openapi: 3.0.3 info: title: Llama Platform Agent Data Beta API version: 0.1.0 tags: - name: Beta paths: /api/v1/classifier/jobs: post: tags: - Beta summary: Create Classify Job description: 'Create a classify job. Experimental: not production-ready and subject to change.' operationId: create_classify_job_api_v1_classifier_jobs_post security: - HTTPBearer: [] parameters: - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ClassifyJobCreate' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ClassifyJob' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' get: tags: - Beta summary: List Classify Jobs description: 'List classify jobs. Experimental: not production-ready and subject to change.' operationId: list_classify_jobs_api_v1_classifier_jobs_get security: - HTTPBearer: [] parameters: - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: page_size in: query required: false schema: anyOf: - type: integer - type: 'null' title: Page Size - name: page_token in: query required: false schema: anyOf: - type: string - type: 'null' title: Page Token - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/PaginatedResponse_ClassifyJob_' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/classifier/jobs/{classify_job_id}: get: tags: - Beta summary: Get Classify Job description: 'Get a classify job. Experimental: not production-ready and subject to change.' operationId: get_classify_job_api_v1_classifier_jobs__classify_job_id__get security: - HTTPBearer: [] parameters: - name: classify_job_id in: path required: true schema: type: string format: uuid title: Classify Job Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ClassifyJob' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/classifier/jobs/{classify_job_id}/results: get: tags: - Beta summary: Get Classification Job Results description: 'Get the results of a classify job. Experimental: not production-ready and subject to change.' operationId: get_classification_job_results_api_v1_classifier_jobs__classify_job_id__results_get security: - HTTPBearer: [] parameters: - name: classify_job_id in: path required: true schema: type: string format: uuid title: Classify Job Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ClassifyJobResults' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/usage-metrics: get: tags: - Beta summary: List Usage Metrics description: List usage metrics with filtering and pagination. operationId: list_usage_metrics_api_v1_beta_usage_metrics_get security: - HTTPBearer: [] parameters: - name: page_size in: query required: false schema: anyOf: - type: integer - type: 'null' description: Number of items per page title: Page Size description: Number of items per page - name: page_token in: query required: false schema: anyOf: - type: string - type: 'null' description: Token for pagination title: Page Token description: Token for pagination - name: include_total in: query required: false schema: type: boolean description: Include total count in response default: false title: Include Total description: Include total count in response - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' description: Filter by project ID title: Project Id description: Filter by project ID - name: user_id in: query required: false schema: anyOf: - type: string - type: 'null' description: Filter by user ID title: User Id description: Filter by user ID - name: event_types in: query required: false schema: anyOf: - type: array items: type: string - type: 'null' description: Filter by event types title: Event Types description: Filter by event types - name: days in: query required: false schema: anyOf: - type: array items: type: string - type: 'null' description: Filter by specific days (YYYY-MM-DD) title: Days description: Filter by specific days (YYYY-MM-DD) - name: day_on_or_before in: query required: false schema: anyOf: - type: string - type: 'null' description: Filter by days on or before this date (YYYY-MM-DD) title: Day On Or Before description: Filter by days on or before this date (YYYY-MM-DD) - name: day_on_or_after in: query required: false schema: anyOf: - type: string - type: 'null' description: Filter by days on or after this date (YYYY-MM-DD) title: Day On Or After description: Filter by days on or after this date (YYYY-MM-DD) - name: event_aggregation_type in: query required: false schema: anyOf: - type: string - type: 'null' description: Filter by event aggregation type title: Event Aggregation Type description: Filter by event aggregation type - name: event_aggregation_key in: query required: false schema: anyOf: - type: string - type: 'null' description: Filter by event aggregation key title: Event Aggregation Key description: Filter by event aggregation key - name: organization_id in: query required: true schema: type: string format: uuid title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/UsageMetricQueryResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/agent-data/{item_id}: get: tags: - Beta summary: Get Agent Data description: Get agent data by ID. operationId: get_agent_data_api_v1_beta_agent_data__item_id__get security: - HTTPBearer: [] parameters: - name: item_id in: path required: true schema: type: string title: Item Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/AgentData' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' put: tags: - Beta summary: Update Agent Data description: Update agent data by ID (overwrites). operationId: update_agent_data_api_v1_beta_agent_data__item_id__put security: - HTTPBearer: [] parameters: - name: item_id in: path required: true schema: type: string title: Item Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/AgentDataUpdate' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/AgentData' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' delete: tags: - Beta summary: Delete Agent Data description: Delete agent data by ID. operationId: delete_agent_data_api_v1_beta_agent_data__item_id__delete security: - HTTPBearer: [] parameters: - name: item_id in: path required: true schema: type: string title: Item Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: type: object additionalProperties: type: string title: Response Delete Agent Data Api V1 Beta Agent Data Item Id Delete '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/agent-data: post: tags: - Beta summary: Create Agent Data description: Create new agent data. operationId: create_agent_data_api_v1_beta_agent_data_post security: - HTTPBearer: [] parameters: - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/AgentDataCreate' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/AgentData' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/agent-data/:search: post: tags: - Beta summary: Search Agent Data description: Search agent data with filtering, sorting, and pagination. operationId: search_agent_data_api_v1_beta_agent_data__search_post security: - HTTPBearer: [] parameters: - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/SearchRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/PaginatedResponse_AgentData_' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/agent-data/:aggregate: post: tags: - Beta summary: Aggregate Agent Data description: Aggregate agent data with grouping and optional counting/first item retrieval. operationId: aggregate_agent_data_api_v1_beta_agent_data__aggregate_post security: - HTTPBearer: [] parameters: - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/AggregateRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/PaginatedResponse_AggregateGroup_' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/agent-data/:delete: post: tags: - Beta summary: Delete Agent Data By Query description: Bulk delete agent data by query (deployment_name, collection, optional filters). operationId: delete_agent_data_by_query_api_v1_beta_agent_data__delete_post security: - HTTPBearer: [] parameters: - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/DeleteRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/DeleteResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/files: get: tags: - Beta summary: List Files description: 'List files with optional filtering and pagination. Filter by `file_name`, `file_ids`, or `external_file_id`. Supports cursor-based pagination and custom ordering.' operationId: list_files_api_v1_beta_files_get security: - HTTPBearer: [] parameters: - name: page_size in: query required: false schema: anyOf: - type: integer maximum: 1000 minimum: 1 - type: 'null' description: The maximum number of items to return. Defaults to 50, maximum is 1000. title: Page Size description: The maximum number of items to return. Defaults to 50, maximum is 1000. - name: page_token in: query required: false schema: anyOf: - type: string - type: 'null' description: A page token received from a previous list call. Provide this to retrieve the subsequent page. title: Page Token description: A page token received from a previous list call. Provide this to retrieve the subsequent page. - name: file_ids in: query required: false schema: anyOf: - type: array items: type: string format: uuid - type: 'null' description: Filter by specific file IDs. title: File Ids description: Filter by specific file IDs. - name: file_name in: query required: false schema: anyOf: - type: string - type: 'null' description: Filter by file name (exact match). title: File Name description: Filter by file name (exact match). - name: external_file_id in: query required: false schema: anyOf: - type: string - type: 'null' description: Filter by external file ID. title: External File Id description: Filter by external file ID. - name: order_by in: query required: false schema: anyOf: - type: string - type: 'null' description: A comma-separated list of fields to order by, sorted in ascending order. Use 'field_name desc' to specify descending order. title: Order By description: A comma-separated list of fields to order by, sorted in ascending order. Use 'field_name desc' to specify descending order. - name: expand in: query required: false schema: anyOf: - type: array items: type: string - type: 'null' description: Fields to expand on each file. examples: - download_url title: Expand description: Fields to expand on each file. - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/FileQueryResponseV2' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' post: tags: - Beta summary: Upload File description: 'Upload a file using multipart/form-data. Set `purpose` to indicate how the file will be used: `user_data`, `parse`, `extract`, `classify`, `split`, `sheet`, or `agent_app`. Returns the created file metadata including its ID for use in subsequent parse, extract, or classify operations.' operationId: upload_file_api_v1_beta_files_post security: - HTTPBearer: [] parameters: - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: multipart/form-data: schema: $ref: '#/components/schemas/Body_upload_file_api_v1_beta_files_post' responses: '201': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/FileV2' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/files/query: post: tags: - Beta summary: Query Files description: 'Query files with filtering and pagination. Deprecated: use `GET /files`.' operationId: query_files_api_v1_beta_files_query_post deprecated: true security: - HTTPBearer: [] parameters: - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/FileQueryRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/FileQueryResponseV2' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/files/{file_id}: get: tags: - Beta summary: Get File description: Get file metadata by ID. operationId: get_file_api_v1_beta_files__file_id__get security: - HTTPBearer: [] parameters: - name: file_id in: path required: true schema: type: string format: uuid title: File Id - name: expand in: query required: false schema: anyOf: - type: array items: type: string - type: 'null' description: Fields to expand. examples: - download_url title: Expand description: Fields to expand. - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/FileV2' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' delete: tags: - Beta summary: Delete File description: Delete a file from the project. operationId: delete_file_api_v1_beta_files__file_id__delete security: - HTTPBearer: [] parameters: - name: file_id in: path required: true schema: type: string format: uuid title: File Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '204': description: Successful Response '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/files/{file_id}/content: get: tags: - Beta summary: Read File Content description: Get a presigned URL to download the file content. operationId: read_file_content_api_v1_beta_files__file_id__content_get security: - HTTPBearer: [] parameters: - name: file_id in: path required: true schema: type: string format: uuid title: File Id - name: expires_at_seconds in: query required: false schema: anyOf: - type: integer - type: 'null' title: Expires At Seconds - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/PresignedUrl' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/sheets/jobs: post: tags: - Beta summary: Create Spreadsheet Job description: 'Create a spreadsheet parsing job. Provide at most one of `configuration` (an inline parsing configuration) or `configuration_id` (a saved configuration preset). If neither is provided, a default configuration is used. Optionally include `webhook_configurations` to receive `sheets.*` status notifications. Experimental: not production-ready and subject to change.' operationId: create_spreadsheet_job_api_v1_beta_sheets_jobs_post security: - HTTPBearer: [] parameters: - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/SpreadsheetJobCreate' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/SpreadsheetJob' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' get: tags: - Beta summary: List Spreadsheet Jobs description: 'List spreadsheet parsing jobs. Experimental: not production-ready and subject to change.' operationId: list_spreadsheet_jobs_api_v1_beta_sheets_jobs_get security: - HTTPBearer: [] parameters: - name: include_results in: query required: false schema: type: boolean default: false title: Include Results - name: status in: query required: false schema: anyOf: - enum: - PENDING - SUCCESS - ERROR - PARTIAL_SUCCESS - CANCELLED type: string - type: 'null' description: Filter by job status title: Status description: Filter by job status - name: job_ids in: query required: false schema: anyOf: - type: array items: type: string - type: 'null' description: Filter by specific job IDs title: Job Ids description: Filter by specific job IDs - name: configuration_id in: query required: false schema: anyOf: - type: string - type: 'null' description: Filter by saved configuration ID title: Configuration Id description: Filter by saved configuration ID - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: page_size in: query required: false schema: anyOf: - type: integer - type: 'null' title: Page Size - name: page_token in: query required: false schema: anyOf: - type: string - type: 'null' title: Page Token - name: created_at_on_or_after in: query required: false schema: anyOf: - type: string format: date-time - type: 'null' description: Include items created at or after this timestamp (inclusive) title: Created At On Or After description: Include items created at or after this timestamp (inclusive) - name: created_at_on_or_before in: query required: false schema: anyOf: - type: string format: date-time - type: 'null' description: Include items created at or before this timestamp (inclusive) title: Created At On Or Before description: Include items created at or before this timestamp (inclusive) - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/PaginatedResponse_SpreadsheetJob_' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/sheets/jobs/{spreadsheet_job_id}: get: tags: - Beta summary: Get Spreadsheet Job description: 'Get a spreadsheet parsing job. When `include_results=True` (default), embeds extracted regions and results if complete, skipping the separate `/results` call. Experimental: not production-ready and subject to change.' operationId: get_spreadsheet_job_api_v1_beta_sheets_jobs__spreadsheet_job_id__get security: - HTTPBearer: [] parameters: - name: spreadsheet_job_id in: path required: true schema: type: string title: Spreadsheet Job Id - name: include_results in: query required: false schema: type: boolean default: true title: Include Results - name: expand in: query required: false schema: type: array items: type: string description: 'Optional fields to populate on the response. Valid values: metadata_state_transitions.' title: Expand description: 'Optional fields to populate on the response. Valid values: metadata_state_transitions.' - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/SpreadsheetJob' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' delete: tags: - Beta summary: Delete Spreadsheet Job description: 'Delete a spreadsheet parsing job and its associated data. Experimental: not production-ready and subject to change.' operationId: delete_spreadsheet_job_api_v1_beta_sheets_jobs__spreadsheet_job_id__delete security: - HTTPBearer: [] parameters: - name: spreadsheet_job_id in: path required: true schema: type: string title: Spreadsheet Job Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: {} '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/sheets/jobs/{spreadsheet_job_id}/regions/{region_id}/result/{region_type}: get: tags: - Beta summary: Get Result Region description: 'Generate a presigned URL to download a specific extracted region. Experimental: not production-ready and subject to change.' operationId: get_result_region_api_v1_beta_sheets_jobs__spreadsheet_job_id__regions__region_id__result__region_type__get security: - HTTPBearer: [] parameters: - name: spreadsheet_job_id in: path required: true schema: type: string title: Spreadsheet Job Id - name: region_id in: path required: true schema: type: string title: Region Id - name: region_type in: path required: true schema: $ref: '#/components/schemas/SpreadsheetResultType' - name: expires_at_seconds in: query required: false schema: anyOf: - type: integer - type: 'null' title: Expires At Seconds - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/PresignedUrl' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/directories: post: tags: - Beta summary: Create Directory description: Create a new directory within the specified project. operationId: create_directory_api_v1_beta_directories_post security: - HTTPBearer: [] parameters: - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/DirectoryCreateRequest' responses: '201': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/DirectoryResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' get: tags: - Beta summary: List Directories operationId: list_directories_api_v1_beta_directories_get security: - HTTPBearer: [] parameters: - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: name in: query required: false schema: anyOf: - type: string - type: 'null' title: Name - name: type in: query required: false schema: anyOf: - enum: - user - index - ephemeral type: string - type: 'null' title: Type - name: include_deleted in: query required: false schema: type: boolean default: false title: Include Deleted - name: page_size in: query required: false schema: anyOf: - type: integer - type: 'null' title: Page Size - name: page_token in: query required: false schema: anyOf: - type: string - type: 'null' title: Page Token - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/DirectoryQueryResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/directories/{directory_id}: get: tags: - Beta summary: Get Directory description: Retrieve a directory by its identifier. operationId: get_directory_api_v1_beta_directories__directory_id__get security: - HTTPBearer: [] parameters: - name: directory_id in: path required: true schema: type: string title: Directory Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/DirectoryResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' patch: tags: - Beta summary: Update Directory description: Update directory metadata. operationId: update_directory_api_v1_beta_directories__directory_id__patch security: - HTTPBearer: [] parameters: - name: directory_id in: path required: true schema: type: string title: Directory Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/DirectoryUpdateRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/DirectoryResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' delete: tags: - Beta summary: Delete Directory description: Permanently delete a directory. operationId: delete_directory_api_v1_beta_directories__directory_id__delete security: - HTTPBearer: [] parameters: - name: directory_id in: path required: true schema: type: string title: