> ## Documentation Index > Fetch the complete documentation index at: https://docs.agentset.ai/llms.txt > Use this file to discover all available pages before exploring further. # Retrieve a document > Retrieve the info for a document. ## OpenAPI ````yaml get /v1/namespace/{namespaceId}/documents/{documentId} openapi: 3.1.1 info: title: AgentsetAPI description: Agentset is agentic rag-as-a-service version: 0.0.1 contact: name: Agentset Support email: support@agentset.ai url: https://api.agentset.ai/ license: name: MIT License url: https://github.com/agentset-ai/agentset/blob/main/LICENSE.md servers: - url: https://api.agentset.ai description: Production API security: [] paths: /v1/namespace/{namespaceId}/documents/{documentId}: get: tags: - Documents summary: Retrieve a document description: Retrieve the info for a document. operationId: getDocument parameters: - $ref: '#/components/parameters/NamespaceIdRef' - $ref: '#/components/parameters/DocumentIdRef' - $ref: '#/components/parameters/TenantIdRef' responses: '200': description: The retrieved ingest job content: application/json: schema: type: object properties: success: type: boolean const: true data: $ref: '#/components/schemas/document' required: - success - data additionalProperties: false '400': $ref: '#/components/responses/400' '401': $ref: '#/components/responses/401' '403': $ref: '#/components/responses/403' '404': $ref: '#/components/responses/404' '409': $ref: '#/components/responses/409' '410': $ref: '#/components/responses/410' '422': $ref: '#/components/responses/422' '429': $ref: '#/components/responses/429' '500': $ref: '#/components/responses/500' security: - token: [] x-codeSamples: - lang: TypeScript source: | import { Agentset } from "agentset"; const agentset = new Agentset({ apiKey: 'agentset_xxx' }); const ns = agentset.namespace('ns_xxx'); const document = await ns.documents.get("doc_123"); console.log(document); - lang: python label: Python (SDK) source: |- from agentset import Agentset with Agentset( namespace_id="ns_123", x_tenant_id="", token="AGENTSET_API_KEY", ) as a_client: res = a_client.documents.get(document_id="doc_123") # Handle response print(res) components: parameters: NamespaceIdRef: in: path name: namespaceId schema: type: string examples: - ns_123 description: The id of the namespace (prefixed with ns_) x-speakeasy-globals-hidden: true required: true description: The id of the namespace (prefixed with ns_) DocumentIdRef: in: path name: documentId schema: type: string examples: - doc_123 description: The id of the document (prefixed with doc_) required: true description: The id of the document (prefixed with doc_) TenantIdRef: in: header name: x-tenant-id schema: description: >- Optional tenant id to use for the request. If not provided, the namespace will be used directly. Must be alphanumeric and up to 64 characters. type: string pattern: ^[A-Za-z0-9]{1,64}$ description: >- Optional tenant id to use for the request. If not provided, the namespace will be used directly. Must be alphanumeric and up to 64 characters. schemas: document: type: object properties: id: type: string description: The unique ID of the document. ingestJobId: type: string description: The ingest job ID of the document. name: default: null description: The name of the document. anyOf: - type: string - type: 'null' tenantId: default: null description: The tenant ID of the ingest job. anyOf: - type: string - type: 'null' status: $ref: '#/components/schemas/document-status' error: default: null description: >- The error message of the document. Only exists when the status is failed. anyOf: - type: string - type: 'null' source: oneOf: - type: object properties: type: type: string const: TEXT text: type: string description: The text to ingest. required: - type - text additionalProperties: false - type: object properties: type: type: string const: FILE fileUrl: type: string format: uri description: The URL of the file to ingest. required: - type - fileUrl additionalProperties: false - type: object properties: type: type: string const: MANAGED_FILE key: type: string description: The key of the managed file to ingest. required: - type - key additionalProperties: false - type: object properties: type: type: string const: CRAWLED_PAGE title: description: The title of the crawled page. type: string description: description: The description of the crawled page. type: string language: description: The language of the crawled page. type: string required: - type additionalProperties: false - type: object properties: type: type: string const: YOUTUBE_VIDEO videoId: type: string description: The ID of the youtube video. duration: description: The duration of the youtube video in seconds. type: number required: - type - videoId additionalProperties: false description: The source of the document. type: object properties: default: null anyOf: - type: object properties: fileSize: type: number description: The size of the file in bytes. mimeType: default: null anyOf: - type: string description: The MIME type of the file. - type: 'null' required: - fileSize - mimeType additionalProperties: false description: The properties of the document. - type: 'null' config: default: null anyOf: - $ref: '#/components/schemas/document-configOutput' - type: 'null' totalChunks: type: number description: The total number of chunks. totalTokens: type: number description: The total number of tokens. totalCharacters: type: number description: The total number of characters. totalPages: type: number description: >- The total number of pages. Will be 0 if the document is not paged (e.g. PDF). createdAt: description: The date and time the document was created. type: string queuedAt: default: null anyOf: - type: string - type: 'null' description: The date and time the document was queued. preProcessingAt: default: null anyOf: - type: string - type: 'null' description: The date and time the document was pre-processed. processingAt: default: null anyOf: - type: string - type: 'null' description: The date and time the document was processed. completedAt: default: null anyOf: - type: string - type: 'null' description: The date and time the document was completed. failedAt: default: null anyOf: - type: string - type: 'null' description: The date and time the