> ## Documentation Index > Fetch the complete documentation index at: https://docs.docintell.com/llms.txt > Use this file to discover all available pages before exploring further. # Get job extraction results > Retrieve full extraction results for a completed job. Returns classification and extraction data with field-level metadata including confidence scores, page numbers, and location hints. Args: job_id: UUID of the extraction job to retrieve results for. session_and_auth: Database session and auth context (injected). Returns: JobResultResponse: Classification and extraction results with metadata. Raises: HTTPException 404: Job not found or not accessible by tenant. HTTPException 400: Job not completed (status must be 'completed'). Notes: - Confidence scores are self-reported by LLM and directionally useful but not calibrated (90% confidence != 90% accuracy) - Field metadata includes page numbers and location hints for provenance - For unknown document types, extraction may be null ## OpenAPI ````yaml openapi.json get /v1/jobs/{job_id}/results openapi: 3.1.0 info: title: DocIntell API description: >- # DocIntell API **Turn Documents into Data. Keep the Source Safe.** Financial document intelligence platform that turns PDFs into queryable data while keeping source files secure and compliant. ## Features - **Document Ingestion**: Upload PDFs with SEC 17a-4 compliant immutable storage - **Schema Projection**: Query extracted data with custom schemas (not data dumps!) - **Multi-Schema Support**: Same document, multiple query patterns - **Webhook Delivery**: Async notifications on job completion - **Row-Level Security**: Multi-tenant isolation built-in ## Authentication All API endpoints (except `/health`, `/`, `/docs`, and `/redoc`) require API key authentication. Include your API key in the `Authorization` header: ``` Authorization: Bearer dk_live_ ``` Test keys start with `dk_test_`, production keys with `dk_live_`. ## Rate Limiting Per-tenant rate limits: - **Document ingestion**: 100 documents/hour - **Projection queries**: 1,000 requests/hour - **Schema operations**: 10 creates/hour Rate limit info is returned in response headers: - `X-RateLimit-Limit`: Maximum requests allowed - `X-RateLimit-Remaining`: Remaining requests in window - `X-RateLimit-Reset`: Unix timestamp when limit resets ## Error Handling All errors follow RFC 7807 Problem Details format: ```json { "error": "error_code", "message": "Human-readable description", "details": {} } ``` Common error codes: - `unauthorized` (401): Missing or invalid API key - `rate_limit_exceeded` (429): Too many requests - `invalid_file_type` (400): Only PDFs supported - `file_too_large` (413): File exceeds size limit (default 100MB, configurable via MAX_UPLOAD_SIZE_MB) - `job_not_found` (404): Job ID doesn't exist or doesn't belong to tenant ## Getting Started 1. Obtain API key from dashboard 2. Upload PDF: `POST /v1/documents` 3. Poll status: `GET /v1/documents/{document_id}/status` 4. Query results: `POST /v1/documents/{document_id}/project` Full documentation: [https://docs.docintel.com](https://docs.docintel.com) contact: name: DocIntell Support url: https://docintel.com/support email: support@docintel.com license: name: Proprietary url: https://docintel.com/terms version: 0.1.0 servers: - url: http://localhost:8000 description: Local development - url: https://api.docintell.com description: Production API - url: https://api-staging.docintell.com description: Staging environment security: - bearerAuth: [] tags: - name: health description: Health check operations. Verify service and dependency connectivity. x-mint-tag-group: System - name: api_keys description: API key management operations. Create, list, and revoke API keys. x-mint-tag-group: Management - name: documents description: Document ingestion operations. Upload PDFs for extraction. x-mint-tag-group: Core - name: jobs description: >- Job status and query operations. Check extraction status and query results. x-mint-tag-group: Core - name: document-types description: >- Document type schemas. List and retrieve extraction schema definitions for financial document types. - name: webhooks description: >- Webhook configuration management. Create, update, and manage webhook endpoints for job completion notifications. x-mint-tag-group: Integrations - name: stats description: Analytics and metrics endpoints. Get document, job, and schema statistics. - name: views description: >- View management for consumption layer. Define field subsets for querying extraction data. paths: /v1/jobs/{job_id}/results: get: tags: - jobs summary: Get job extraction results description: >- Retrieve full extraction results for a completed job. Returns classification and extraction data with field-level metadata including confidence scores, page numbers, and location hints. Args: job_id: UUID of the extraction job to retrieve results for. session_and_auth: Database session and auth context (injected). Returns: JobResultResponse: Classification and extraction results with metadata. Raises: HTTPException 404: Job not found or not accessible by tenant. HTTPException 400: Job not completed (status must be 'completed'). Notes: - Confidence scores are self-reported by LLM and