Directory Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '204': description: Successful Response '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/directories/{directory_id}/files: post: tags: - Beta summary: Add Directory File description: Create a new file within the specified directory; the directory must exist in the project and `file_id` must reference an existing file. operationId: add_directory_file_api_v1_beta_directories__directory_id__files_post security: - HTTPBearer: [] parameters: - name: directory_id in: path required: true schema: type: string title: Directory Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/DirectoryFileCreateRequest' responses: '201': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/DirectoryFileResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' get: tags: - Beta summary: List Directory Files description: List all files within the specified directory with optional filtering and pagination. operationId: list_directory_files_api_v1_beta_directories__directory_id__files_get security: - HTTPBearer: [] parameters: - name: directory_id in: path required: true schema: type: string title: Directory Id - name: expand in: query required: false schema: anyOf: - type: array items: type: string - type: 'null' description: Fields to expand on each directory file. examples: - download_url title: Expand description: Fields to expand on each directory file. - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: display_name in: query required: false schema: anyOf: - type: string - type: 'null' title: Display Name - name: display_name_contains in: query required: false schema: anyOf: - type: string - type: 'null' title: Display Name Contains - name: unique_id in: query required: false schema: anyOf: - type: string - type: 'null' title: Unique Id - name: file_id in: query required: false schema: anyOf: - type: string - type: 'null' title: File Id - name: include_deleted in: query required: false schema: type: boolean default: false title: Include Deleted - name: page_size in: query required: false schema: anyOf: - type: integer - type: 'null' title: Page Size - name: page_token in: query required: false schema: anyOf: - type: string - type: 'null' title: Page Token - name: updated_at_on_or_after in: query required: false schema: anyOf: - type: string format: date-time - type: 'null' description: Include items updated at or after this timestamp (inclusive) title: Updated At On Or After description: Include items updated at or after this timestamp (inclusive) - name: updated_at_on_or_before in: query required: false schema: anyOf: - type: string format: date-time - type: 'null' description: Include items updated at or before this timestamp (inclusive) title: Updated At On Or Before description: Include items updated at or before this timestamp (inclusive) - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: content: application/json: schema: anyOf: - type: array items: type: string maxItems: 200 - type: 'null' title: Directory File Ids responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/DirectoryFileQueryResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/directories/{directory_id}/files/upload: post: tags: - Beta summary: Upload File To Directory description: Upload a file and create its directory entry in one call; `unique_id` / `display_name` default to values derived from file metadata. operationId: upload_file_to_directory_api_v1_beta_directories__directory_id__files_upload_post security: - HTTPBearer: [] parameters: - name: directory_id in: path required: true schema: type: string title: Directory Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: multipart/form-data: schema: $ref: '#/components/schemas/Body_upload_file_to_directory_api_v1_beta_directories__directory_id__files_upload_post' responses: '201': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/DirectoryFileResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/directories/{directory_id}/files/{directory_file_id}: get: tags: - Beta summary: Get Directory File description: Get a directory file by `directory_file_id`; to look up by `unique_id`, use the list endpoint with a filter. operationId: get_directory_file_api_v1_beta_directories__directory_id__files__directory_file_id__get security: - HTTPBearer: [] parameters: - name: directory_id in: path required: true schema: type: string title: Directory Id - name: directory_file_id in: path required: true schema: type: string title: Directory File Id - name: expand in: query required: false schema: anyOf: - type: array items: type: string - type: 'null' description: Fields to expand. examples: - download_url title: Expand description: Fields to expand. - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/DirectoryFileResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' patch: tags: - Beta summary: Update Directory File description: Update directory-file metadata by `directory_file_id`; set `directory_id` to move the file to a different directory. To resolve from `unique_id`, list with a filter first. operationId: update_directory_file_api_v1_beta_directories__directory_id__files__directory_file_id__patch security: - HTTPBearer: [] parameters: - name: directory_id in: path required: true schema: type: string title: Directory Id - name: directory_file_id in: path required: true schema: type: string title: Directory File Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/DirectoryFileUpdateRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/DirectoryFileResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' delete: tags: - Beta summary: Delete Directory File description: Delete a directory file by `directory_file_id`; to resolve from `unique_id`, list with a filter first. operationId: delete_directory_file_api_v1_beta_directories__directory_id__files__directory_file_id__delete security: - HTTPBearer: [] parameters: - name: directory_id in: path required: true schema: type: string title: Directory Id - name: directory_file_id in: path required: true schema: type: string title: Directory File Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '204': description: Successful Response '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/directories/{directory_id}/files/bulk-delete: post: tags: - Beta summary: Bulk Delete Directory Files description: Delete up to 100 files from the specified directory; all must belong to it. operationId: bulk_delete_directory_files_api_v1_beta_directories__directory_id__files_bulk_delete_post security: - HTTPBearer: [] parameters: - name: directory_id in: path required: true schema: type: string title: Directory Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/DirectoryFileBulkDeleteRequest' responses: '204': description: Successful Response '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/configurations: post: tags: - Beta summary: Create Configuration description: Upsert a product configuration; updates if one with the same name + product type + project exists, otherwise creates. operationId: create_configuration_api_v1_beta_configurations_post security: - HTTPBearer: [] parameters: - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ConfigurationCreateRequest' responses: '201': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ConfigurationResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' get: tags: - Beta summary: List Configurations description: List product configurations for the current project. operationId: list_configurations_api_v1_beta_configurations_get security: - HTTPBearer: [] parameters: - name: product_type in: query required: false schema: anyOf: - type: array items: enum: - split_v1 - extract_v2 - classify_v2 - parse_v2 - spreadsheet_v1 - unknown type: string - type: 'null' description: Filter by one or more product types. Repeat the parameter for multiple values. title: Product Type description: Filter by one or more product types. Repeat the parameter for multiple values. - name: name in: query required: false schema: anyOf: - type: string - type: 'null' description: Filter by configuration name. title: Name description: Filter by configuration name. - name: page_size in: query required: false schema: anyOf: - type: integer - type: 'null' description: Number of items per page. title: Page Size description: Number of items per page. - name: page_token in: query required: false schema: anyOf: - type: string - type: 'null' description: Pagination token. title: Page Token description: Pagination token. - name: latest_only in: query required: false schema: type: boolean description: Return only the latest version per configuration name. default: false title: Latest Only description: Return only the latest version per configuration name. - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ConfigurationQueryResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/configurations/{config_id}: get: tags: - Beta summary: Get Configuration description: Get a single product configuration by ID. operationId: get_configuration_api_v1_beta_configurations__config_id__get security: - HTTPBearer: [] parameters: - name: config_id in: path required: true schema: type: string title: Config Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ConfigurationResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' put: tags: - Beta summary: Update Configuration description: Update an existing product configuration. operationId: update_configuration_api_v1_beta_configurations__config_id__put security: - HTTPBearer: [] parameters: - name: config_id in: path required: true schema: type: string title: Config Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ConfigurationUpdateRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ConfigurationResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' delete: tags: - Beta summary: Delete Configuration description: Delete a product configuration. operationId: delete_configuration_api_v1_beta_configurations__config_id__delete security: - HTTPBearer: [] parameters: - name: config_id in: path required: true schema: type: string title: Config Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '204': description: Successful Response '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/split/jobs: post: tags: - Beta summary: Create Split Job description: Create a document split job. operationId: create_split_job_api_v1_beta_split_jobs_post security: - HTTPBearer: [] parameters: - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/SplitCreateRequest' responses: '201': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/SplitJobResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' get: tags: - Beta summary: List Split Jobs description: List document split jobs. operationId: list_split_jobs_api_v1_beta_split_jobs_get security: - HTTPBearer: [] parameters: - name: status in: query required: false schema: anyOf: - enum: - pending - processing - completed - failed - cancelled type: string - type: 'null' description: Filter by job status (pending, processing, completed, failed, cancelled) title: Status description: Filter by job status (pending, processing, completed, failed, cancelled) - name: job_ids in: query required: false schema: anyOf: - type: array items: type: string - type: 'null' description: Filter by specific job IDs title: Job Ids description: Filter by specific job IDs - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: page_size in: query required: false schema: anyOf: - type: integer - type: 'null' title: Page Size - name: page_token in: query required: false schema: anyOf: - type: string - type: 'null' title: Page Token - name: created_at_on_or_after in: query required: false schema: anyOf: - type: string format: date-time - type: 'null' description: Include items created at or after this timestamp (inclusive) title: Created At On Or After description: Include items created at or after this timestamp (inclusive) - name: created_at_on_or_before in: query required: false schema: anyOf: - type: string format: date-time - type: 'null' description: Include items created at or before this timestamp (inclusive) title: Created At On Or Before description: Include items created at or before this timestamp (inclusive) - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/SplitJobQueryResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/split/jobs/{split_job_id}: get: tags: - Beta summary: Get Split Job description: Get a document split job. operationId: get_split_job_api_v1_beta_split_jobs__split_job_id__get security: - HTTPBearer: [] parameters: - name: split_job_id in: path required: true schema: type: string title: Split Job Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/SplitJobResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/batch-processing: post: tags: - Beta summary: Create Batch Job description: 'Create a batch processing job. Processes files from a directory or a specific list of item IDs. Supports batch parsing and classification operations. Provide either `directory_id` to process all files in a directory, or `item_ids` for specific items. The job runs asynchronously — poll `GET /batch/{job_id}` for progress.' operationId: create_batch_job_api_v1_beta_batch_processing_post security: - HTTPBearer: [] parameters: - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: temporal-namespace in: header required: false schema: anyOf: - type: string - type: 'null' title: Temporal-Namespace - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/BatchJobCreateRequest' responses: '201': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/BatchJobResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' get: tags: - Beta summary: List Batch Jobs description: 'List batch processing jobs with optional filtering. Filter by `directory_id`, `job_type`, or `status`. Results are paginated with configurable `limit` and `offset`.' operationId: list_batch_jobs_api_v1_beta_batch_processing_get security: - HTTPBearer: [] parameters: - name: directory_id in: query required: false schema: anyOf: - type: string - type: 'null' description: Filter by directory ID title: Directory Id description: Filter by directory ID - name: job_type in: query required: false schema: anyOf: - $ref: '#/components/schemas/BatchJobType' - type: 'null' description: Filter by job type (PARSE, EXTRACT, CLASSIFY) title: Job Type description: Filter by job type (PARSE, EXTRACT, CLASSIFY) - name: status in: query required: false schema: anyOf: - $ref: '#/components/schemas/BatchJobStatus' - type: 'null' description: Filter by job status (PENDING, RUNNING, COMPLETED, FAILED, CANCELLED) title: Status description: Filter by job status (PENDING, RUNNING, COMPLETED, FAILED, CANCELLED) - name: limit in: query required: false schema: type: integer maximum: 1000 minimum: 1 description: Maximum number of jobs to return default: 50 title: Limit description: Maximum number of jobs to return - name: offset in: query required: false schema: type: integer minimum: 0 description: Number of jobs to skip for pagination default: 0 title: Offset description: Number of jobs to skip for pagination - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/BatchJobQueryResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/batch-processing/{job_id}: get: tags: - Beta summary: Get Batch Job Status description: 'Get detailed status of a batch processing job. Returns current progress percentage, file counts (total, processed, failed, skipped), and timestamps.' operationId: get_batch_job_status_api_v1_beta_batch_processing__job_id__get security: - HTTPBearer: [] parameters: - name: job_id in: path required: true schema: type: string title: Job Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/BatchJobStatusResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/batch-processing/{job_id}/items: get: tags: - Beta summary: List Batch Job Items description: 'List items in a batch job with optional status filtering. Useful for finding failed items, viewing completed items, or debugging processing issues.' operationId: list_batch_job_items_api_v1_beta_batch_processing__job_id__items_get security: - HTTPBearer: [] parameters: - name: job_id in: path required: true schema: type: string title: Job Id - name: status in: query required: false schema: anyOf: - $ref: '#/components/schemas/BatchFileStatus' - type: 'null' description: Filter items by status title: Status description: Filter items by status - name: limit in: query required: false schema: type: integer maximum: 1000 minimum: 1 description: Maximum number of items to return default: 100 title: Limit description: Maximum number of items to return - name: offset in: query required: false schema: type: integer minimum: 0 description: Number of items to skip default: 0 title: Offset description: Number of items to skip - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/BatchItemListResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/batch-processing/{job_id}/cancel: post: tags: - Beta summary: Cancel Batch Job description: 'Cancel a running batch processing job. Stops processing and marks pending items as cancelled. Items currently being processed may still complete.' operationId: cancel_batch_job_api_v1_beta_batch_processing__job_id__cancel_post security: - HTTPBearer: [] parameters: - name: job_id in: path required: true schema: type: string title: Job Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: temporal-namespace in: header required: false schema: anyOf: - type: string - type: 'null' title: Temporal-Namespace - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/BatchJobCancelRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/BatchJobCancelResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/batch-processing/items/{item_id}/processing-results: get: tags: - Beta summary: Get Item Processing Results description: 'Get all processing results for a specific item. Returns the complete processing history for an item including what operations were performed, parameters used, and where outputs are stored. Optionally filter by `job_type`.' operationId: get_item_processing_results_api_v1_beta_batch_processing_items__item_id__processing_results_get security: - HTTPBearer: [] parameters: - name: item_id in: path required: true schema: type: string title: Item Id - name: job_type in: query required: false schema: anyOf: - $ref: '#/components/schemas/BatchJobType' - type: 'null' description: Filter results by job type title: Job Type description: Filter results by job type - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ItemProcessingResultsResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/beta/pipelines/{pipeline_id}/files: get: tags: - Beta summary: List Pipeline Files description: List files for a pipeline with pagination and filtering. operationId: list_pipeline_files_api_v1_beta_pipelines__pipeline_id__files_get security: - HTTPBearer: [] parameters: - name: pipeline_id in: path required: true schema: type: string format: uuid title: Pipeline Id - name: data_source_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' description: Filter by data source ID. title: Data Source Id description: Filter by data source ID. - name: file_name_contains in: query required: false schema: anyOf: - type: string - type: 'null' description: Filter by files whose names contain this substring (case-insensitive). title: File Name Contains description: Filter by files whose names contain this substring (case-insensitive). - name: statuses in: query required: false schema: anyOf: - type: array items: enum: - NOT_STARTED - IN_PROGRESS - SUCCESS - ERROR - CANCELLED type: string - type: 'null' description: Filter by pipeline file statuses. title: Statuses description: Filter by pipeline file statuses. - name: page_size in: query required: false schema: anyOf: - type: integer maximum: 1000 minimum: 1 - type: 'null' description: Maximum number of items to return. Defaults to 50, max 1000. title: Page Size description: Maximum number of items to return. Defaults to 50, max 1000. - name: page_token in: query required: false schema: anyOf: - type: string - type: 'null' description: Page token for pagination, from a previous response. title: Page Token description: Page token for pagination, from a previous response. - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/PipelineFileListResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' components: schemas: DirectoryCreateRequest: properties: name: type: string minLength: 1 title: Name description: Human-readable name for the directory. description: anyOf: - type: string - type: 'null' title: Description description: Optional description shown to users. type: type: string enum: - user - ephemeral title: Type description: Directory type. Use 'ephemeral' for batch processing with automatic cleanup. default: user examples: - user - ephemeral expires_at: anyOf: - type: string format: date-time - type: 'null' title: Expires At description: When this directory expires. Required for ephemeral directories. examples: - '2026-05-10T00:00:00Z' system_metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: System Metadata description: Reserved system-managed metadata. type: object required: - name title: DirectoryCreateRequest description: API request schema for creating a directory. StatusEnum: type: string enum: - PENDING - SUCCESS - ERROR - PARTIAL_SUCCESS - CANCELLED title: StatusEnum description: Enum for representing the status of a job BatchParseJobRecordCreate: properties: job_name: type: string const: parse_raw_file_job title: Job Name default: parse_raw_file_job partitions: additionalProperties: anyOf: - type: string format: uuid - type: string propertyNames: $ref: '#/components/schemas/PartitionNames' type: object title: Partitions description: The partitions for this execution. Used for determining where to save job output. parameters: anyOf: - $ref: '#/components/schemas/BatchParseJobConfig' - type: 'null' description: The generic parse configuration for all files in the batch. session_id: anyOf: - type: string format: uuid - type: 'null' title: Session Id description: The upstream request ID that created this job. Used for tracking the job across services. correlation_id: anyOf: - type: string format: uuid - type: 'null' title: Correlation Id description: The correlation ID for this job. Used for tracking the job across services. parent_job_execution_id: anyOf: - type: string format: uuid - type: 'null' title: Parent Job Execution Id description: The ID of the parent job execution. user_id: anyOf: - type: string - type: 'null' title: User Id description: The ID of the user that created this job project_id: anyOf: - type: string format: uuid - type: 'null' title: Project Id description: The ID of the project this job belongs to. webhook_url: anyOf: - type: string - type: 'null' title: Webhook Url description: The URL that needs to be called at the end of the parsing job. type: object title: BatchParseJobRecordCreate description: "Batch-specific parse job record for batch processing.