document failed. required: - id - ingestJobId - name - tenantId - status - error - source - properties - config - totalChunks - totalTokens - totalCharacters - totalPages - createdAt - queuedAt - preProcessingAt - processingAt - completedAt - failedAt additionalProperties: false title: Document document-status: type: string enum: - BACKLOG - QUEUED - QUEUED_FOR_RESYNC - QUEUED_FOR_DELETE - PRE_PROCESSING - PROCESSING - DELETING - CANCELLING - COMPLETED - FAILED - CANCELLED description: The status of the document. document-configOutput: type: object properties: chunkSize: type: integer minimum: 32 maximum: 9007199254740991 description: >- Chunk size (in characters). Controls approximately how much text is included in each chunk. Defaults to `2048`. delimiter: type: string description: Delimiter to use for separating text before chunking. metadata: type: object propertyNames: type: string additionalProperties: anyOf: - type: string - type: number - type: boolean - type: array items: type: string description: >- Custom metadata to be added to the ingested documents. It cannot contain nested objects; only string, number, boolean, and array of strings are allowed. languageCode: $ref: '#/components/schemas/language-code' description: >- Language code to use for text processing (for example, `en`, `ar`, or `fr`). When omitted, the partition API will attempt to detect the language automatically. mode: $ref: '#/components/schemas/mode' disableImageExtraction: type: boolean description: >- Disable image extraction from the document. When combined with `useLlm`, images may still be automatically captioned by the partition API. Defaults to `false`. disableImageCaptions: type: boolean description: >- Disable synthetic image captions/descriptions in output. Images will be rendered as plain img tags without alt text. Defaults to `false`. chartUnderstanding: type: boolean description: >- Enable chart understanding. This will extract the data from the charts in the document. Defaults to `false`. keepPageheaderInOutput: type: boolean description: Keep the page header in the output. Defaults to `false`. keepPagefooterInOutput: type: boolean description: Keep the page footer in the output. Defaults to `false`. forceOcr: type: boolean description: >- Force OCR on the document even if selectable text exists. Useful for scanned documents with unreliable embedded text. Defaults to `false`. deprecated: true x-speakeasy-deprecation-message: We no longer support this option. disableOcrMath: type: boolean description: >- Disable inline math recognition in OCR. This can be useful if the document contains content that is frequently misclassified as math. Defaults to `false`. deprecated: true x-speakeasy-deprecation-message: We no longer support this option. useLlm: type: boolean description: >- Enable LLM-assisted parsing to improve tables, forms, inline math, and layout detection. May increase latency and token usage. Defaults to `true`. deprecated: true x-speakeasy-deprecation-message: We no longer support this option. Use `mode` instead. chunkOverlap: type: number description: >- [Deprecated] Custom chunk overlap (in characters) between consecutive chunks. Helps preserve context across chunk boundaries. deprecated: true x-speakeasy-deprecation-message: We no longer support this option. Use `chunkSize` instead. maxChunkSize: type: number description: >- [Deprecated] Hard chunk size. This option is ignored by the current partition pipeline and kept only for backwards compatibility. deprecated: true x-speakeasy-deprecation-message: We no longer support this option. Use `chunkSize` instead. chunkingStrategy: type: string enum: - basic - by_title description: >- [Deprecated] The legacy chunking strategy. This option is ignored by the current partition pipeline and kept only for backwards compatibility. deprecated: true x-speakeasy-deprecation-message: We no longer support this option. strategy: type: string enum: - auto - fast - hi_res - ocr_only description: >- [Deprecated] Legacy processing strategy used by the previous partition API. This option is ignored by the current pipeline and kept only for backwards compatibility. deprecated: true x-speakeasy-deprecation-message: We no longer support this option. Use `mode` instead. additionalProperties: false description: The document config. language-code: type: string enum: - af - am - ar - bg - bn - ca - cs - cy - da - de - en - es - et - fa - fi - fr - ga - gl - he - hi - hr - hu - id - is - it - jp - kr - lt - lv - mk - ms - mt - ne - nl - 'no' - pl - pt - ro - ru - sk - sl - sr - sv - sw - ta - te - th - tl - tr - uk - ur - vi - zh - zu mode: type: string enum: - fast - balanced - accurate description: >- Processing mode for the parser. `fast` favors speed, `accurate` (pro subscription only) favors quality and layout fidelity, and `balanced` offers a compromise between the two. Defaults to `balanced`. responses: '400': description: >- The server cannot or will not process the request due to something that is perceived to be a client error (e.g., malformed request syntax, invalid request message framing, or deceptive request routing). content: application/json: schema: x-speakeasy-name-override: BadRequest type: object properties: success: type: boolean example: false error: type: object properties: code: type: string enum: - bad_request description: A short code indicating the error code returned. example: bad_request message: x-speakeasy-error-message: true type: string description: A human readable explanation of what went wrong. example: The requested resource was not found. doc_url: type: string description: >- A link to our documentation with more details about this error code example: https://docs.agentset.ai/api-reference/errors#bad-request required: - code - message required: - success - error '401': description: >- Although the HTTP standard specifies "unauthorized", semantically this response means "unauthenticated". That is, the client must authenticate itself to get the requested response. content: application/json: schema: x-speakeasy-name-override: Unauthorized type: object properties: success: type: boolean example: false error: type: object properties: code: type: string enum: - unauthorized description: A short code indicating the error