directionally useful but not calibrated (90% confidence != 90% accuracy) - Field metadata includes page numbers and location hints for provenance - For unknown document types, extraction may be null operationId: get_job_results_v1_jobs__job_id__results_get parameters: - name: job_id in: path required: true schema: type: string format: uuid description: UUID of the extraction job title: Job Id description: UUID of the extraction job responses: '200': description: Full extraction results with classification and field metadata content: application/json: schema: $ref: '#/components/schemas/JobResultResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' components: schemas: JobResultResponse: properties: job_id: type: string format: uuid title: Job Id description: Extraction job identifier document_id: type: string format: uuid title: Document Id description: Source document identifier status: type: string const: completed title: Status description: Job status classification: anyOf: - $ref: '#/components/schemas/ClassificationResponse' - type: 'null' description: Classification result with reasoning extraction: anyOf: - $ref: '#/components/schemas/ExtractionResultResponse' - type: 'null' description: Extraction result with field metadata type: object required: - job_id - document_id - status title: JobResultResponse description: Full job result with classification and extraction data. examples: - classification: citation: INVOICE citation_page: 1 confidence: 0.95 document_type: invoice reasoning: Document is a vendor invoice with itemized charges. document_id: 6789def0-abcd-4567-ef01-23456789abcd extraction: data: invoice_number: INV-2024-0892 document_type: invoice field_metadata: {} page_count: 2 validation: is_valid: true job_id: 550e8400-e29b-41d4-a716-446655440000 status: completed HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError ClassificationResponse: properties: document_type: type: string title: Document Type description: Classified document type code confidence: type: number maximum: 1 minimum: 0 title: Confidence description: Classification confidence (0-1) reasoning: type: string title: Reasoning description: 1-2 sentence explanation of classification citation: anyOf: - type: string - type: 'null' title: Citation description: Direct quote from document supporting classification citation_page: anyOf: - type: integer minimum: 1 - type: 'null' title: Citation Page description: Page number where citation was found (1-indexed) type: object required: - document_type - confidence - reasoning title: ClassificationResponse description: Classification result with reasoning and evidence. examples: - citation: CAPITAL CALL NOTICE - Fund IV, L.P. citation_page: 1 confidence: 0.95 document_type: capital_call reasoning: Document is a capital call notice from a private equity fund. ExtractionResultResponse: properties: document_type: type: string title: Document Type description: Extracted document type page_count: anyOf: - type: integer - type: 'null' title: Page Count description: Number of pages in document extraction_model: anyOf: - type: string - type: 'null' title: Extraction Model description: LLM model used processing_time_ms: anyOf: - type: integer - type: 'null' title: Processing Time Ms description: Processing time in milliseconds data: additionalProperties: true type: object title: Data description: Extracted fields as key-value pairs field_metadata: additionalProperties: $ref: '#/components/schemas/FieldMetadataResponse' type: object title: Field Metadata description: Per-field metadata validation: additionalProperties: true type: object title: Validation description: Validation results type: object required: - document_type - data title: ExtractionResultResponse description: Extraction result with data and field metadata. examples: - data: invoice_date: '2024-12-01' invoice_number: INV-2024-0892 total_amount: 1234.56 document_type: invoice extraction_model: google-vertex:gemini-2.5-flash field_metadata: invoice_number: confidence: 0.98 location_hint: top right header page_number: 1 raw_text: INV-2024-0892 page_count: 2 processing_time_ms: 3500 validation: hard_violations: [] is_valid: true soft_violations: [] ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError FieldMetadataResponse: properties: confidence: anyOf: - type: number maximum: 1 minimum: 0 - type: 'null' title: Confidence description: Self-reported confidence (0-1, directionally useful) page_number: anyOf: - type: integer minimum: 1 - type: 'null' title: Page Number description: Page where found (1-indexed) location_hint: anyOf: - type: string - type: 'null' title: Location Hint description: Qualitative location description raw_text: anyOf: - type: string - type: 'null' title: Raw Text description: Original text as it appeared extraction_notes: anyOf: - type: string - type: 'null' title: Extraction Notes description: Extraction issues or notes type: object title: FieldMetadataResponse description: Metadata for an extracted field. examples: - confidence: 0.95 location_hint: top right header page_number: 1 raw_text: INV-2024-0892 securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: API Key description: 'API Key authentication. Format: dk_test_ or dk_live_' ````