\n\nThis model contains the metadata and configuration for a batch parse job,\nbut excludes file-specific information. It's used as input to the batch\nparent workflow and combined with DirectoryFile data to create full\nParseJobRecordCreate instances for each file.\n\nAttributes:\n job_name: Must be PARSE_RAW_FILE\n partitions: Partitions for job output location\n parameters: Generic parse configuration (BatchParseJobConfig)\n session_id: Upstream request ID for tracking\n correlation_id: Correlation ID for cross-service tracking\n parent_job_execution_id: Parent job execution ID if nested\n user_id: User who created the job\n project_id: Project this job belongs to\n webhook_url: Optional webhook URL for job completion notifications" ClassifyV2Rule: properties: type: type: string maxLength: 50 minLength: 1 title: Type description: Document type to assign when rule matches examples: - invoice - receipt - contract - report - proposal description: type: string maxLength: 500 minLength: 10 title: Description description: Natural language criteria for matching this rule examples: - contains invoice number, line items, and total amount - purchase receipt with transaction info and merchant details - legal contract with terms, conditions, and signatures type: object required: - type - description title: ClassifyV2Rule description: A rule for classifying documents. File: properties: id: type: string format: uuid title: Id description: Unique identifier created_at: anyOf: - type: string format: date-time - type: 'null' title: Created At description: Creation datetime updated_at: anyOf: - type: string format: date-time - type: 'null' title: Updated At description: Update datetime name: type: string maxLength: 3000 minLength: 1 title: Name external_file_id: anyOf: - type: string - type: 'null' title: External File Id description: The ID of the file in the external system file_size: anyOf: - type: integer minimum: 0.0 - type: 'null' title: File Size description: Size of the file in bytes file_type: anyOf: - type: string maxLength: 3000 minLength: 1 - type: 'null' title: File Type description: File type (e.g. pdf, docx, etc.) project_id: type: string format: uuid title: Project Id description: The ID of the project that the file belongs to last_modified_at: anyOf: - type: string format: date-time - type: 'null' title: Last Modified At description: The last modified time of the file resource_info: anyOf: - additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object - type: 'null' title: Resource Info description: Resource information for the file permission_info: anyOf: - additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object - type: 'null' title: Permission Info description: Permission information for the file data_source_id: anyOf: - type: string format: uuid - type: 'null' title: Data Source Id description: The ID of the data source that the file belongs to expires_at: anyOf: - type: string format: date-time - type: 'null' title: Expires At description: The expiration date for the file. Files past this date can be deleted. purpose: anyOf: - type: string - type: 'null' title: Purpose description: The intended purpose of the file (e.g., 'user_data', 'parse', 'extract', 'split', 'classify') type: object required: - id - name - project_id title: File description: Schema for a file. AggregateRequest: properties: page_size: anyOf: - type: integer - type: 'null' title: Page Size description: The maximum number of items to return. The service may return fewer than this value. If unspecified, a default page size will be used. The maximum value is typically 1000; values above this will be coerced to the maximum. page_token: anyOf: - type: string - type: 'null' title: Page Token description: A page token, received from a previous list call. Provide this to retrieve the subsequent page. filter: anyOf: - additionalProperties: $ref: '#/components/schemas/FilterOperation' type: object - type: 'null' title: Filter description: A filter object or expression that filters resources listed in the response. order_by: anyOf: - type: string - type: 'null' title: Order By description: A comma-separated list of fields to order by, sorted in ascending order. Use 'field_name desc' to specify descending order. deployment_name: type: string title: Deployment Name description: The agent deployment's name to aggregate data for collection: type: string title: Collection description: The logical agent data collection to aggregate data for default: default group_by: anyOf: - items: type: string type: array - type: 'null' title: Group By description: The fields to group by. If empty, the entire dataset is grouped on. e.g. if left out, can be used for simple count operations count: anyOf: - type: boolean - type: 'null' title: Count description: Whether to count the number of items in each group default: false first: anyOf: - type: boolean - type: 'null' title: First description: Whether to return the first item in each group (Sorted by created_at) default: false offset: anyOf: - type: integer maximum: 1000.0 minimum: 0.0 - type: 'null' title: Offset description: The offset to start from. If not provided, the first page is returned default: 0 type: object required: - deployment_name title: AggregateRequest description: API request body for aggregating agent data LlamaParseTables: properties: compact_markdown_tables: anyOf: - type: boolean - type: 'null' title: Compact Markdown Tables description: Remove extra whitespace padding in markdown table cells for more compact output output_tables_as_markdown: anyOf: - type: boolean - type: 'null' title: Output Tables As Markdown description: Output tables as markdown pipe tables instead of HTML <table> tags. Markdown tables are simpler but cannot represent complex structures like merged cells markdown_table_multiline_separator: anyOf: - type: string - type: 'null' title: Markdown Table Multiline Separator description: 'Separator string for multiline cell content in markdown tables. Example: ''<br>'' to preserve line breaks, '' '' to join with spaces' merge_continued_tables: anyOf: - type: boolean - type: 'null' title: Merge Continued Tables description: Automatically merge tables that span multiple pages into a single table. The merged table appears on the first page with merged_from_pages metadata additionalProperties: false type: object title: LlamaParseTables description: Table formatting options for markdown output. AgentDataCreate: properties: deployment_name: type: string title: Deployment Name collection: type: string title: Collection default: default data: additionalProperties: true type: object title: Data type: object required: - deployment_name - data title: AgentDataCreate description: API request model for creating agent data AutoModePresentationOptions: properties: out_of_bounds_content: anyOf: - type: boolean - type: 'null' title: Out Of Bounds Content description: Extract out of bounds content in presentation slides skip_embedded_data: anyOf: - type: boolean - type: 'null' title: Skip Embedded Data description: Skip extraction of embedded data for charts in presentation slides additionalProperties: false type: object title: AutoModePresentationOptions description: Presentation-specific options for auto mode parsing configuration. LlamaParseIgnoreOptions: properties: ignore_diagonal_text: anyOf: - type: boolean - type: 'null' title: Ignore Diagonal Text description: Skip text rotated at an angle (not horizontal/vertical). Useful for ignoring watermarks or decorative angled text ignore_text_in_image: anyOf: - type: boolean - type: 'null' title: Ignore Text In Image description: Skip OCR text extraction from embedded images. Use when images contain irrelevant text (watermarks, logos) that shouldn't be in the output ignore_hidden_text: anyOf: - type: boolean - type: 'null' title: Ignore Hidden Text description: Skip text marked as hidden in the document structure. Some PDFs contain invisible text layers used for accessibility or search indexing additionalProperties: false type: object title: LlamaParseIgnoreOptions description: Options for ignoring specific types of text during extraction. PaginatedResponse_ClassifyJob_: properties: items: items: $ref: '#/components/schemas/ClassifyJob' type: array title: Items description: The list of items. next_page_token: anyOf: - type: string - type: 'null' title: Next Page Token description: A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. total_size: anyOf: - type: integer - type: 'null' title: Total Size description: The total number of items available. This is only populated when specifically requested. The value may be an estimate and can be used for display purposes only. type: object required: - items title: PaginatedResponse[ClassifyJob] FileFilter: properties: project_id: anyOf: - type: string format: uuid - type: 'null' title: Project Id description: Filter by project ID file_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: File Ids description: Filter by specific file IDs file_name: anyOf: - type: string - type: 'null' title: File Name description: Filter by file name data_source_id: anyOf: - type: string format: uuid - type: 'null' title: Data Source Id description: Filter by data source ID external_file_id: anyOf: - type: string - type: 'null' title: External File Id description: Filter by external file ID only_manually_uploaded: anyOf: - type: boolean - type: 'null' title: Only Manually Uploaded description: Filter only manually uploaded files (data_source_id is null) type: object title: FileFilter description: Filter parameters for file queries. SplitCategory: properties: name: type: string maxLength: 200 minLength: 1 title: Name description: Name of the category. description: anyOf: - type: string maxLength: 2000 minLength: 1 - type: 'null' title: Description description: Optional description of what content belongs in this category. type: object required: - name title: SplitCategory description: Category definition for document splitting. BatchJobType: type: string enum: - parse - extract - classify title: BatchJobType description: Type of batch processing operation. Body_upload_file_to_directory_api_v1_beta_directories__directory_id__files_upload_post: properties: upload_file: type: string format: binary title: Upload File unique_id: anyOf: - type: string - type: 'null' title: Unique Id display_name: anyOf: - type: string - type: 'null' title: Display Name external_file_id: anyOf: - type: string - type: 'null' title: External File Id metadata: anyOf: - type: string - type: 'null' title: Metadata description: User metadata as a JSON object string. examples: - '{"source": "web", "priority": 1}' type: object required: - upload_file title: Body_upload_file_to_directory_api_v1_beta_directories__directory_id__files_upload_post PipelineFileListResponse: properties: items: items: $ref: '#/components/schemas/PipelineFileResponse' type: array title: Items description: The list of items. next_page_token: anyOf: - type: string - type: 'null' title: Next Page Token description: A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. total_size: anyOf: - type: integer - type: 'null' title: Total Size description: The total number of items available. This is only populated when specifically requested. The value may be an estimate and can be used for display purposes only. type: object required: - items title: PipelineFileListResponse description: Beta API query response schema for pipeline files. DirectoryFileCreateRequest: properties: file_id: type: string title: File Id description: File ID for the storage location (required). unique_id: anyOf: - type: string - type: 'null' title: Unique Id description: Unique identifier for the file in the directory. If not provided, will use the file's external_file_id or name. display_name: anyOf: - type: string - type: 'null' title: Display Name description: Display name for the file. If not provided, will use the file's name. metadata: anyOf: - $ref: '#/components/schemas/MetadataDict' - type: 'null' description: User-defined metadata key-value pairs to associate with the file. type: object required: - file_id title: DirectoryFileCreateRequest description: API request schema for creating a directory file. AgentDataUpdate: properties: data: additionalProperties: true type: object title: Data type: object required: - data title: AgentDataUpdate description: API request model for updating agent data SplitConfiguration: properties: categories: items: $ref: '#/components/schemas/SplitCategory' type: array maxItems: 50 minItems: 1 title: Categories description: Categories to split documents into. splitting_strategy: $ref: '#/components/schemas/SplitStrategy' description: Strategy for splitting documents. type: object required: - categories title: SplitConfiguration description: Split configuration with categories and splitting strategy. ClassifyJobCreate: properties: rules: items: $ref: '#/components/schemas/ClassifierRule' type: array minItems: 1 title: Rules description: The rules to classify the files mode: $ref: '#/components/schemas/ClassifyMode' description: The classification mode to use default: FAST file_ids: items: type: string format: uuid type: array maxItems: 500 minItems: 1 title: File Ids description: The IDs of the files to classify parsing_configuration: $ref: '#/components/schemas/ClassifyParsingConfiguration' description: The configuration for the parsing job default: lang: en max_pages: 5 webhook_configurations: items: $ref: '#/components/schemas/LlamaParseWebhookConfiguration' type: array title: Webhook Configurations description: List of webhook configurations for notifications type: object required: - rules - file_ids title: ClassifyJobCreate description: A classify job. BatchJobQueryResponse: properties: items: items: $ref: '#/components/schemas/BatchJobResponse' type: array title: Items description: The list of items. next_page_token: anyOf: - type: string - type: 'null' title: Next Page Token description: A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. total_size: anyOf: - type: integer - type: 'null' title: Total Size description: The total number of items available. This is only populated when specifically requested. The value may be an estimate and can be used for display purposes only. type: object required: - items title: BatchJobQueryResponse description: Response schema for paginated batch job queries. FileQueryRequest: properties: page_size: anyOf: - type: integer - type: 'null' title: Page Size description: The maximum number of items to return. The service may return fewer than this value. If unspecified, a default page size will be used. The maximum value is typically 1000; values above this will be coerced to the maximum. page_token: anyOf: - type: string - type: 'null' title: Page Token description: A page token, received from a previous list call. Provide this to retrieve the subsequent page. filter: anyOf: - $ref: '#/components/schemas/FileFilter' - type: 'null' description: A filter object or expression that filters resources listed in the response. order_by: anyOf: - type: string - type: 'null' title: Order By description: A comma-separated list of fields to order by, sorted in ascending order. Use 'field_name desc' to specify descending order. type: object title: FileQueryRequest description: Request schema for querying files with pagination and filtering. ClassifyJobResults: properties: items: items: $ref: '#/components/schemas/FileClassification' type: array title: Items description: The list of items. next_page_token: anyOf: - type: string - type: 'null' title: Next Page Token description: A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. total_size: anyOf: - type: integer - type: 'null' title: Total Size description: The total number of items available. This is only populated when specifically requested. The value may be an estimate and can be used for display purposes only. type: object required: - items title: ClassifyJobResults description: Response model for the classify endpoint following AIP-132 pagination standard. DirectoryFileUpdateRequest: properties: unique_id: anyOf: - type: string minLength: 1 - type: 'null' title: Unique Id description: Updated unique identifier. display_name: anyOf: - type: string - type: 'null' title: Display Name description: Updated display name. target_directory_id: anyOf: - type: string - type: 'null' title: Target Directory Id description: Move file to a different directory. metadata: anyOf: - $ref: '#/components/schemas/MetadataDict' - type: 'null' description: User-defined metadata key-value pairs. Replaces the user metadata layer. type: object title: DirectoryFileUpdateRequest description: API request schema for updating a directory file. LlamaParseSpreadsheetOptions: properties: detect_sub_tables_in_sheets: anyOf: - type: boolean - type: 'null' title: Detect Sub Tables In Sheets description: Detect and extract multiple tables within a single sheet. Useful when spreadsheets contain several data regions separated by blank rows/columns force_formula_computation_in_sheets: anyOf: - type: boolean - type: 'null' title: Force Formula Computation In Sheets description: Compute formula results instead of extracting formula text. Use when you need calculated values rather than formula definitions include_hidden_sheets: anyOf: - type: boolean - type: 'null' title: Include Hidden Sheets description: Parse hidden sheets in addition to visible ones. By default, hidden sheets are skipped additionalProperties: false type: object title: LlamaParseSpreadsheetOptions description: Spreadsheet (Excel, CSV, ODS) parsing options. SplitDocumentInput: properties: type: type: string title: Type description: 'Type of document input. Valid values are: file_id' value: type: string title: Value description: Document identifier. type: object required: - type - value title: SplitDocumentInput description: Document input specification for beta API. SpreadsheetV1Parameters: properties: sheet_names: anyOf: - items: type: string type: array - type: 'null' title: Sheet Names description: The names of the sheets to extract regions from. If empty, all sheets will be processed. include_hidden_cells: type: boolean title: Include Hidden Cells description: Whether to include hidden cells when extracting regions from the spreadsheet. default: true extraction_range: anyOf: - type: string - type: 'null' title: Extraction Range description: A1 notation of the range to extract a single region from. If None, the entire sheet is used. generate_additional_metadata: type: boolean title: Generate Additional Metadata description: Whether to generate additional metadata (title, description) for each extracted region. default: true use_experimental_processing: type: boolean