> ## Documentation Index > Fetch the complete documentation index at: https://docs.beta.adapter.com/llms.txt > Use this file to discover all available pages before exploring further. # Create Ask Job > Ask a question asynchronously: returns a job id immediately; poll GET /knowledge/ask/jobs/{job_id} until `status` leaves "running". Same grounding and citations as /knowledge/ask, without the long-poll timeout — use for deep or broad questions that may exceed the sync window. ## OpenAPI ````yaml POST /v1/knowledge/ask/jobs openapi: 3.1.0 info: title: Adapter API description: Connect and sync data from any SaaS tool. version: 0.1.0 servers: - url: https://api.adapter.com security: - ApiKeyAuth: [] tags: - name: connections description: Manage OAuth connections to data sources. paths: /v1/knowledge/ask/jobs: post: tags: - knowledge summary: Create Ask Job description: >- Ask a question asynchronously: returns a job id immediately; poll GET /knowledge/ask/jobs/{job_id} until `status` leaves "running". Same grounding and citations as /knowledge/ask, without the long-poll timeout — use for deep or broad questions that may exceed the sync window. operationId: create_ask_job requestBody: content: application/json: schema: $ref: '#/components/schemas/PublicAskRequest' required: true responses: '202': description: Successful Response content: application/json: schema: additionalProperties: true type: object title: Response Create Ask Job '401': content: application/json: schema: $ref: '#/components/schemas/AuthenticationErrorModel' description: Unauthorized '403': content: application/json: schema: $ref: '#/components/schemas/PermissionDeniedErrorModel' description: Forbidden '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' '429': description: >- Rate limit exceeded for the caller's tier. RFC 9457 problem+json body; IETF RateLimit-* headers and Retry-After are set. headers: Retry-After: description: Seconds to wait before retrying (RFC 9110). schema: type: integer RateLimit-Limit: description: Requests allowed per window. schema: type: integer RateLimit-Remaining: description: Requests remaining in the current window. schema: type: integer RateLimit-Reset: description: Delta-seconds until the window resets. schema: type: integer RateLimit-Policy: description: Active policy, e.g. '5;w=60'. schema: type: string content: application/problem+json: schema: $ref: '#/components/schemas/RateLimitProblemDetail' application/json: schema: $ref: '#/components/schemas/RateLimitProblemDetail' '500': content: application/json: schema: $ref: '#/components/schemas/InternalServerErrorModel' description: Internal Server Error '503': description: Service Unavailable content: application/json: schema: $ref: '#/components/schemas/ServiceUnavailableErrorModel' components: schemas: PublicAskRequest: properties: query: type: string maxLength: 2000 minLength: 1 title: Query examples: - What are our top blockers for Q1? timezone: anyOf: - type: string - type: 'null' title: Timezone description: >- IANA timezone identifier (e.g. "America/New_York") for resolving relative time references like "today" or "last week". Defaults to UTC. examples: - America/New_York metadata: anyOf: - additionalProperties: type: string type: object maxProperties: 20 - type: 'null' title: Metadata description: >- Restrict the evidence the model can ground its answer in to rows whose `metadata` contains ALL the given key/value pairs (AND-of-exact-match). Max 20 keys; string values only. examples: - env: staging additionalProperties: false type: object required: - query title: PublicAskRequest AuthenticationErrorModel: properties: error_code: type: string const: authentication_error title: Error Code default: authentication_error message: type: string title: Message default: Invalid or missing credentials. details: anyOf: - additionalProperties: true type: object - type: 'null' title: Details type: object title: AuthenticationErrorModel PermissionDeniedErrorModel: properties: error_code: type: string const: permission_denied title: Error Code default: permission_denied message: type: string title: Message default: You do not have permission to perform this action. details: anyOf: - additionalProperties: true type: object - type: 'null' title: Details type: object title: PermissionDeniedErrorModel HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError RateLimitProblemDetail: properties: type: type: string title: Type description: >- Stable problem-type URI, e.g. '{api_base_url}/errors/rate_limit_exceeded'. title: type: string const: Too Many Requests title: Title default: Too Many Requests status: type: integer const: 429 title: Status default: 429 detail: type: string title: Detail description: Human-readable explanation, including the retry hint. error_code: type: string const: rate_limit_exceeded title: Error Code default: rate_limit_exceeded endpoint: type: string title: Endpoint description: Logical endpoint the limit applies to (e.g. 'ask', 'search'). tier: type: string title: Tier description: The caller's billing tier (e.g. 'free'). limit: type: integer title: Limit description: Requests allowed per window for this tier + endpoint. remaining: type: integer title: Remaining description: Requests remaining in the current window (0 when blocked). window_seconds: type: integer title: Window Seconds description: Length of the fixed rate-limit window, in seconds. retry_after: type: integer title: Retry After description: Seconds to wait before retrying (mirrors the Retry-After header). instance: anyOf: - type: string - type: 'null' title: Instance description: The request path that was limited. type: object required: - type - detail - endpoint - tier - limit - remaining - window_seconds - retry_after title: RateLimitProblemDetail description: >- The 429 response body, exactly as ``RateLimitError.problem_detail`` renders it — RFC 9457 Problem Details, served as ``application/problem+json`` alongside the IETF ``RateLimit-*`` headers and ``Retry-After``. (Distinct from the legacy ``RateLimitErrorModel`` shape, which does not match what the handler emits.) InternalServerErrorModel: properties: error_code: type: string const: internal_server_error title: Error Code default: internal_server_error message: type: string title: Message default: An unexpected error occurred. details: anyOf: - additionalProperties: true type: object - type: 'null' title: Details type: object title: InternalServerErrorModel ServiceUnavailableErrorModel: properties: error_code: type: string const: service_unavailable title: Error Code default: service_unavailable message: type: string title: Message default: >- The service is currently experiencing issues. Please try again later. details: anyOf: - additionalProperties: true type: object - type: 'null' title: Details type: object title: ServiceUnavailableErrorModel ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError securitySchemes: ApiKeyAuth: type: http scheme: bearer description: Pass your `pk_live_...` API key as a Bearer token. ````