code returned. example: unauthorized message: x-speakeasy-error-message: true type: string description: A human readable explanation of what went wrong. example: The requested resource was not found. doc_url: type: string description: >- A link to our documentation with more details about this error code example: https://docs.agentset.ai/api-reference/errors#unauthorized required: - code - message required: - success - error '403': description: >- The client does not have access rights to the content; that is, it is unauthorized, so the server is refusing to give the requested resource. Unlike 401 Unauthorized, the client's identity is known to the server. content: application/json: schema: x-speakeasy-name-override: Forbidden type: object properties: success: type: boolean example: false error: type: object properties: code: type: string enum: - forbidden description: A short code indicating the error code returned. example: forbidden message: x-speakeasy-error-message: true type: string description: A human readable explanation of what went wrong. example: The requested resource was not found. doc_url: type: string description: >- A link to our documentation with more details about this error code example: https://docs.agentset.ai/api-reference/errors#forbidden required: - code - message required: - success - error '404': description: The server cannot find the requested resource. content: application/json: schema: x-speakeasy-name-override: NotFound type: object properties: success: type: boolean example: false error: type: object properties: code: type: string enum: - not_found description: A short code indicating the error code returned. example: not_found message: x-speakeasy-error-message: true type: string description: A human readable explanation of what went wrong. example: The requested resource was not found. doc_url: type: string description: >- A link to our documentation with more details about this error code example: https://docs.agentset.ai/api-reference/errors#not-found required: - code - message required: - success - error '409': description: >- This response is sent when a request conflicts with the current state of the server. content: application/json: schema: x-speakeasy-name-override: Conflict type: object properties: success: type: boolean example: false error: type: object properties: code: type: string enum: - conflict description: A short code indicating the error code returned. example: conflict message: x-speakeasy-error-message: true type: string description: A human readable explanation of what went wrong. example: The requested resource was not found. doc_url: type: string description: >- A link to our documentation with more details about this error code example: https://docs.agentset.ai/api-reference/errors#conflict required: - code - message required: - success - error '410': description: >- This response is sent when the requested content has been permanently deleted from server, with no forwarding address. content: application/json: schema: x-speakeasy-name-override: InviteExpired type: object properties: success: type: boolean example: false error: type: object properties: code: type: string enum: - invite_expired description: A short code indicating the error code returned. example: invite_expired message: x-speakeasy-error-message: true type: string description: A human readable explanation of what went wrong. example: The requested resource was not found. doc_url: type: string description: >- A link to our documentation with more details about this error code example: >- https://docs.agentset.ai/api-reference/errors#invite-expired required: - code - message required: - success - error '422': description: >- The request was well-formed but was unable to be followed due to semantic errors. content: application/json: schema: x-speakeasy-name-override: UnprocessableEntity type: object properties: success: type: boolean example: false error: type: object properties: code: type: string enum: - unprocessable_entity description: A short code indicating the error code returned. example: unprocessable_entity message: x-speakeasy-error-message: true type: string description: A human readable explanation of what went wrong. example: The requested resource was not found. doc_url: type: string description: >- A link to our documentation with more details about this error code example: >- https://docs.agentset.ai/api-reference/errors#unprocessable-entity required: - code - message required: - success - error '429': description: >- The user has sent too many requests in a given amount of time ("rate limiting") content: application/json: schema: x-speakeasy-name-override: RateLimitExceeded type: object properties: success: type: boolean example: false error: type: object properties: code: type: string enum: - rate_limit_exceeded description: A short code indicating the error code returned. example: rate_limit_exceeded message: x-speakeasy-error-message: true type: string description: A human readable explanation of what went wrong. example: The requested resource was not found. doc_url: type: string description: >- A link to our documentation with more details about this error code example: >- https://docs.agentset.ai/api-reference/errors#rate-limit_exceeded required: - code - message required: - success - error '500': description: The server has encountered a situation it does not know how to handle. content: application/json: schema: x-speakeasy-name-override: InternalServerError type: object properties: success: type: boolean example: false error: type: object properties: code: type: string enum: - internal_server_error description: A short code indicating the error code returned. example: internal_server_error message: x-speakeasy-error-message: true type: string description: A human readable explanation of what went wrong. example: The requested resource was not found. doc_url: type: string description: >- A link to our documentation with more details about this error code example: >- https://docs.agentset.ai/api-reference/errors#internal-server_error required: - code - message required: - success - error securitySchemes: token: type: http description: Default authentication mechanism scheme: bearer x-speakeasy-example: AGENTSET_API_KEY ````