SUPERMEMORY_API_KEY // Preview first, then run again with dryRun: false const preview = await client.memories.forgetMatching("user_123", { query: "forget everything about the old pricing plan", dryRun: true, }); console.log(preview.matches.map((m) => m.memory)); - lang: python label: Python SDK source: |- from supermemory import Supermemory client = Supermemory() # reads SUPERMEMORY_API_KEY # Preview first, then run again with dry_run=False preview = client.memories.forget_matching( "user_123", query="forget everything about the old pricing plan", dry_run=True, ) print([m.memory for m in preview.matches]) - lang: bash label: cURL source: >- curl -X DELETE "https://api.supermemory.ai/ns/user_123/memories/semantic" \ -H "Authorization: Bearer $SUPERMEMORY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "query": "forget everything about the old pricing plan", "dryRun": true }' components: schemas: ErrorResponse: type: object properties: error: type: string description: Error message example: Invalid request parameters details: type: string description: Additional error details example: Query must be at least 1 character long required: - error ValidationErrorResponse: type: object description: Body returned when request input fails schema validation properties: success: type: boolean enum: - false error: type: array description: Validation issues items: type: object properties: message: type: string path: type: array items: oneOf: - type: string - type: number required: - message data: description: The input that failed validation required: - success - error securitySchemes: bearerAuth: scheme: bearer type: http ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.