> ## Documentation Index > Fetch the complete documentation index at: https://docs.decimal.app/llms.txt > Use this file to discover all available pages before exploring further. # Delete a knowledge article > Deletes a knowledge article. Your AI agent stops using it within a few minutes. An article imported from a helpdesk comes back on its next sync if it still exists there. Delete it in the helpdesk first. ## OpenAPI ````yaml /openapi-v0.yaml delete /v0/knowledge/articles/{id} openapi: 3.1.0 info: title: Decimal Chat API version: v0 description: > ## Authentication All endpoints require a Bearer token: ``` Authorization: Bearer sk-de-... ``` API tokens are created in the Decimal dashboard under Settings → API keys. Every endpoint except `GET /v0/me` requires a scope, and a token without it gets `403` with code `forbidden`. Scopes: `chat:read`, `chat:write`, `chat:escalate`, `tickets:read`, `tickets:delete`, `knowledge:read`, `knowledge:delete`, `audit_logs:read`, `pull_requests:read`, `gaps:read`, `automations:read`. ## Quick Start ```bash # 1. Send a message curl -X POST https://api.getdecimal.ai/v0/chat \ -H "Authorization: Bearer sk-de-..." \ -H "Content-Type: application/json" \ -d '{"message": "How do I configure SSO?"}' # → 202 { "conversation_id": "abc123", "status": "processing" } # 2. Poll until complete curl https://api.getdecimal.ai/v0/chat/abc123 \ -H "Authorization: Bearer sk-de-..." # → 200 { "status": "completed", "messages": [...] } ``` ### Continue a conversation ```bash curl -X POST https://api.getdecimal.ai/v0/chat \ -H "Authorization: Bearer sk-de-..." \ -H "Content-Type: application/json" \ -d '{"message": "Can you show me the SAML setup?", "conversation_id": "abc123"}' ``` ## Rate Limiting Every response includes rate limit headers: - `X-RateLimit-Limit`: Requests allowed per minute - `X-RateLimit-Remaining`: Requests remaining in current window - `X-RateLimit-Reset`: Unix timestamp when the window resets Rate limits apply at two levels: - **Per API token:** 120 requests/min - **Per organization:** 600 requests/min across all tokens Some endpoints also have a lower per-organization limit of their own. The stricter limit applies. Headers report the limit with the fewest requests remaining. Contact support for higher limits. ## Idempotency Endpoints that create something accept an `Idempotency-Key` header. Retrying with the same key within 24 hours returns the original response instead of running the request again, with an `Idempotent-Replayed: true` header. Only successful responses are saved, so a request that failed can be retried with the same key. Reusing a key for a different path or request body returns `409 Conflict`. ## Request IDs Every response includes a `Request-Id` header. Include it when you contact support. contact: name: Decimal Support url: https://getdecimal.ai servers: - url: https://api.getdecimal.ai description: Production - url: http://localhost:3000 description: Local development security: - BearerAuth: [] tags: - name: Chat description: >- Send messages and get AI-powered answers from your public knowledge base and code. - name: Escalation description: Escalate conversations to external ticketing integrations. - name: Tickets description: Manage tickets synced from your helpdesk. - name: Pull requests description: Read pull requests from your connected repositories. - name: Gaps description: Read changes Decimal proposes to your knowledge base, docs, and code. - name: Automations description: >- Read your automations: what starts them, what they do, and how their runs went. - name: Audit logs description: Read who did what in your organization. Requires audit logs on your plan. - name: Knowledge description: Read and delete the articles your AI agent answers from. - name: Utility description: Token introspection. paths: /v0/knowledge/articles/{id}: parameters: - $ref: '#/components/parameters/KnowledgeArticleId' delete: tags: - Knowledge summary: Delete a knowledge article description: > Deletes a knowledge article. Your AI agent stops using it within a few minutes. An article imported from a helpdesk comes back on its next sync if it still exists there. Delete it in the helpdesk first. operationId: deleteKnowledgeArticle responses: '204': description: Article deleted. headers: Request-Id: $ref: '#/components/headers/Request-Id' X-RateLimit-Limit: $ref: '#/components/headers/X-RateLimit-Limit' X-RateLimit-Remaining: $ref: '#/components/headers/X-RateLimit-Remaining' X-RateLimit-Reset: $ref: '#/components/headers/X-RateLimit-Reset' '401': $ref: '#/components/responses/Unauthorized' '403': $ref: '#/components/responses/Forbidden' '404': $ref: '#/components/responses/NotFound' '429': $ref: '#/components/responses/RateLimited' '500': $ref: '#/components/responses/InternalError' security: - BearerAuth: - knowledge:delete components: parameters: KnowledgeArticleId: name: id in: path required: true schema: type: integer description: Knowledge article ID. headers: Request-Id: description: Unique ID for this request. Include it when you contact support. schema: type: string X-RateLimit-Limit: description: Maximum requests allowed per minute. schema: type: integer X-RateLimit-Remaining: description: Requests remaining in the current window. schema: type: integer X-RateLimit-Reset: description: Unix timestamp when the rate limit window resets. schema: type: integer responses: Unauthorized: description: >- Missing or invalid API key. Correct the Authorization header before retrying. content: application/json: schema: $ref: '#/components/schemas/Error' example: error: code: unauthorized message: Invalid or expired API token Forbidden: description: Valid API key but insufficient scope. content: application/json: schema: $ref: '#/components/schemas/Error' example: error: code: forbidden message: Insufficient permissions NotFound: description: Resource not found. content: application/json: schema: $ref: '#/components/schemas/Error' example: error: code: not_found message: Resource not found RateLimited: description: Rate limit exceeded. headers: Request-Id: $ref: '#/components/headers/Request-Id' X-RateLimit-Limit: $ref: '#/components/headers/X-RateLimit-Limit' X-RateLimit-Remaining: $ref: '#/components/headers/X-RateLimit-Remaining' X-RateLimit-Reset: $ref: '#/components/headers/X-RateLimit-Reset' Retry-After: description: Seconds until the rate limit resets. schema: type: integer content: application/json: schema: $ref: '#/components/schemas/Error' example: error: code: rate_limited message: Too many requests retryable: true InternalError: description: Unexpected server error. content: application/json: schema: $ref: '#/components/schemas/Error' example: error: code: internal_error message: An internal error occurred retryable: true schemas: Error: type: object properties: error: type: object properties: code: type: string enum: - bad_request - unauthorized - forbidden - not_found - conflict - rate_limited - internal_error description: Machine-readable error code. message: type: string description: Human-readable error message. retryable: description: Whether the client should retry the request. type: boolean required: - code - message required: - error securitySchemes: BearerAuth: type: http scheme: bearer description: | API token with `sk-de-` prefix. Created in the Decimal dashboard under Settings → API Tokens. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.