title: Use Experimental Processing description: Enables experimental processing. Accuracy may be impacted. default: false flatten_hierarchical_tables: type: boolean title: Flatten Hierarchical Tables description: Return a flattened dataframe when a detected table is recognized as hierarchical. default: false table_merge_sensitivity: type: string enum: - strong - weak title: Table Merge Sensitivity description: Influences how likely similar-looking regions are merged into a single table. Useful for spreadsheets that either have sparse tables (strong merging) or many distinct tables close together (weak merging). default: strong specialization: anyOf: - type: string - type: 'null' title: Specialization description: 'Optional specialization mode for domain-specific extraction. Supported values: ''financial-standard'', ''financial-enhanced'', ''financial-precise''. Default None uses the general-purpose pipeline.' product_type: type: string const: spreadsheet_v1 title: Product Type description: Product type. type: object required: - product_type title: SpreadsheetV1Parameters description: Typed parameters for a *spreadsheet v1* product configuration. WorksheetMetadata: properties: sheet_name: type: string title: Sheet Name description: Name of the worksheet title: anyOf: - type: string - type: 'null' title: Title description: Generated title for the worksheet description: anyOf: - type: string - type: 'null' title: Description description: Generated description of the worksheet type: object required: - sheet_name title: WorksheetMetadata description: Metadata about a worksheet in a spreadsheet MetadataDict: additionalProperties: $ref: '#/components/schemas/MetadataValue' type: object SpreadsheetParsingConfig: properties: sheet_names: anyOf: - items: type: string type: array - type: 'null' title: Sheet Names description: The names of the sheets to extract regions from. If empty, all sheets will be processed. include_hidden_cells: type: boolean title: Include Hidden Cells description: Whether to include hidden cells when extracting regions from the spreadsheet. default: true extraction_range: anyOf: - type: string - type: 'null' title: Extraction Range description: A1 notation of the range to extract a single region from. If None, the entire sheet is used. generate_additional_metadata: type: boolean title: Generate Additional Metadata description: Whether to generate additional metadata (title, description) for each extracted region. default: true use_experimental_processing: type: boolean title: Use Experimental Processing description: Enables experimental processing. Accuracy may be impacted. default: false flatten_hierarchical_tables: type: boolean title: Flatten Hierarchical Tables description: Return a flattened dataframe when a detected table is recognized as hierarchical. default: false table_merge_sensitivity: type: string enum: - strong - weak title: Table Merge Sensitivity description: Influences how likely similar-looking regions are merged into a single table. Useful for spreadsheets that either have sparse tables (strong merging) or many distinct tables close together (weak merging). default: strong specialization: anyOf: - type: string - type: 'null' title: Specialization description: 'Optional specialization mode for domain-specific extraction. Supported values: ''financial-standard'', ''financial-enhanced'', ''financial-precise''. Default None uses the general-purpose pipeline.' type: object title: SpreadsheetParsingConfig description: Configuration for spreadsheet parsing and region extraction LlamaParseProcessingControl: properties: timeouts: $ref: '#/components/schemas/LlamaParseTimeouts' description: Timeout settings for job execution. Increase for large or complex documents job_failure_conditions: $ref: '#/components/schemas/LlamaParseJobFailureConditions' description: Quality thresholds that determine when a job should fail vs complete with partial results additionalProperties: false type: object title: LlamaParseProcessingControl description: Job processing controls for timeouts and failure handling. HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError DirectoryResponse: properties: id: type: string title: Id description: Unique identifier for the directory. created_at: anyOf: - type: string format: date-time - type: 'null' title: Created At description: Creation datetime updated_at: anyOf: - type: string format: date-time - type: 'null' title: Updated At description: Update datetime project_id: type: string title: Project Id description: Project the directory belongs to. name: type: string minLength: 1 title: Name description: Human-readable name for the directory. description: anyOf: - type: string - type: 'null' title: Description description: Optional description shown to users. type: anyOf: - type: string enum: - user - index - ephemeral - system_ephemeral - type: 'null' title: Type description: 'Directory type: ''user'', ''index'', ''ephemeral'', or ''system_ephemeral''.' expires_at: anyOf: - type: string format: date-time - type: 'null' title: Expires At description: When this directory expires and is eligible for cleanup. system_metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: System Metadata description: Reserved system-managed metadata. deleted_at: anyOf: - type: string format: date-time - type: 'null' title: Deleted At description: Optional timestamp of when the directory was deleted. Null if not deleted. type: object required: - id - project_id - name title: DirectoryResponse description: API response schema for a directory. LlamaParsePresentationOptions: properties: out_of_bounds_content: anyOf: - type: boolean - type: 'null' title: Out Of Bounds Content description: Extract content positioned outside the visible slide area. Some presentations have hidden notes or content that extends beyond slide boundaries skip_embedded_data: anyOf: - type: boolean - type: 'null' title: Skip Embedded Data description: Skip extraction of embedded chart data tables. When true, only the visual representation of charts is captured, not the underlying data additionalProperties: false type: object title: LlamaParsePresentationOptions description: Presentation (PowerPoint, Keynote, ODP) parsing options. ConfigurationResponse: properties: id: type: string title: Id description: Unique configuration ID. created_at: anyOf: - type: string format: date-time - type: 'null' title: Created At description: Creation timestamp. updated_at: anyOf: - type: string format: date-time - type: 'null' title: Updated At description: Last update timestamp. name: type: string title: Name description: Configuration name. product_type: type: string enum: - split_v1 - extract_v2 - classify_v2 - parse_v2 - spreadsheet_v1 - unknown title: Product Type description: Product type. version: type: string title: Version description: Version identifier (datetime string). parameters: oneOf: - $ref: '#/components/schemas/SplitV1Parameters' - $ref: '#/components/schemas/ExtractV2Parameters' - $ref: '#/components/schemas/ClassifyV2Parameters' - $ref: '#/components/schemas/ParseV2Parameters' - $ref: '#/components/schemas/SpreadsheetV1Parameters' - $ref: '#/components/schemas/UntypedParameters' title: Parameters description: Product-specific configuration parameters. discriminator: propertyName: product_type mapping: classify_v2: '#/components/schemas/ClassifyV2Parameters' extract_v2: '#/components/schemas/ExtractV2Parameters' parse_v2: '#/components/schemas/ParseV2Parameters' split_v1: '#/components/schemas/SplitV1Parameters' spreadsheet_v1: '#/components/schemas/SpreadsheetV1Parameters' unknown: '#/components/schemas/UntypedParameters' type: object required: - id - name - product_type - version - parameters title: ConfigurationResponse description: Response schema for a single product configuration. ClassificationResult: properties: reasoning: type: string title: Reasoning description: Step-by-step explanation of why this classification was chosen and the confidence score assigned confidence: type: number maximum: 1.0 minimum: 0.0 title: Confidence description: Confidence score of the classification (0.0-1.0) type: anyOf: - type: string - type: 'null' title: Type description: The document type that best matches, or null if no match. type: object required: - reasoning - confidence - type title: ClassificationResult description: Result of classifying a single file. ClassifyV2Parameters: properties: rules: items: $ref: '#/components/schemas/ClassifyV2Rule' type: array minItems: 1 title: Rules description: Classify rules to evaluate against the document (at least one required) mode: type: string const: FAST title: Mode description: Classify execution mode default: FAST parsing_configuration: anyOf: - $ref: '#/components/schemas/ClassifyV2ParsingConfiguration' - type: 'null' description: Parsing configuration for controlling which pages are read product_type: type: string const: classify_v2 title: Product Type description: Product type. type: object required: - rules - product_type title: ClassifyV2Parameters description: Typed parameters for a *classify v2* product configuration. SplitJobQueryResponse: properties: items: items: $ref: '#/components/schemas/SplitJobResponse' type: array title: Items description: The list of items. next_page_token: anyOf: - type: string - type: 'null' title: Next Page Token description: A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. total_size: anyOf: - type: integer - type: 'null' title: Total Size description: The total number of items available. This is only populated when specifically requested. The value may be an estimate and can be used for display purposes only. type: object required: - items title: SplitJobQueryResponse description: Beta paginated list of split jobs. SplitCreateRequest: properties: document_input: $ref: '#/components/schemas/SplitDocumentInput' description: Document to be split. configuration: anyOf: - $ref: '#/components/schemas/SplitConfiguration' - type: 'null' description: Inline split configuration. configuration_id: anyOf: - type: string - type: 'null' title: Configuration Id description: Saved split configuration ID. type: object required: - document_input title: SplitCreateRequest description: Beta create request — accepts legacy document_input and flat formats. BatchJobStatusResponse: properties: job: $ref: '#/components/schemas/BatchJobResponse' progress_percentage: type: number maximum: 100.0 minimum: 0.0 title: Progress Percentage description: Percentage of items processed (0-100) type: object required: - job - progress_percentage title: BatchJobStatusResponse description: Detailed status response for a batch processing job. DeleteResponse: properties: deleted_count: type: integer title: Deleted Count type: object required: - deleted_count title: DeleteResponse description: API response for bulk delete operation PipelineFileResponse: properties: id: type: string format: uuid title: Id description: Unique identifier for the pipeline file. name: anyOf: - type: string - type: 'null' title: Name description: Name of the file. external_file_id: anyOf: - type: string - type: 'null' title: External File Id description: The ID of the file in the external system. file_size: anyOf: - type: integer - type: 'null' title: File Size description: Size of the file in bytes. file_type: anyOf: - type: string - type: 'null' title: File Type description: File type (e.g. pdf, docx, etc.). project_id: anyOf: - type: string format: uuid - type: 'null' title: Project Id description: The ID of the project that the file belongs to. last_modified_at: anyOf: - type: string format: date-time - type: 'null' title: Last Modified At description: The last modified time of the file. file_id: anyOf: - type: string format: uuid - type: 'null' title: File Id description: The ID of the file. pipeline_id: type: string format: uuid title: Pipeline Id description: The ID of the pipeline that the file is associated with. resource_info: anyOf: - additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object - type: 'null' title: Resource Info description: Resource information for the file. permission_info: anyOf: - additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object - type: 'null' title: Permission Info description: Permission information for the file. custom_metadata: anyOf: - additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object - type: 'null' title: Custom Metadata description: Custom metadata for the file. data_source_id: anyOf: - type: string format: uuid - type: 'null' title: Data Source Id description: The ID of the data source that the file belongs to. status: anyOf: - type: string enum: - NOT_STARTED - IN_PROGRESS - SUCCESS - ERROR - CANCELLED - type: 'null' title: Status description: Status of the pipeline file. status_updated_at: anyOf: - type: string format: date-time - type: 'null' title: Status Updated At description: The last time the status was updated. created_at: anyOf: - type: string format: date-time - type: 'null' title: Created At description: When the pipeline file was created. updated_at: anyOf: - type: string format: date-time - type: 'null' title: Updated At description: When the pipeline file was last updated. type: object required: - id - pipeline_id title: PipelineFileResponse description: Beta API response schema for a pipeline file. BatchJobCancelRequest: properties: reason: anyOf: - type: string - type: 'null' title: Reason description: Optional reason for cancelling the job type: object title: BatchJobCancelRequest description: Request to cancel a running batch job. ParseV2Parameters: properties: tier: type: string enum: - fast - cost_effective - agentic - agentic_plus title: Tier description: 'Parsing tier: ''fast'' (rule-based, cheapest), ''cost_effective'' (balanced), ''agentic'' (AI-powered with custom prompts), or ''agentic_plus'' (premium AI with highest accuracy)' version: anyOf: - type: string enum: - latest - '2026-06-05' - '2026-06-04' - '2025-12-11' x-enum-order-preserved: true - type: string title: Version description: 'Version for the selected tier. Use `latest`, or pin one of that tier''s dated versions. Current `latest` by tier: - `fast`: `2025-12-11` - `cost_effective`: `2026-06-05` - `agentic`: `2026-06-04` - `agentic_plus`: `2026-06-04` Full list: `GET /api/v2/parse/versions`.' client_name: anyOf: - type: string - type: 'null' title: Client Name description: 'Identifier for the client/application making the request. Used for analytics and debugging. Example: ''my-app-v2''' processing_options: $ref: '#/components/schemas/LlamaParseProcessingOptions' description: Document processing options including OCR, table extraction, and chart parsing fast_options: anyOf: - $ref: '#/components/schemas/LlamaParseFastOptions' - type: 'null' description: Fast tier configuration options. Auto-initialized when tier='fast'. Cannot be used with other tiers agentic_options: anyOf: - $ref: '#/components/schemas/LlamaParseAgenticOptions' - type: 'null' description: AI-powered tier configuration (custom prompts). Auto-initialized for cost_effective/agentic/agentic_plus tiers. Cannot be used with fast tier webhook_configurations: items: $ref: '#/components/schemas/LlamaParseWebhookConfiguration' type: array title: Webhook Configurations description: Webhook endpoints for job status notifications. Multiple webhooks can be configured for different events or services input_options: $ref: '#/components/schemas/LlamaParseInputOptions' description: Format-specific options (HTML, PDF, spreadsheet, presentation). Applied based on detected input file type crop_box: $ref: '#/components/schemas/LlamaParseCropBox' description: Crop boundaries to process only a portion of each page. Values are ratios 0-1 from page edges page_ranges: $ref: '#/components/schemas/LlamaParsePageRanges' description: 'Page selection: limit total pages or specify exact pages to process' disable_cache: anyOf: - type: boolean - type: 'null' title: Disable Cache description: Bypass result caching and force re-parsing. Use when document content may have changed or you need fresh results output_options: $ref: '#/components/schemas/LlamaParseOutputOptions' description: Output formatting options for markdown, text, and extracted images processing_control: $ref: '#/components/schemas/LlamaParseProcessingControl' description: Job execution controls including timeouts and failure thresholds product_type: type: string const: parse_v2 title: Product Type description: Product type. type: object required: - tier - version - product_type title: ParseV2Parameters description: 'Configuration for LlamaParse v2 document parsing. Includes tier selection, processing options, output formatting, page targeting, and webhook delivery. Refer to the LlamaParse documentation for details on each field.' LlamaParseHtmlOptions: properties: make_all_elements_visible: anyOf: - type: boolean - type: 'null' title: Make All Elements Visible description: Force all HTML elements to be visible by overriding CSS display/visibility properties. Useful for parsing pages with hidden content or collapsed sections remove_fixed_elements: anyOf: - type: boolean - type: 'null' title: Remove Fixed Elements description: Remove fixed-position elements (headers, footers, floating buttons) that appear on every page render remove_navigation_elements: anyOf: - type: boolean - type: 'null' title: Remove Navigation Elements description: Remove navigation elements (nav bars, sidebars, menus) to focus on main content additionalProperties: false type: object title: LlamaParseHtmlOptions description: HTML/web page parsing options. ClassifyV2ParsingConfiguration: properties: lang: type: string title: Lang description: ISO 639-1 language code for the document default: en examples: - en - es - zh target_pages: anyOf: - type: string - type: 'null' title: Target Pages description: Comma-separated page numbers or ranges to process (1-based). Omit to process all pages. examples: - 1,3,5-7 - 1-3,8-10 max_pages: anyOf: - type: integer minimum: 1.0 - type: 'null' title: Max Pages description: Maximum number of pages to process. Omit for no limit. examples: - 10 type: object title: ClassifyV2ParsingConfiguration description: Parsing configuration for classify jobs. LlamaParseProcessingOptions: properties: ignore: $ref: '#/components/schemas/LlamaParseIgnoreOptions' description: Options for ignoring specific text types (diagonal, hidden, text in images) ocr_parameters: $ref: '#/components/schemas/LlamaParseOcrParameters' description: OCR configuration including language detection settings aggressive_table_extraction: anyOf: - type: boolean - type: 'null' title: Aggressive Table Extraction description: Use aggressive heuristics to detect table boundaries, even without visible borders. Useful for documents with borderless or complex tables disable_heuristics: anyOf: - type: boolean - type: 'null' title: Disable Heuristics description: Disable automatic heuristics including outlined table extraction and adaptive long table handling. Use when heuristics produce incorrect results specialized_chart_parsing: anyOf: - type: string enum: - agentic_plus - agentic - efficient - type: 'null' title: Specialized Chart Parsing description: 'Enable AI-powered chart analysis. Modes: ''efficient'' (fast, lower cost), ''agentic'' (balanced), ''agentic_plus'' (highest accuracy). Automatically enables extract_layout and precise_bounding_box when set' cost_optimizer: anyOf: - $ref: '#/components/schemas/LlamaParseCostOptimizerParameters' - type: 'null' description: Cost optimization settings. Only available with 'agentic' or 'agentic_plus' tiers auto_mode_configuration: anyOf: - items: $ref: '#/components/schemas/AutoModeConfigurationEntry' type: array - type: 'null' title: Auto Mode Configuration description: Conditional processing rules that apply different parsing options based on page content, document structure, or filename patterns. Each entry defines trigger conditions and the parsing configuration to apply when triggered additionalProperties: false type: object title: LlamaParseProcessingOptions description: 'Processing options shared across all parsing tiers. These options control how documents are analyzed and processed regardless of the selected tier. Some options automatically enable additional behaviors (e.g., specialized_chart_parsing enables extract_layout and precise_bounding_box).' FileV2: properties: id: type: string title: Id description: Unique file identifier examples: - dfl-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee name: type: string maxLength: 3000 minLength: 1 title: Name description: File name including extension examples: - invoice.pdf external_file_id: anyOf: - type: string - type: 'null' title: External File Id description: Optional ID for correlating with an external system examples: - ext-12345 file_type: anyOf: - type: string maxLength: 3000 minLength: 1 - type: 'null' title: File Type description: File extension (pdf, docx, png, etc.) examples: - pdf project_id: type: string format: uuid title: Project Id description: Project this file belongs to examples: - 123e4567-e89b-12d3-a456-426614174000 last_modified_at: anyOf: - type: string format: date-time - type: 'null' title: Last Modified At description: When the file was last modified (ISO 8601) expires_at: anyOf: - type: string format: date-time - type: 'null' title: Expires At description: When the file expires and may be automatically removed. Null means no expiration. purpose: anyOf: - type: string - type: 'null' title: Purpose description: 'How the file will be used: user_data, parse, extract, classify, split, sheet, or agent_app' examples: - parse download_url: anyOf: - $ref: '#/components/schemas/PresignedUrl' - type: 'null' description: Presigned URL to download the file content. type: object required: - id - name - project_id title: FileV2 description: An uploaded file. LlamaParseCostOptimizerParameters: properties: enable: anyOf: - type: boolean - type: 'null' title: Enable description: 'Enable cost-optimized parsing. Routes simpler pages to faster processing while complex pages use full AI analysis. May reduce speed on some documents. IMPORTANT: Only available with ''agentic'' or ''agentic_plus'' tiers' additionalProperties: false type: object title: LlamaParseCostOptimizerParameters description: 'Cost optimizer configuration for reducing parsing costs on simpler pages. When enabled, the parser analyzes each page and routes simpler pages to faster, cheaper processing while preserving quality for complex pages. Only works with ''agentic'' or ''agentic_plus'' tiers.' ProcessingResultMetadata: properties: {} type: object title: ProcessingResultMetadata description: 'Metadata about processing output. Currently empty - will be populated with job-type-specific metadata fields in the future.' SearchRequest: properties: page_size: anyOf: - type: integer - type: 'null' title: Page Size description: The maximum number of items to return. The service may return fewer than this value. If unspecified, a default page size will be used. The maximum value is typically 1000; values above this will be coerced to the maximum. page_token: anyOf: - type: string - type: 'null' title: Page Token description: A page token, received from a previous list call. Provide this to retrieve the subsequent page. filter: anyOf: - additionalProperties: $ref: '#/components/schemas/FilterOperation' type: object - type: 'null' title: Filter description: A filter object or expression that filters resources listed in the response. order_by: anyOf: - type: string - type: 'null' title: Order By description: A comma-separated list of fields to order by, sorted in ascending order. Use 'field_name desc' to specify descending order. deployment_name: type: string title: Deployment Name description: The agent deployment's name to search within collection: type: string title: Collection description: The logical agent data collection to search within default: default include_total: type: boolean title: Include Total description: Whether to include the total number of items in the response default: false offset: anyOf: - type: integer maximum: 1000.0 minimum: 0.0 - type: 'null' title: Offset description: The offset to start from. If not provided, the first page is returned default: 0 type: object required: - deployment_name title: SearchRequest description: API request body for searching agent data FailPageMode: type: string enum: - raw_text - blank_page - error_message title: FailPageMode description: Enum for representing the different available page error handling modes. AutoModeSpatialTextOptions: properties: preserve_layout_alignment_across_pages: anyOf: - type: boolean - type: 'null' title: Preserve Layout Alignment Across Pages description: Preserve text alignment across page boundaries preserve_very_small_text: anyOf: - type: boolean - type: 'null' title: Preserve Very Small Text description: Include very small text in spatial output do_not_unroll_columns: anyOf: - type: boolean - type: 'null' title: Do Not Unroll Columns description: Keep column structure intact without unrolling additionalProperties: false type: object title: AutoModeSpatialTextOptions description: Spatial text options for auto mode parsing configuration. SpreadsheetResultType: type: string enum: - table - extra - cell_metadata title: SpreadsheetResultType AggregateGroup: properties: group_key: additionalProperties: true type: object title: Group Key count: anyOf: - type: integer - type: 'null' title: Count first_item: anyOf: - additionalProperties: true type: object - type: 'null' title: First Item type: object required: - group_key title: AggregateGroup description: API Result for a single group in the aggregate response ClassifierRule: properties: type: type: string maxLength: 50 minLength: 1 title: Type description: The document type to assign when this rule matches (e.g., 'invoice', 'receipt', 'contract') examples: - invoice - receipt - contract - report - proposal description: type: string maxLength: 500 minLength: 10 title: Description description: Natural language description of what to classify. Be specific about the content characteristics that identify this document type. examples: - contains invoice number, line items, and total amount - purchase receipt with transaction info and merchant details - legal contract with terms, conditions, and signatures type: object required: - type - description title: ClassifierRule description: 'A rule for classifying documents - v0 simplified version. This represents a single classification rule that will be applied to documents. All rules are content-based and use natural language descriptions.' LlamaParseTimeouts: properties: base_in_seconds: anyOf: - type: integer maximum: 7200.0 exclusiveMinimum: 0.0 - type: 'null' title: Base In Seconds description: Base timeout for the job in seconds (max 7200 = 2 hours). This is the minimum time allowed regardless of document size extra_time_per_page_in_seconds: anyOf: - type: integer maximum: 300.0 exclusiveMinimum: 0.0 - type: 'null' title: Extra Time Per Page In Seconds description: Additional timeout per page in seconds (max 300 = 5 minutes). Total timeout = base + (this value × page count) additionalProperties: false type: object title: LlamaParseTimeouts description: 'Job timeout configuration. Total timeout = base_in_seconds + (extra_time_per_page_in_seconds × page_count). Use these settings for large documents or complex parsing that needs more time.' ExtractV2Parameters: properties: target_pages: anyOf: - type: string - type: 'null' title: Target Pages description: Comma-separated page numbers or ranges to process (1-based). Omit to process all pages. examples: - 1,3,5-7 - 1-3,8-10 max_pages: anyOf: - type: integer minimum: 1.0 - type: 'null' title: Max Pages description: Maximum number of pages to process. Omit for no limit. examples: - 10 tier: type: string enum: - cost_effective - agentic title: Tier description: 'Extract tier: cost_effective (5 credits/page) or agentic (15 credits/page)' default: cost_effective examples: - cost_effective - agentic version: type: string title: Version description: Use 'latest' for the latest release for the selected tier or a date string (YYYY-MM-DD format) to pin to the nearest release at or before that date. default: latest examples: - latest data_schema: additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object title: Data Schema description: JSON Schema defining the fields to extract. Validate with the /schema/validate endpoint first. extraction_target: type: string enum: - per_doc - per_page - per_table_row title: Extraction Target description: 'Granularity of extraction: per_doc returns one object per document, per_page returns one object per page, per_table_row returns one object per table row' default: per_doc examples: - per_doc - per_page - per_table_row system_prompt: anyOf: - type: string - type: 'null' title: System Prompt description: Custom system prompt to guide extraction behavior examples: - Extract all monetary values in USD. If a currency is not specified, assume USD. cite_sources: type: boolean title: Cite Sources description: Include citations in results default: false confidence_scores: type: boolean title: Confidence Scores description: Include confidence scores in results default: false parse_tier: anyOf: - type: string - type: 'null' title: Parse Tier description: Parse tier to use before extraction. Defaults to the extract tier if not specified. examples: - fast - cost_effective parse_config_id: anyOf: - type: string - type: 'null' title: Parse Config Id description: Saved parse configuration ID to control how the document is parsed before extraction examples: - cfg-11111111-2222-3333-4444-555555555555 product_type: type: string const: extract_v2 title: Product Type description: Product type. type: object required: - data_schema - product_type title: ExtractV2Parameters description: Typed parameters for an *extract v2* product configuration. SplitV1Parameters: properties: categories: items: $ref: '#/components/schemas/SplitCategory' type: array maxItems: 50 minItems: 1 title: Categories description: Categories to split documents into. splitting_strategy: $ref: '#/components/schemas/SplitStrategy' description: Strategy for splitting documents. product_type: type: string const: split_v1 title: Product Type description: Product type. type: object required: - categories - product_type title: SplitV1Parameters description: Typed parameters for a *split v1* product configuration. UntypedParameters: properties: product_type: type: string const: unknown title: Product Type description: Product type. additionalProperties: true type: object required: - product_type title: UntypedParameters description: 'Catch-all for configurations without a dedicated typed schema. Accepts arbitrary JSON fields alongside ``product_type``.' PaginatedResponse_AgentData_: properties: items: items: $ref: '#/components/schemas/AgentData' type: array title: Items description: The list of items. next_page_token: anyOf: - type: string - type: 'null' title: Next Page Token description: A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. total_size: anyOf: - type: integer - type: 'null' title: Total Size description: The total number of items available. This is only populated when specifically requested. The value may be an estimate and can be used for display purposes only. type: object required: - items title: PaginatedResponse[AgentData] PresignedUrl: properties: url: type: string minLength: 1 format: uri title: Url description: A presigned URL for IO operations against a private file expires_at: type: string format: date-time title: Expires At description: The time at which the presigned URL expires form_fields: anyOf: - additionalProperties: type: string type: object - type: 'null' title: Form Fields description: Form fields for a presigned POST request type: object required: - url - expires_at title: PresignedUrl description: Schema for a presigned URL. MetadataListValue: items: type: string type: array LlamaParseSpatialTextOptions: properties: preserve_layout_alignment_across_pages: anyOf: - type: boolean - type: 'null' title: Preserve Layout Alignment Across Pages description: Maintain consistent text column alignment across page boundaries. Automatically enabled for document-level parsing modes preserve_very_small_text: anyOf: - type: boolean - type: 'null' title: Preserve Very Small Text description: Include text below the normal size threshold. Useful for footnotes, watermarks, or fine print that might otherwise be filtered out do_not_unroll_columns: anyOf: - type: boolean - type: 'null' title: Do Not Unroll Columns description: Keep multi-column layouts intact instead of linearizing columns into sequential text. Automatically enabled for non-fast tiers additionalProperties: false type: object title: LlamaParseSpatialTextOptions description: 'Spatial text output options for preserving document layout. Spatial text maintains the visual positioning of text elements, useful for documents where layout conveys meaning (forms, tables, multi-column layouts).' LlamaParseFastOptions: properties: {} additionalProperties: false type: object title: LlamaParseFastOptions description: 'Options for fast tier parsing (rule-based, no AI). Fast tier uses deterministic algorithms for text extraction without AI enhancement. It''s the fastest and most cost-effective option, best suited for simple documents with standard layouts. Currently has no configurable options but reserved for future expansion.' BatchFileStatus: type: string enum: - pending - processing - completed - failed - skipped - cancelled title: BatchFileStatus description: Status of an individual file in a batch job. ItemProcessingResultsResponse: properties: item_id: type: string title: Item Id description: ID of the source item item_name: type: string title: Item Name description: Name of the source item processing_results: items: $ref: '#/components/schemas/ProcessingResult' type: array title: Processing Results description: List of all processing operations performed on this item type: object required: - item_id - item_name title: ItemProcessingResultsResponse description: Response containing all processing results for an item. BatchParseJobConfig: properties: webhook_configurations: anyOf: - items: $ref: '#/components/schemas/WebhookConfiguration' type: array - type: 'null' title: Webhook Configurations description: Outbound webhook endpoints to notify on job status changes priority: anyOf: - type: string enum: - low - medium - high - critical - type: 'null' title: Priority description: The priority for the request. This field may be ignored or overwritten depending on the organization tier. custom_metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: Custom Metadata description: The custom metadata to attach to the documents. resource_info: anyOf: - additionalProperties: true type: object - type: 'null' title: Resource Info description: The resource info about the file languages: items: $ref: '#/components/schemas/ParserLanguages' type: array minItems: 1 title: Languages parsing_instruction: anyOf: - type: string - type: 'null' title: Parsing Instruction default: '' disable_ocr: anyOf: - type: boolean - type: 'null' title: Disable Ocr default: false annotate_links: anyOf: - type: boolean - type: 'null' title: Annotate Links default: false adaptive_long_table: anyOf: - type: boolean - type: 'null' title: Adaptive Long Table default: false compact_markdown_table: anyOf: - type: boolean - type: 'null' title: Compact Markdown Table default: false disable_reconstruction: anyOf: - type: boolean - type: 'null' title: Disable Reconstruction default: false disable_image_extraction: anyOf: - type: boolean - type: 'null' title: Disable Image Extraction default: false invalidate_cache: anyOf: - type: boolean - type: 'null' title: Invalidate Cache default: false outlined_table_extraction: anyOf: - type: boolean - type: 'null' title: Outlined Table Extraction default: false aggressive_table_extraction: anyOf: - type: boolean - type: 'null' title: Aggressive Table Extraction default: false merge_tables_across_pages_in_markdown: anyOf: - type: boolean - type: 'null' title: Merge Tables Across Pages In Markdown default: false output_pdf_of_document: anyOf: - type: boolean - type: 'null' title: Output Pdf Of Document default: false do_not_cache: anyOf: - type: boolean - type: 'null' title: Do Not Cache default: false fast_mode: anyOf: - type: boolean - type: 'null' title: Fast Mode default: false skip_diagonal_text: anyOf: - type: boolean - type: 'null' title: Skip Diagonal Text default: false preserve_layout_alignment_across_pages: anyOf: - type: boolean - type: 'null' title: Preserve Layout Alignment Across Pages default: false preserve_very_small_text: anyOf: - type: boolean - type: 'null' title: Preserve Very Small Text default: false gpt4o_mode: anyOf: - type: boolean - type: 'null' title: Gpt4O Mode default: false gpt4o_api_key: anyOf: - type: string - type: 'null' title: Gpt4O Api Key do_not_unroll_columns: anyOf: - type: boolean - type: 'null' title: Do Not Unroll Columns default: false extract_layout: anyOf: - type: boolean - type: 'null' title: Extract Layout default: false high_res_ocr: anyOf: - type: boolean - type: 'null' title: High Res Ocr default: false html_make_all_elements_visible: anyOf: - type: boolean - type: 'null' title: Html Make All Elements Visible default: false layout_aware: anyOf: - type: boolean - type: 'null' title: Layout Aware default: false specialized_chart_parsing_agentic: anyOf: - type: boolean - type: 'null' title: Specialized Chart Parsing Agentic default: false specialized_chart_parsing_plus: anyOf: - type: boolean - type: 'null' title: Specialized Chart Parsing Plus default: false specialized_chart_parsing_efficient: anyOf: - type: boolean - type: 'null' title: Specialized Chart Parsing Efficient default: false specialized_image_parsing: anyOf: - type: boolean - type: 'null' title: Specialized Image Parsing default: false precise_bounding_box: anyOf: - type: boolean - type: 'null' title: Precise Bounding Box default: false line_level_bounding_box: anyOf: - type: boolean - type: 'null' title: Line Level Bounding Box default: false html_remove_navigation_elements: anyOf: - type: boolean - type: 'null' title: Html Remove Navigation Elements default: false html_remove_fixed_elements: anyOf: - type: boolean - type: 'null' title: Html Remove Fixed Elements default: false guess_xlsx_sheet_name: anyOf: - type: boolean - type: 'null' title: Guess Xlsx Sheet Name default: false page_separator: anyOf: - type: string - type: 'null' title: Page Separator bounding_box: anyOf: - type: string - type: 'null' title: Bounding Box bbox_top: anyOf: - type: number - type: 'null' title: Bbox Top bbox_right: anyOf: - type: number - type: 'null' title: Bbox Right bbox_bottom: anyOf: - type: number - type: 'null' title: Bbox Bottom bbox_left: anyOf: - type: number - type: 'null' title: Bbox Left target_pages: anyOf: - type: string - type: 'null' title: Target Pages use_vendor_multimodal_model: anyOf: - type: boolean - type: 'null' title: Use Vendor Multimodal Model default: false vendor_multimodal_model_name: anyOf: - type: string - type: 'null' title: Vendor Multimodal Model Name model: anyOf: - type: string - type: 'null' title: Model vendor_multimodal_api_key: anyOf: - type: string - type: 'null' title: Vendor Multimodal Api Key page_prefix: anyOf: - type: string - type: 'null' title: Page Prefix page_suffix: anyOf: - type: string - type: 'null' title: Page Suffix webhook_url: anyOf: - type: string - type: 'null' title: Webhook Url preset: anyOf: - type: string - type: 'null' title: Preset take_screenshot: anyOf: - type: boolean - type: 'null' title: Take Screenshot default: false is_formatting_instruction: anyOf: - type: boolean - type: 'null' title: Is Formatting Instruction default: true premium_mode: anyOf: - type: boolean - type: 'null' title: Premium Mode default: false continuous_mode: anyOf: - type: boolean - type: 'null' title: Continuous Mode default: false input_s3_path: anyOf: - type: string - type: 'null' title: Input S3 Path input_s3_region: anyOf: - type: string - type: 'null' title: Input S3 Region description: The region for the input S3 bucket. output_s3_path_prefix: anyOf: - type: string - type: 'null' title: Output S3 Path Prefix description: If specified, llamaParse will save the output to the specified path. All output file will use this 'prefix' should be a valid s3:// url output_s3_region: anyOf: - type: string - type: 'null' title: Output S3 Region description: The region for the output S3 bucket. project_id: anyOf: - type: string - type: 'null' title: Project Id azure_openai_deployment_name: anyOf: - type: string - type: 'null' title: Azure Openai Deployment Name azure_openai_endpoint: anyOf: - type: string - type: 'null' title: Azure Openai Endpoint azure_openai_api_version: anyOf: - type: string - type: 'null' title: Azure Openai Api Version azure_openai_key: anyOf: - type: string - type: 'null' title: Azure Openai Key input_url: anyOf: - type: string - type: 'null' title: Input Url http_proxy: anyOf: - type: string - type: 'null' title: Http Proxy auto_mode: anyOf: - type: boolean - type: 'null' title: Auto Mode default: false auto_mode_trigger_on_regexp_in_page: anyOf: - type: string - type: 'null' title: Auto Mode Trigger On Regexp In Page auto_mode_trigger_on_text_in_page: anyOf: - type: string - type: 'null' title: Auto Mode Trigger On Text In Page auto_mode_trigger_on_table_in_page: anyOf: - type: boolean - type: 'null' title: Auto Mode Trigger On Table In Page default: false auto_mode_trigger_on_image_in_page: anyOf: - type: boolean - type: 'null' title: Auto Mode Trigger On Image In Page default: false auto_mode_configuration_json: anyOf: - type: string - type: 'null' title: Auto Mode Configuration Json structured_output: anyOf: - type: boolean - type: 'null' title: Structured Output default: false structured_output_json_schema: anyOf: - type: string - type: 'null' title: Structured Output Json Schema structured_output_json_schema_name: anyOf: - type: string - type: 'null' title: Structured Output Json Schema Name max_pages: anyOf: - type: integer - type: 'null' title: Max Pages max_pages_enforced: anyOf: - type: integer - type: 'null' title: Max Pages Enforced extract_charts: anyOf: - type: boolean - type: 'null' title: Extract Charts default: false formatting_instruction: anyOf: - type: string - type: 'null' title: Formatting Instruction complemental_formatting_instruction: anyOf: - type: string - type: 'null' title: Complemental Formatting Instruction content_guideline_instruction: anyOf: - type: string - type: 'null' title: Content Guideline Instruction spreadsheet_extract_sub_tables: anyOf: - type: boolean - type: 'null' title: Spreadsheet Extract Sub Tables default: false spreadsheet_force_formula_computation: anyOf: - type: boolean - type: 'null' title: Spreadsheet Force Formula Computation default: false spreadsheet_include_hidden_sheets: anyOf: - type: boolean - type: 'null' title: Spreadsheet Include Hidden Sheets default: false inline_images_in_markdown: anyOf: - type: boolean - type: 'null' title: Inline Images In Markdown default: false job_timeout_in_seconds: anyOf: - type: number - type: 'null' title: Job Timeout In Seconds job_timeout_extra_time_per_page_in_seconds: anyOf: - type: number - type: 'null' title: Job Timeout Extra Time Per Page In Seconds strict_mode_image_extraction: anyOf: - type: boolean - type: 'null' title: Strict Mode Image Extraction default: false strict_mode_image_ocr: anyOf: - type: boolean - type: 'null' title: Strict Mode Image Ocr default: false strict_mode_reconstruction: anyOf: - type: boolean - type: 'null' title: Strict Mode Reconstruction default: false strict_mode_buggy_font: anyOf: - type: boolean - type: 'null' title: Strict Mode Buggy Font default: false save_images: anyOf: - type: boolean - type: 'null' title: Save Images default: true images_to_save: anyOf: - items: type: string enum: - screenshot - embedded - layout type: array - type: 'null' title: Images To Save hide_headers: anyOf: - type: boolean - type: 'null' title: Hide Headers default: false hide_footers: anyOf: - type: boolean - type: 'null' title: Hide Footers default: false page_header_prefix: anyOf: - type: string - type: 'null' title: Page Header Prefix page_header_suffix: anyOf: - type: string - type: 'null' title: Page Header Suffix page_footer_prefix: anyOf: - type: string - type: 'null' title: Page Footer Prefix page_footer_suffix: anyOf: - type: string - type: 'null' title: Page Footer Suffix remove_hidden_text: anyOf: - type: boolean - type: 'null' title: Remove Hidden Text default: false keep_page_separator_when_merging_tables: anyOf: - type: boolean - type: 'null' title: Keep Page Separator When Merging Tables default: false ignore_document_elements_for_layout_detection: anyOf: - type: boolean - type: 'null' title: Ignore Document Elements For Layout Detection default: false output_tables_as_HTML: anyOf: - type: boolean - type: 'null' title: Output Tables As Html default: false internal_is_screenshot_job: anyOf: - type: boolean - type: 'null' title: Internal Is Screenshot Job default: false parse_mode: anyOf: - $ref: '#/components/schemas/ParsingMode' - type: 'null' system_prompt: anyOf: - type: string - type: 'null' title: System Prompt system_prompt_append: anyOf: - type: string - type: 'null' title: System Prompt Append user_prompt: anyOf: - type: string - type: 'null' title: User Prompt page_error_tolerance: anyOf: - type: number - type: 'null' title: Page Error Tolerance default: 0.05 replace_failed_page_mode: anyOf: - $ref: '#/components/schemas/FailPageMode' - type: 'null' default: raw_text replace_failed_page_with_error_message_prefix: anyOf: - type: string - type: 'null' title: Replace Failed Page With Error Message Prefix replace_failed_page_with_error_message_suffix: anyOf: - type: string - type: 'null' title: Replace Failed Page With Error Message Suffix markdown_table_multiline_header_separator: anyOf: - type: string - type: 'null' title: Markdown Table Multiline Header Separator presentation_out_of_bounds_content: anyOf: - type: boolean - type: 'null' title: Presentation Out Of Bounds Content default: false presentation_skip_embedded_data: anyOf: - type: boolean - type: 'null' title: Presentation Skip Embedded Data default: false tier: anyOf: - type: string - type: 'null' title: Tier version: anyOf: - type: string - type: 'null' title: Version extract_printed_page_number: anyOf: - type: boolean - type: 'null' title: Extract Printed Page Number default: false enable_cost_optimizer: anyOf: - type: boolean - type: 'null' title: Enable Cost Optimizer type: type: string const: parse title: Type default: parse lang: type: string title: Lang description: The language. default: en outputBucket: anyOf: - type: string - type: 'null' title: Outputbucket description: The output bucket. pipeline_id: anyOf: - type: string - type: 'null' title: Pipeline Id description: The pipeline ID. type: object title: BatchParseJobConfig description: 'Generic parse job configuration for batch processing. This model contains the parsing configuration that applies to all files in a batch, but excludes file-specific fields like file_name, file_id, etc. Those file-specific fields are populated from DirectoryFile data when creating individual ParseJobRecordCreate instances for each file. The fields in this model should be generic settings that apply uniformly to all files being processed in the batch.' AgentData: properties: id: anyOf: - type: string - type: 'null' title: Id deployment_name: type: string title: Deployment Name project_id: anyOf: - type: string - type: 'null' title: Project Id collection: type: string title: Collection default: default data: additionalProperties: true type: object title: Data created_at: anyOf: - type: string format: date-time - type: 'null' title: Created At updated_at: anyOf: - type: string format: date-time - type: 'null' title: Updated At type: object required: - deployment_name - data title: AgentData description: API Result for a single agent data item MetadataScalarValue: anyOf: - type: string - type: integer - type: number - type: boolean - type: 'null' MetadataValue: anyOf: - $ref: '#/components/schemas/MetadataScalarValue' - $ref: '#/components/schemas/MetadataListValue' AutoModeIgnoreOptions: properties: ignore_diagonal_text: anyOf: - type: boolean - type: 'null' title: Ignore Diagonal Text description: Whether to ignore diagonal text in the document ignore_hidden_text: anyOf: - type: boolean - type: 'null' title: Ignore Hidden Text description: Whether to ignore hidden text in the document additionalProperties: false type: object title: AutoModeIgnoreOptions description: Ignore options for auto mode parsing configuration. AutoModeCropBox: properties: bottom: anyOf: - type: number maximum: 1.0 minimum: 0.0 - type: 'null' title: Bottom description: Bottom boundary of crop box as ratio (0-1) left: anyOf: - type: number maximum: 1.0 minimum: 0.0 - type: 'null' title: Left description: Left boundary of crop box as ratio (0-1) right: anyOf: - type: number maximum: 1.0 minimum: 0.0 - type: 'null' title: Right description: Right boundary of crop box as ratio (0-1) top: anyOf: - type: number maximum: 1.0 minimum: 0.0 - type: 'null' title: Top description: Top boundary of crop box as ratio (0-1) additionalProperties: false type: object title: AutoModeCropBox description: Crop box options for auto mode parsing configuration. PaginatedResponse_SpreadsheetJob_: properties: items: items: $ref: '#/components/schemas/SpreadsheetJob' type: array title: Items description: The list of items. next_page_token: anyOf: - type: string - type: 'null' title: Next Page Token description: A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. total_size: anyOf: - type: integer - type: 'null' title: Total Size description: The total number of items available. This is only populated when specifically requested. The value may be an estimate and can be used for display purposes only. type: object required: - items title: PaginatedResponse[SpreadsheetJob] DirectoryQueryResponse: properties: items: items: $ref: '#/components/schemas/DirectoryResponse' type: array title: Items description: The list of items. next_page_token: anyOf: - type: string - type: 'null' title: Next Page Token description: A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. total_size: anyOf: - type: integer - type: 'null' title: Total Size description: The total number of items available. This is only populated when specifically requested. The value may be an estimate and can be used for display purposes only. type: object required: - items title: DirectoryQueryResponse description: API query response schema for directories. LlamaParseTablesAsSpreadsheetOptions: properties: enable: anyOf: - type: boolean - type: 'null' title: Enable description: Whether this option is enabled guess_sheet_name: type: boolean title: Guess Sheet Name description: Automatically generate descriptive sheet names from table context (headers, surrounding text) instead of using generic names like 'Table_1' default: true additionalProperties: false type: object title: LlamaParseTablesAsSpreadsheetOptions description: Options for exporting extracted tables as XLSX spreadsheet files. SplitJobResponse: properties: id: type: string title: Id description: Unique identifier for the split job. created_at: anyOf: - type: string format: date-time - type: 'null' title: Created At description: Creation datetime updated_at: anyOf: - type: string format: date-time - type: 'null' title: Updated At description: Update datetime project_id: type: string title: Project Id description: Project ID this job belongs to. user_id: type: string title: User Id description: User ID who created this job. configuration_id: anyOf: - type: string - type: 'null' title: Configuration Id description: Split configuration ID used for this job. document_input: $ref: '#/components/schemas/SplitDocumentInput' description: Document that was split. categories: items: $ref: '#/components/schemas/SplitCategory' type: array title: Categories description: Categories used for splitting. status: type: string title: Status description: 'Current status of the job. Valid values are: pending, processing, completed, failed, cancelled.' result: anyOf: - $ref: '#/components/schemas/SplitResultResponse' - type: 'null' description: Split result (available when status is COMPLETED). error_message: anyOf: - type: string - type: 'null' title: Error Message description: Error message if the job failed. type: object required: - id - project_id - user_id - document_input - categories - status title: SplitJobResponse description: Beta response — uses nested document_input object. DeleteRequest: properties: deployment_name: type: string title: Deployment Name description: The agent deployment's name to delete data for collection: type: string title: Collection description: The logical agent data collection to delete from default: default filter: anyOf: - additionalProperties: $ref: '#/components/schemas/FilterOperation' type: object - type: 'null' title: Filter description: Optional filters to select which items to delete type: object required: - deployment_name title: DeleteRequest description: API request body for bulk deleting agent data by query LlamaParseOutputOptions: properties: markdown: $ref: '#/components/schemas/LlamaParseMarkdownOptions' description: Markdown formatting options including table styles and link annotations spatial_text: $ref: '#/components/schemas/LlamaParseSpatialTextOptions' description: Spatial text output options for preserving document layout structure tables_as_spreadsheet: $ref: '#/components/schemas/LlamaParseTablesAsSpreadsheetOptions' description: Options for exporting tables as XLSX spreadsheets extract_printed_page_number: anyOf: - type: boolean - type: 'null' title: Extract Printed Page Number description: Extract the printed page number as it appears in the document (e.g., 'Page 5 of 10', 'v', 'A-3'). Useful for referencing original page numbers images_to_save: items: type: string enum: - screenshot - embedded - layout type: array title: Images To Save description: 'Image categories to extract and save. Options: ''screenshot'' (full page renders useful for visual QA), ''embedded'' (images found within the document), ''layout'' (cropped regions from layout detection like figures and diagrams). Empty list saves no images' additional_outputs: items: type: string type: array title: Additional Outputs description: 'Optional additional output artifacts to save alongside the primary parse output. Each value opts in to generating and persisting one extra file; the empty list (default) saves none. The three accepted values are: ''stripped_md'' — per-page markdown stripped of formatting (links, bold/italic, images, HTML), saved as JSON for full-text-search indexing; fetch via `expand=stripped_markdown_content_metadata`. ''concatenated_stripped_txt'' — all stripped pages concatenated into a single plain-text file with `\n\n---\n\n` between pages, useful for feeding the document into search or embedding pipelines as one blob; fetch via `expand=concatenated_stripped_markdown_content_metadata`. ''word_bbox'' — raw word-level bounding boxes (one JSON object per word, with page number and x/y/w/h coordinates) saved as JSONL, useful for highlighting or grounding extracted answers back to the source document; fetch via `expand=raw_words_content_metadata`.' examples: - - stripped_md - concatenated_stripped_txt - word_bbox granular_bboxes: items: type: string enum: - cell - line - word type: array title: Granular Bboxes description: Bounding-box granularity levels to compute for the parse. 'word' computes one bounding box per detected word; 'line' computes one per text line; 'cell' computes one per table cell. Multiple levels can be requested. Empty list (default) disables granular bboxes — only item-level layout boxes are returned on the result. When set, the computed boxes are not inlined on the result items; they are written to a separate `grounded_items` sidecar (JSONL, one row per page) and exposed as `result_content_metadata.grounded_items` (a presigned download URL) on the parse result. Each row matches the `GroundedJsonItem` shape. examples: - - word - line - cell additionalProperties: false type: object title: LlamaParseOutputOptions description: 'Output formatting and content extraction options. Controls how parsed content is formatted and what additional data is extracted.' LlamaParseMarkdownOptions: properties: annotate_links: anyOf: - type: boolean - type: 'null' title: Annotate Links description: Add link annotations to markdown output in the format [text](url). When false, only the link text is included tables: $ref: '#/components/schemas/LlamaParseTables' description: Table formatting options including markdown vs HTML format and merging behavior inline_images: anyOf: - type: boolean - type: 'null' title: Inline Images description: Embed images directly in markdown as base64 data URIs instead of extracting them as separate files. Useful for self-contained markdown output additionalProperties: false type: object title: LlamaParseMarkdownOptions description: Markdown output formatting options. LlamaParseAgenticOptions: properties: custom_prompt: anyOf: - type: string - type: 'null' title: Custom Prompt description: 'Custom instructions for the AI parser. Use to guide extraction behavior, specify output formatting, or provide domain-specific context. Example: ''Extract financial tables with currency symbols. Format dates as YYYY-MM-DD.''' additionalProperties: false type: object title: LlamaParseAgenticOptions description: 'Options for AI-powered parsing tiers (cost_effective, agentic, agentic_plus). These options customize how the AI processes and interprets document content. Only applicable when using non-fast tiers.' ParsingMode: type: string enum: - parse_page_without_llm - parse_page_with_llm - parse_page_with_lvm - parse_page_with_agent - parse_page_with_layout_agent - parse_document_with_llm - parse_document_with_lvm - parse_document_with_agent title: ParsingMode description: Enum for representing the mode of parsing to be used. SplitResultResponse: properties: segments: items: $ref: '#/components/schemas/SplitSegmentResponse' type: array title: Segments description: List of document segments. type: object required: - segments title: SplitResultResponse description: Result of a completed split job. FilterOperation: properties: eq: anyOf: - type: number - type: integer - type: string - type: string format: date-time - type: 'null' title: Eq ne: anyOf: - type: number - type: integer - type: string - type: string format: date-time - type: 'null' title: Ne gt: anyOf: - type: number - type: integer - type: string - type: string format: date-time - type: 'null' title: Gt gte: anyOf: - type: number - type: integer - type: string - type: string format: date-time - type: 'null' title: Gte lt: anyOf: - type: number - type: integer - type: string - type: string format: date-time - type: 'null' title: Lt lte: anyOf: - type: number - type: integer - type: string - type: string format: date-time - type: 'null' title: Lte includes: items: anyOf: - type: number - type: integer - type: string - type: string format: date-time - type: 'null' type: array title: Includes excludes: items: anyOf: - type: number - type: integer - type: string - type: string format: date-time - type: 'null' type: array title: Excludes type: object title: FilterOperation description: API request model for a filter comparison operation. DirectoryUpdateRequest: properties: name: anyOf: - type: string minLength: 1 - type: 'null' title: Name description: Updated name for the directory. description: anyOf: - type: string - type: 'null' title: Description description: Updated description for the directory. type: object title: DirectoryUpdateRequest description: API request schema for updating a directory. ConfigurationUpdateRequest: properties: name: anyOf: - type: string maxLength: 255 minLength: 1 - type: 'null' title: Name description: Updated name (omit to leave unchanged). parameters: anyOf: - oneOf: - $ref: '#/components/schemas/SplitV1Parameters' - $ref: '#/components/schemas/ExtractV2Parameters' - $ref: '#/components/schemas/ClassifyV2Parameters' - $ref: '#/components/schemas/ParseV2Parameters' - $ref: '#/components/schemas/SpreadsheetV1Parameters' - $ref: '#/components/schemas/UntypedParameters' discriminator: propertyName: product_type mapping: classify_v2: '#/components/schemas/ClassifyV2Parameters' extract_v2: '#/components/schemas/ExtractV2Parameters' parse_v2: '#/components/schemas/ParseV2Parameters' split_v1: '#/components/schemas/SplitV1Parameters' spreadsheet_v1: '#/components/schemas/SpreadsheetV1Parameters' unknown: '#/components/schemas/UntypedParameters' - type: 'null' title: Parameters description: Updated parameters (omit to leave unchanged). type: object title: ConfigurationUpdateRequest description: Request body for updating a product configuration. FileQueryResponseV2: properties: items: items: $ref: '#/components/schemas/FileV2' type: array title: Items description: The list of items. next_page_token: anyOf: - type: string - type: 'null' title: Next Page Token description: A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. total_size: anyOf: - type: integer - type: 'null' title: Total Size description: The total number of items available. This is only populated when specifically requested. The value may be an estimate and can be used for display purposes only. type: object required: - items title: FileQueryResponseV2 description: Paginated list of files. LlamaParseWebhookConfiguration: properties: webhook_url: anyOf: - type: string pattern: '^https?:' - type: 'null' title: Webhook Url description: HTTPS URL to receive webhook POST requests. Must be publicly accessible webhook_headers: anyOf: - additionalProperties: true type: object - type: 'null' title: Webhook Headers description: 'Custom HTTP headers to include in webhook requests. Use for authentication tokens or custom routing. Example: {''Authorization'': ''Bearer xyz''}' webhook_events: anyOf: - items: type: string type: array - type: 'null' title: Webhook Events description: 'Events that trigger this webhook. Options: ''parse.success'' (job completed), ''parse.error'' (job failed), ''parse.partial_success'' (some pages failed), ''parse.pending'', ''parse.running'', ''parse.cancelled''. If not specified, webhook fires for all events' examples: - - parse.success - parse.error webhook_output_format: anyOf: - type: string enum: - string - json - type: 'null' title: Webhook Output Format description: Format of the webhook payload body. 'string' (default) sends the payload as a JSON-encoded string; 'json' sends it as a JSON object. examples: - json additionalProperties: false type: object title: LlamaParseWebhookConfiguration description: 'Webhook configuration for receiving parsing job notifications. Webhooks are called when specified events occur during job processing. Configure multiple webhook configurations to send to different endpoints.' BatchJobCreateRequest: properties: directory_id: anyOf: - type: string - type: 'null' title: Directory Id description: ID of the directory containing files to process examples: - dir-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee item_ids: anyOf: - items: type: string type: array - type: 'null' title: Item Ids description: List of specific item IDs to process. Either this or directory_id must be provided. examples: - - dfl-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee - dfl-11111111-2222-3333-4444-555555555555 job_config: anyOf: - $ref: '#/components/schemas/BatchParseJobRecordCreate' - $ref: '#/components/schemas/ClassifyJob' title: Job Config description: Job configuration — either a parse or classify config page_size: type: integer maximum: 1000.0 minimum: 1.0 title: Page Size description: Number of files to process per batch when using directory mode default: 100 continue_as_new_threshold: anyOf: - type: integer - type: 'null' title: Continue As New Threshold description: Maximum files to process per execution cycle in directory mode. Defaults to page_size. type: object required: - job_config title: BatchJobCreateRequest description: 'Request to create a batch processing job. Supports two modes: 1. Directory mode: Process all files in a directory (use directory_id) 2. Item list mode: Process specific items (use item_ids). Project must be provided via validate_project dependency.' ConfigurationQueryResponse: properties: items: items: $ref: '#/components/schemas/ConfigurationResponse' type: array title: Items description: The list of items. next_page_token: anyOf: - type: string - type: 'null' title: Next Page Token description: A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. total_size: anyOf: - type: integer - type: 'null' title: Total Size description: The total number of items available. This is only populated when specifically requested. The value may be an estimate and can be used for display purposes only. type: object required: - items title: ConfigurationQueryResponse description: Paginated list of product configurations. ClassifyJob: properties: status: $ref: '#/components/schemas/StatusEnum' description: The status of the classify job effective_at: type: string format: date-time title: Effective At job_record_id: anyOf: - type: string - type: 'null' title: Job Record Id description: The job record ID associated with this status, if any. error_message: anyOf: - type: string - type: 'null' title: Error Message description: Error message for the latest job attempt, if any. id: type: string format: uuid title: Id description: Unique identifier created_at: anyOf: - type: string format: date-time - type: 'null' title: Created At description: Creation datetime updated_at: anyOf: - type: string format: date-time - type: 'null' title: Updated At description: Update datetime rules: items: $ref: '#/components/schemas/ClassifierRule' type: array minItems: 1 title: Rules description: The rules to classify the files user_id: type: string title: User Id description: The ID of the user project_id: type: string format: uuid title: Project Id description: The ID of the project mode: $ref: '#/components/schemas/ClassifyMode' description: The classification mode to use default: FAST parsing_configuration: $ref: '#/components/schemas/ClassifyParsingConfiguration' description: The configuration for the parsing job default: lang: en max_pages: 5 type: object required: - status - id - rules - user_id - project_id title: ClassifyJob description: A classify job. ParserLanguages: type: string enum: - af - az - bs - cs - cy - da - de - en - es - et - fr - ga - hr - hu - id - is - it - ku - la - lt - lv - mi - ms - mt - nl - 'no' - oc - pi - pl - pt - ro - rs_latin - sk - sl - sq - sv - sw - tl - tr - uz - vi - ar - fa - ug - ur - bn - as - mni - ru - rs_cyrillic - be - bg - uk - mn - abq - ady - kbd - ava - dar - inh - che - lbe - lez - tab - tjk - hi - mr - ne - bh - mai - ang - bho - mah - sck - new - gom - sa - bgc - th - ch_sim - ch_tra - ja - ko - ta - te - kn title: ParserLanguages description: Enum for representing the languages supported by the parser. UsageMetric: properties: id: type: string format: uuid title: Id description: The system-generated UUID for the metric user_id: type: string title: User Id description: The ID of the user event_type: type: string enum: - pages_indexed - pages_embedded - pages_parsed - set_total_pages_indexed - set_total_indexes - layout_extracted - layout_aware_parsing - layout_aware_chart_extraction - chart_parsing_agentic - chart_parsing_plus - chart_parsing_efficient - image_classified - precise_bbox_extraction - audio_seconds_parsed - extraction_num_pages - extraction_num_pages_parsed - pages_split - pages_classified - directory_file_count_snapshot - directory_count_snapshot title: Event Type description: The event type that is emitted project_id: type: string title: Project Id description: The project ID organization_id: type: string title: Organization Id description: The organization ID value: type: integer title: Value description: The unit measurement associated with the event type properties: additionalProperties: true type: object title: Properties description: Properties associated with the metric day: type: string title: Day description: The day the metric was emitted [UTC], in the format 'YYYY-MM-DD' event_aggregation_key: type: string title: Event Aggregation Key description: The source job identifier, i.e. job_id or file_id event_aggregation_type: type: string title: Event Aggregation Type description: The source job aggregation type, i.e. pdf credits: anyOf: - type: number - type: 'null' title: Credits description: The number of credits consumed by this metric type: object required: - id - user_id - event_type - project_id - organization_id - value - day - event_aggregation_key - event_aggregation_type title: UsageMetric description: API boundary representation of a usage metric. WebhookConfiguration: properties: webhook_url: anyOf: - type: string - type: 'null' title: Webhook Url description: URL to receive webhook POST notifications examples: - https://example.com/webhooks/llamacloud webhook_headers: anyOf: - additionalProperties: type: string type: object - type: 'null' title: Webhook Headers description: Custom HTTP headers sent with each webhook request (e.g. auth tokens) examples: - Authorization: Bearer sk-... webhook_events: anyOf: - items: type: string enum: - extract.pending - extract.success - extract.error - extract.partial_success - extract.cancelled - parse.pending - parse.running - parse.success - parse.error - parse.partial_success - parse.cancelled - classify.pending - classify.running - classify.success - classify.error - classify.partial_success - classify.cancelled - sheets.pending - sheets.success - sheets.error - sheets.partial_success - sheets.cancelled - unmapped_event type: array - type: 'null' title: Webhook Events description: Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered. examples: - - parse.success - parse.error webhook_output_format: anyOf: - type: string - type: 'null' title: Webhook Output Format description: 'Response format sent to the webhook: ''string'' (default) or ''json''' examples: - json type: object title: WebhookConfiguration description: Configuration for a single outbound webhook endpoint. BatchJobCancelResponse: properties: job_id: type: string title: Job Id description: ID of the cancelled job status: $ref: '#/components/schemas/BatchJobStatus' description: New status (should be 'cancelled') processed_items: type: integer title: Processed Items description: Number of items processed before cancellation message: type: string title: Message description: Confirmation message type: object required: - job_id - status - processed_items - message title: BatchJobCancelResponse description: Response after cancelling a batch job. LlamaParsePageRanges: properties: max_pages: anyOf: - type: integer minimum: 1.0 - type: 'null' title: Max Pages description: Maximum number of pages to process. Pages are processed in order starting from page 1. If both max_pages and target_pages are set, target_pages takes precedence target_pages: anyOf: - type: string - type: 'null' title: Target Pages description: 'Comma-separated list of specific pages to process using 1-based indexing. Supports individual pages and ranges. Examples: ''1,3,5'' (pages 1, 3, 5), ''1-5'' (pages 1 through 5 inclusive), ''1,3,5-8,10'' (pages 1, 3, 5-8, and 10). Pages are sorted and deduplicated automatically. Duplicate pages cause an error' additionalProperties: false type: object title: LlamaParsePageRanges description: Page selection options for processing specific pages or limiting page count. BatchJobResponse: properties: status: $ref: '#/components/schemas/BatchJobStatus' description: Current job status effective_at: type: string format: date-time title: Effective At job_record_id: anyOf: - type: string - type: 'null' title: Job Record Id description: The job record ID associated with this status, if any. error_message: anyOf: - type: string - type: 'null' title: Error Message description: Error message for the latest job attempt, if any. id: type: string title: Id description: Unique identifier for the batch job examples: - bjb-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee created_at: anyOf: - type: string format: date-time - type: 'null' title: Created At description: Creation datetime updated_at: anyOf: - type: string format: date-time - type: 'null' title: Updated At description: Update datetime project_id: type: string title: Project Id description: Project this job belongs to examples: - proj-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee directory_id: anyOf: - type: string - type: 'null' title: Directory Id description: Directory being processed examples: - dir-aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee job_type: $ref: '#/components/schemas/BatchJobType' description: Type of processing operation (parse or classify) total_items: type: integer title: Total Items description: Total number of items in the job processed_items: type: integer title: Processed Items description: Number of items processed so far default: 0 failed_items: type: integer title: Failed Items description: Number of items that failed processing default: 0 skipped_items: type: integer title: Skipped Items description: Number of items skipped (already processed or size limit) default: 0 workflow_id: anyOf: - type: string - type: 'null' title: Workflow Id description: Async job tracking ID started_at: anyOf: - type: string format: date-time - type: 'null' title: Started At description: Timestamp when job processing started completed_at: anyOf: - type: string format: date-time - type: 'null' title: Completed At description: Timestamp when job completed type: object required: - status - id - project_id - job_type - total_items title: BatchJobResponse description: Response schema for a batch processing job. SplitStrategy: properties: allow_uncategorized: type: string enum: - include - forbid - omit title: Allow Uncategorized description: 'Controls handling of pages that don''t match any category. ''include'': pages can be grouped as ''uncategorized'' and included in results. ''forbid'': all pages must be assigned to a defined category. ''omit'': pages can be classified as ''uncategorized'' but are excluded from results.' default: include type: object title: SplitStrategy description: Configuration for how to split the document. SpreadsheetJob: properties: id: type: string title: Id description: The ID of the job user_id: type: string title: User Id description: The ID of the user project_id: type: string format: uuid title: Project Id description: The ID of the project configuration: $ref: '#/components/schemas/SpreadsheetParsingConfig' description: Configuration applied to the parsing job (inline or resolved from a saved preset). config: anyOf: - $ref: '#/components/schemas/SpreadsheetParsingConfig' - type: 'null' description: 'Deprecated: use `configuration` instead.' deprecated: true status: type: string enum: - PENDING - SUCCESS - ERROR - PARTIAL_SUCCESS - CANCELLED title: Status description: The status of the parsing job parameters: $ref: '#/components/schemas/SpreadsheetJobParameters' description: Job-time parameters such as webhook configurations. configuration_id: anyOf: - type: string - type: 'null' title: Configuration Id description: The saved product configuration ID used at create time, if any. metadata_state_transitions: anyOf: - additionalProperties: true type: object - type: 'null' title: Metadata State Transitions description: Per-status entry timestamps. Returned only when requested via `?expand=metadata_state_transitions`. created_at: type: string title: Created At description: When the job was created updated_at: type: string title: Updated At description: When the job was last updated success: anyOf: - type: boolean - type: 'null' title: Success description: Whether the job completed successfully regions: items: $ref: '#/components/schemas/ExtractedRegionSummary' type: array title: Regions description: All extracted regions (populated when job is complete) worksheet_metadata: items: $ref: '#/components/schemas/WorksheetMetadata' type: array title: Worksheet Metadata description: Metadata for each processed worksheet (populated when job is complete) errors: items: type: string type: array title: Errors description: Any errors encountered file_id: anyOf: - type: string format: uuid - type: 'null' title: File Id description: The ID of the input file file: anyOf: - $ref: '#/components/schemas/File' - type: 'null' description: '[DEPRECATED] The file that was parsed. Use file_id instead.' deprecated: true type: object required: - id - user_id - project_id - configuration - status - created_at - updated_at - file_id title: SpreadsheetJob description: A spreadsheet parsing job. FileClassification: properties: id: type: string format: uuid title: Id description: Unique identifier created_at: anyOf: - type: string format: date-time - type: 'null' title: Created At description: Creation datetime updated_at: anyOf: - type: string format: date-time - type: 'null' title: Updated At description: Update datetime classify_job_id: type: string format: uuid title: Classify Job Id description: The ID of the classify job file_id: anyOf: - type: string format: uuid - type: 'null' title: File Id description: The ID of the classified file result: anyOf: - $ref: '#/components/schemas/ClassificationResult' - type: 'null' description: The classification result type: object required: - id - classify_job_id title: FileClassification description: A file classification. SpreadsheetJobCreate: properties: configuration_id: anyOf: - type: string - type: 'null' title: Configuration Id description: Saved configuration ID examples: - cfg-11111111-2222-3333-4444-555555555555 configuration: anyOf: - $ref: '#/components/schemas/SpreadsheetParsingConfig' - type: 'null' description: Inline configuration webhook_configurations: anyOf: - items: $ref: '#/components/schemas/WebhookConfiguration' type: array - type: 'null' title: Webhook Configurations description: Outbound webhook endpoints to notify on job status changes config: anyOf: - $ref: '#/components/schemas/SpreadsheetParsingConfig' - type: 'null' description: 'Deprecated: use `configuration` instead.' deprecated: true file_id: type: string format: uuid title: File Id description: The ID of the file to parse type: object required: - file_id title: SpreadsheetJobCreate description: 'Request to create a spreadsheet parsing job. Provide at most one of `configuration` (inline) or `configuration_id` (saved preset). If neither is provided, a default inline configuration is used.' LlamaParseInputOptions: properties: html: $ref: '#/components/schemas/LlamaParseHtmlOptions' description: HTML/web page parsing options (applies to .html, .htm files) pdf: $ref: '#/components/schemas/LlamaParsePdfOptions' description: PDF-specific parsing options (applies to .pdf files) spreadsheet: $ref: '#/components/schemas/LlamaParseSpreadsheetOptions' description: Spreadsheet parsing options (applies to .xlsx, .xls, .csv, .ods files) presentation: $ref: '#/components/schemas/LlamaParsePresentationOptions' description: Presentation parsing options (applies to .pptx, .ppt, .odp, .key files) additionalProperties: false type: object title: LlamaParseInputOptions description: 'Input format-specific parsing options. These options only apply when parsing documents of the corresponding format. LlamaParse automatically detects the input format based on file extension and content.' ExtractedRegionSummary: properties: region_id: type: string title: Region Id description: Unique identifier for this region within the file sheet_name: type: string title: Sheet Name description: Worksheet name where region was found location: type: string title: Location description: Location of the region in the spreadsheet region_type: type: string title: Region Type description: Type of the extracted region title: anyOf: - type: string - type: 'null' title: Title description: Generated title for the region description: anyOf: - type: string - type: 'null' title: Description description: Generated description for the region type: object required: - sheet_name - location - region_type title: ExtractedRegionSummary description: A summary of a single extracted region from a spreadsheet UsageMetricQueryResponse: properties: items: items: $ref: '#/components/schemas/UsageMetric' type: array title: Items description: The list of items. next_page_token: anyOf: - type: string - type: 'null' title: Next Page Token description: A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. total_size: anyOf: - type: integer - type: 'null' title: Total Size description: The total number of items available. This is only populated when specifically requested. The value may be an estimate and can be used for display purposes only. type: object required: - items title: UsageMetricQueryResponse description: Paginated response containing usage metrics. BatchItemDetail: properties: status: $ref: '#/components/schemas/BatchFileStatus' description: Processing status of this item effective_at: type: string format: date-time title: Effective At job_record_id: anyOf: - type: string - type: 'null' title: Job Record Id description: The job record ID associated with this status, if any. error_message: anyOf: - type: string - type: 'null' title: Error Message description: Error message for the latest job attempt, if any. item_id: type: string title: Item Id description: ID of the item item_name: type: string title: Item Name description: Name of the item job_id: anyOf: - type: string - type: 'null' title: Job Id description: Job ID for the underlying processing job (links to parse/extract job results) skip_reason: anyOf: - type: string - type: 'null' title: Skip Reason description: Reason item was skipped (e.g., 'already_processed', 'size_limit_exceeded') started_at: anyOf: - type: string format: date-time - type: 'null' title: Started At description: When processing started for this item completed_at: anyOf: - type: string format: date-time - type: 'null' title: Completed At description: When processing completed for this item type: object required: - status - item_id - item_name title: BatchItemDetail description: Detailed information about an item in a batch job. LlamaParseJobFailureConditions: properties: allowed_page_failure_ratio: anyOf: - type: number maximum: 1.0 exclusiveMinimum: 0.0 - type: 'null' title: Allowed Page Failure Ratio description: 'Maximum ratio of pages allowed to fail before the job fails (0-1). Example: 0.1 means job fails if more than 10% of pages fail. Default is 0.05 (5%)' fail_on_image_extraction_error: anyOf: - type: boolean - type: 'null' title: Fail On Image Extraction Error description: Fail the entire job if any embedded image cannot be extracted. By default, image extraction errors are logged but don't fail the job fail_on_image_ocr_error: anyOf: - type: boolean - type: 'null' title: Fail On Image Ocr Error description: Fail the entire job if OCR fails on any image. By default, OCR errors result in empty text for that image fail_on_markdown_reconstruction_error: anyOf: - type: boolean - type: 'null' title: Fail On Markdown Reconstruction Error description: Fail the entire job if markdown cannot be reconstructed for any page. By default, failed pages use fallback text extraction fail_on_buggy_font: anyOf: - type: boolean - type: 'null' title: Fail On Buggy Font description: Fail the job if a problematic font is detected that may cause incorrect text extraction. Buggy fonts can produce garbled or missing characters additionalProperties: false type: object title: LlamaParseJobFailureConditions description: 'Conditions that determine when a parsing job should fail vs complete with partial results. By default, jobs complete successfully even if some pages fail to parse. Use these settings to enforce stricter quality requirements.' LlamaParseOcrParameters: properties: languages: anyOf: - items: $ref: '#/components/schemas/ParserLanguages' type: array - type: 'null' title: Languages description: 'Languages to use for OCR text recognition. Specify multiple languages if document contains mixed-language content. Order matters - put primary language first. Example: [''en'', ''es''] for English with Spanish' additionalProperties: false type: object title: LlamaParseOcrParameters description: OCR (Optical Character Recognition) configuration parameters. AutoModeParsingConf: properties: tier: anyOf: - type: string enum: - fast - cost_effective - agentic - agentic_plus - type: 'null' title: Tier description: Override the parsing tier for matched pages. Must be paired with version version: anyOf: - type: string enum: - latest - '2026-06-05' - '2026-06-04' - '2025-12-11' x-enum-order-preserved: true - type: string - type: 'null' title: Version description: 'Version for the override tier. Required when `tier` is set. Use `latest`, or pin one of that tier''s dated versions. Current `latest` by tier: - `fast`: `2025-12-11` - `cost_effective`: `2026-06-05` - `agentic`: `2026-06-04` - `agentic_plus`: `2026-06-04` Full list: `GET /api/v2/parse/versions`.' custom_prompt: anyOf: - type: string - type: 'null' title: Custom Prompt description: Custom AI instructions for matched pages. Overrides the base custom_prompt ignore: anyOf: - $ref: '#/components/schemas/AutoModeIgnoreOptions' - type: 'null' description: Options for ignoring specific text types aggressive_table_extraction: anyOf: - type: boolean - type: 'null' title: Aggressive Table Extraction description: Whether to use aggressive table extraction outlined_table_extraction: anyOf: - type: boolean - type: 'null' title: Outlined Table Extraction description: Whether to use outlined table extraction adaptive_long_table: anyOf: - type: boolean - type: 'null' title: Adaptive Long Table description: Whether to use adaptive long table handling extract_layout: anyOf: - type: boolean - type: 'null' title: Extract Layout description: Whether to extract layout information specialized_chart_parsing: anyOf: - type: string enum: - agentic_plus - agentic - efficient - type: 'null' title: Specialized Chart Parsing description: Enable specialized chart parsing with the specified mode high_res_ocr: anyOf: - type: boolean - type: 'null' title: High Res Ocr description: Whether to use high resolution OCR language: anyOf: - type: string - type: 'null' title: Language description: Primary language of the document crop_box: anyOf: - $ref: '#/components/schemas/AutoModeCropBox' - type: 'null' description: Document crop box boundaries spatial_text: anyOf: - $ref: '#/components/schemas/AutoModeSpatialTextOptions' - type: 'null' description: Spatial text output options presentation: anyOf: - $ref: '#/components/schemas/AutoModePresentationOptions' - type: 'null' description: Presentation-specific parsing options additionalProperties: false type: object title: AutoModeParsingConf description: 'Parsing configuration applied when auto mode triggers match. These settings override the base configuration for pages where trigger conditions are satisfied. Only specify fields you want to override - unset fields inherit from the base configuration.' PartitionNames: type: string enum: - data_source_id_partition - pipeline_id_partition - eval_dataset_id_partition - file_id_partition - pipeline_file_id_partition - file_parsing_id_partition - extraction_schema_id_partition title: PartitionNames description: Enum for dataset partition names. Body_upload_file_api_v1_beta_files_post: properties: purpose: type: string title: Purpose description: 'The intended purpose of the file. Valid values: ''user_data'', ''parse'', ''extract'', ''split'', ''classify'', ''sheet'', ''agent_app''. This determines the storage and retention policy for the file.' file: type: string format: binary title: File description: The file to upload external_file_id: anyOf: - type: string - type: 'null' title: External File Id description: The ID of the file in the external system type: object required: - purpose - file title: Body_upload_file_api_v1_beta_files_post ClassifyParsingConfiguration: properties: lang: $ref: '#/components/schemas/ParserLanguages' description: The language to parse the files in default: en max_pages: anyOf: - type: integer - type: 'null' title: Max Pages description: The maximum number of pages to parse default: 5 target_pages: anyOf: - items: type: integer type: array minItems: 1 - type: 'null' title: Target Pages description: The pages to target for parsing (0-indexed, so first page is at 0) type: object title: ClassifyParsingConfiguration description: Parsing configuration for a classify job. AutoModeConfigurationEntry: properties: parsing_conf: $ref: '#/components/schemas/AutoModeParsingConf' description: Parsing configuration to apply when trigger conditions are met trigger_mode: anyOf: - type: string - type: 'null' title: Trigger Mode description: 'How to combine multiple trigger conditions: ''and'' (all conditions must match, this is the default) or ''or'' (any single condition can trigger)' page_md_error: anyOf: - type: boolean - type: 'null' title: Page Md Error description: Trigger on pages with markdown extraction errors text_in_page: anyOf: - type: string - type: 'null' title: Text In Page description: Trigger if page text/markdown contains this string table_in_page: anyOf: - type: boolean - type: 'null' title: Table In Page description: Trigger if page contains a table image_in_page: anyOf: - type: boolean - type: 'null' title: Image In Page description: Trigger if page contains non-screenshot images full_page_image_in_page: anyOf: - type: boolean - type: 'null' title: Full Page Image In Page description: Trigger if page contains a full-page image (scanned page detection) full_page_image_in_page_threshold: anyOf: - type: number - type: string - type: 'null' title: Full Page Image In Page Threshold description: Threshold for full page image detection (0.0-1.0, default 0.8) filename_regexp: anyOf: - type: string - type: 'null' title: Filename Regexp description: Regex pattern to match against filename filename_regexp_mode: anyOf: - type: string - type: 'null' title: Filename Regexp Mode description: Regex mode flags (e.g., 'i' for case-insensitive) filename_match_glob: anyOf: - type: string - type: 'null' title: Filename Match Glob description: Single glob pattern to match against filename filename_match_glob_list: anyOf: - items: type: string type: array - type: 'null' title: Filename Match Glob List description: List of glob patterns to match against filename page_longer_than_n_chars: anyOf: - type: integer - type: string - type: 'null' title: Page Longer Than N Chars description: Trigger if page has more than N characters page_shorter_than_n_chars: anyOf: - type: integer - type: string - type: 'null' title: Page Shorter Than N Chars description: Trigger if page has fewer than N characters page_contains_at_least_n_words: anyOf: - type: integer - type: string - type: 'null' title: Page Contains At Least N Words description: Trigger if page has more than N words page_contains_at_most_n_words: anyOf: - type: integer - type: string - type: 'null' title: Page Contains At Most N Words description: Trigger if page has fewer than N words page_contains_at_least_n_lines: anyOf: - type: integer - type: string - type: 'null' title: Page Contains At Least N Lines description: Trigger if page has more than N lines page_contains_at_most_n_lines: anyOf: - type: integer - type: string - type: 'null' title: Page Contains At Most N Lines description: Trigger if page has fewer than N lines page_contains_at_least_n_images: anyOf: - type: integer - type: string - type: 'null' title: Page Contains At Least N Images description: Trigger if page has more than N images page_contains_at_most_n_images: anyOf: - type: integer - type: string - type: 'null' title: Page Contains At Most N Images description: Trigger if page has fewer than N images page_contains_at_least_n_tables: anyOf: - type: integer - type: string - type: 'null' title: Page Contains At Least N Tables description: Trigger if page has more than N tables page_contains_at_most_n_tables: anyOf: - type: integer - type: string - type: 'null' title: Page Contains At Most N Tables description: Trigger if page has fewer than N tables page_contains_at_least_n_links: anyOf: - type: integer - type: string - type: 'null' title: Page Contains At Least N Links description: Trigger if page has more than N links page_contains_at_most_n_links: anyOf: - type: integer - type: string - type: 'null' title: Page Contains At Most N Links description: Trigger if page has fewer than N links page_contains_at_least_n_charts: anyOf: - type: integer - type: string - type: 'null' title: Page Contains At Least N Charts description: Trigger if page has more than N charts page_contains_at_most_n_charts: anyOf: - type: integer - type: string - type: 'null' title: Page Contains At Most N Charts description: Trigger if page has fewer than N charts page_contains_at_least_n_layout_elements: anyOf: - type: integer - type: string - type: 'null' title: Page Contains At Least N Layout Elements description: Trigger if page has more than N layout elements page_contains_at_most_n_layout_elements: anyOf: - type: integer - type: string - type: 'null' title: Page Contains At Most N Layout Elements description: Trigger if page has fewer than N layout elements page_contains_at_least_n_percent_numbers: anyOf: - type: integer - type: string - type: 'null' title: Page Contains At Least N Percent Numbers description: Trigger if page has more than N% numeric words page_contains_at_most_n_percent_numbers: anyOf: - type: integer - type: string - type: 'null' title: Page Contains At Most N Percent Numbers description: Trigger if page has fewer than N% numeric words page_contains_at_least_n_numbers: anyOf: - type: integer - type: string - type: 'null' title: Page Contains At Least N Numbers description: Trigger if page has more than N numeric words page_contains_at_most_n_numbers: anyOf: - type: integer - type: string - type: 'null' title: Page Contains At Most N Numbers description: Trigger if page has fewer than N numeric words regexp_in_page: anyOf: - type: string - type: 'null' title: Regexp In Page description: Regex pattern to match in page content regexp_in_page_mode: anyOf: - type: string - type: 'null' title: Regexp In Page Mode description: Regex mode flags for regexp_in_page layout_element_in_page: anyOf: - type: string - type: 'null' title: Layout Element In Page description: Trigger if page contains this layout element type layout_element_in_page_confidence_threshold: anyOf: - type: number - type: string - type: 'null' title: Layout Element In Page Confidence Threshold description: Confidence threshold for layout element detection additionalProperties: false type: object required: - parsing_conf title: AutoModeConfigurationEntry description: 'A single auto mode rule with trigger conditions and parsing configuration. Auto mode allows conditional parsing where different configurations are applied based on page content, structure, or filename. When triggers match, the parsing_conf overrides default settings for that page.' examples: - parsing_conf: tier: agentic version: latest table_in_page: true - image_in_page: true parsing_conf: tier: agentic version: latest - filename_match_glob: '*.txt' parsing_conf: tier: fast version: latest ConfigurationCreateRequest: properties: name: type: string maxLength: 255 minLength: 1 title: Name description: Human-readable name for this configuration. parameters: oneOf: - $ref: '#/components/schemas/SplitV1Parameters' - $ref: '#/components/schemas/ExtractV2Parameters' - $ref: '#/components/schemas/ClassifyV2Parameters' - $ref: '#/components/schemas/ParseV2Parameters' - $ref: '#/components/schemas/SpreadsheetV1Parameters' - $ref: '#/components/schemas/UntypedParameters' title: Parameters description: Product-specific configuration parameters. discriminator: propertyName: product_type mapping: classify_v2: '#/components/schemas/ClassifyV2Parameters' extract_v2: '#/components/schemas/ExtractV2Parameters' parse_v2: '#/components/schemas/ParseV2Parameters' split_v1: '#/components/schemas/SplitV1Parameters' spreadsheet_v1: '#/components/schemas/SpreadsheetV1Parameters' unknown: '#/components/schemas/UntypedParameters' type: object required: - name - parameters title: ConfigurationCreateRequest description: Request body for creating a product configuration. SpreadsheetJobParameters: properties: webhook_configurations: anyOf: - items: $ref: '#/components/schemas/WebhookConfiguration' type: array - type: 'null' title: Webhook Configurations description: Webhook configurations for job status notifications. type: object title: SpreadsheetJobParameters description: Job-time parameters returned on a spreadsheet job response. ProcessingResult: properties: result_id: type: string title: Result Id description: Unique identifier for this result item_id: type: string title: Item Id description: Source item that was processed job_type: $ref: '#/components/schemas/BatchJobType' description: Type of processing performed job_config: anyOf: - $ref: '#/components/schemas/BatchParseJobRecordCreate' - $ref: '#/components/schemas/ClassifyJob' title: Job Config description: Job configuration used for processing parameters_hash: type: string title: Parameters Hash description: Content hash of the job configuration for dedup output_s3_path: type: string title: Output S3 Path description: Location of the processing output output_metadata: anyOf: - $ref: '#/components/schemas/ProcessingResultMetadata' - type: 'null' description: Summary statistics about the output processed_at: type: string format: date-time title: Processed At description: When this processing occurred type: object required: - result_id - item_id - job_type - job_config - parameters_hash - output_s3_path - processed_at title: ProcessingResult description: A processing result with lineage information. ClassifyMode: type: string enum: - FAST - MULTIMODAL title: ClassifyMode description: Supported classification execution modes. DirectoryFileQueryResponse: properties: items: items: $ref: '#/components/schemas/DirectoryFileResponse' type: array title: Items description: The list of items. next_page_token: anyOf: - type: string - type: 'null' title: Next Page Token description: A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. total_size: anyOf: - type: integer - type: 'null' title: Total Size description: The total number of items available. This is only populated when specifically requested. The value may be an estimate and can be used for display purposes only. type: object required: - items title: DirectoryFileQueryResponse description: API query response schema for directory files. DirectoryFileResponse: properties: id: type: string title: Id description: Unique identifier for the directory file. created_at: anyOf: - type: string format: date-time - type: 'null' title: Created At description: Creation datetime updated_at: anyOf: - type: string format: date-time - type: 'null' title: Updated At description: Update datetime project_id: type: string title: Project Id description: Project the directory file belongs to. directory_id: type: string title: Directory Id description: Directory the file belongs to. unique_id: type: string minLength: 1 title: Unique Id description: Unique identifier for the file in the directory display_name: type: string minLength: 1 title: Display Name description: Display name for the file. file_id: anyOf: - type: string - type: 'null' title: File Id description: File ID for the storage location. metadata: $ref: '#/components/schemas/MetadataDict' description: Merged metadata from all sources. Higher-priority sources override lower. deleted_at: anyOf: - type: string format: date-time - type: 'null' title: Deleted At description: Soft delete marker when the file is removed upstream or by user action. download_url: anyOf: - $ref: '#/components/schemas/PresignedUrl' - type: 'null' description: Presigned URL to download the underlying file content. type: object required: - id - project_id - directory_id - unique_id - display_name title: DirectoryFileResponse description: API response schema for a directory file. PaginatedResponse_AggregateGroup_: properties: items: items: $ref: '#/components/schemas/AggregateGroup' type: array title: Items description: The list of items. next_page_token: anyOf: - type: string - type: 'null' title: Next Page Token description: A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. total_size: anyOf: - type: integer - type: 'null' title: Total Size description: The total number of items available. This is only populated when specifically requested. The value may be an estimate and can be used for display purposes only. type: object required: - items title: PaginatedResponse[AggregateGroup] 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 LlamaParseCropBox: properties: bottom: anyOf: - type: number maximum: 1.0 minimum: 0.0 - type: 'null' title: Bottom description: Bottom boundary as ratio (0-1). 0=top edge, 1=bottom edge. Content below this line is excluded left: anyOf: - type: number maximum: 1.0 minimum: 0.0 - type: 'null' title: Left description: Left boundary as ratio (0-1). 0=left edge, 1=right edge. Content left of this line is excluded right: anyOf: - type: number maximum: 1.0 minimum: 0.0 - type: 'null' title: Right description: Right boundary as ratio (0-1). 0=left edge, 1=right edge. Content right of this line is excluded top: anyOf: - type: number maximum: 1.0 minimum: 0.0 - type: 'null' title: Top description: Top boundary as ratio (0-1). 0=top edge, 1=bottom edge. Content above this line is excluded additionalProperties: false type: object title: LlamaParseCropBox description: 'Crop box boundaries for processing only a portion of each page. All values are ratios from 0 to 1, where (0,0) is the top-left corner and (1,1) is the bottom-right corner. For example, to process only the top half of each page, set bottom=0.5 (keeping top=0, left=0, right=1).' SplitSegmentResponse: properties: category: type: string title: Category description: Category name this split belongs to. pages: items: type: integer type: array title: Pages description: 1-indexed page numbers in this split. confidence_category: type: string title: Confidence Category description: 'Categorical confidence level. Valid values are: high, medium, low.' type: object required: - category - pages - confidence_category title: SplitSegmentResponse description: A segment of the split document. DirectoryFileBulkDeleteRequest: properties: directory_file_ids: items: type: string type: array maxItems: 100 minItems: 1 title: Directory File Ids description: List of directory file IDs to delete (max 100). type: object required: - directory_file_ids title: DirectoryFileBulkDeleteRequest description: API request schema for bulk deleting directory files. BatchItemListResponse: properties: items: items: $ref: '#/components/schemas/BatchItemDetail' type: array title: Items description: List of item details next_page_token: anyOf: - type: string - type: 'null' title: Next Page Token description: A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. total_size: anyOf: - type: integer - type: 'null' title: Total Size description: The total number of items available. This is only populated when specifically requested. The value may be an estimate and can be used for display purposes only. type: object title: BatchItemListResponse description: Paginated response containing batch job item details. BatchJobStatus: type: string enum: - pending - running - dispatched - completed - failed - cancelled title: BatchJobStatus description: Status of a batch processing job. LlamaParsePdfOptions: properties: {} additionalProperties: false type: object title: LlamaParsePdfOptions securitySchemes: HTTPBearer: type: http scheme: bearer