> ## Documentation Index > Fetch the complete documentation index at: https://docs.bigdata.com/llms.txt > Use this file to discover all available pages before exploring further. # Get annotated document > Returns a time-limited pre-signed URL to download **private** document content in annotated (structured) JSON format. Use this only for documents you ingested via the Content API (connectors or direct upload). When you GET the URL, the response contains document content, metadata and annotations. The URL expires after 24 hours; request a new one if needed. ## OpenAPI ````yaml /api-rest/openapi/openapi_content_data.json get /contents/v1/documents/{content_id}/annotated openapi: 3.1.0 info: title: Bigdata Content API description: API for managing and accessing private content documents uploaded by users. version: 1.0.0 servers: - url: https://api.bigdata.com/ security: - ApiKeyAuth: [] paths: /contents/v1/documents/{content_id}/annotated: get: tags: - Documents summary: Get annotated document description: >- Returns a time-limited pre-signed URL to download **private** document content in annotated (structured) JSON format. Use this only for documents you ingested via the Content API (connectors or direct upload). When you GET the URL, the response contains document content, metadata and annotations. The URL expires after 24 hours; request a new one if needed. parameters: - name: content_id in: path required: true description: Content ID of the document (32-character uppercase hex string). schema: type: string pattern: ^[A-F0-9]{32}$ example: E0618D0E9D3A960C1731A620EDE56B5C responses: '200': description: >- The endpoint returns an object containing a pre-signed url. Perform a GET request on that URL to retrieve the annotated document in JSON format. The URL is valid for 24 hours; request a new one if needed. content: application/json: schema: type: object properties: url: type: string format: uri description: >- Pre-signed URL that provides temporary access to the annotated document in JSON format. When you access the URL, you receive the complete document with structure: document (metadata), content (title and body blocks), profiling (processor timestamps), and analytics (document-level metrics, events array, entities array). example: >- https://content.bigdata.com/classified-documents/E0618D0E9D3A960C1731A620EDE56B5C.json?Expires=1770304237&Signature=abc123...&Key-Pair-Id=K34UQS1JQ2RLGM document: $ref: '#/components/schemas/PrivateDocument' description: >- **Returned by URL** - Document metadata including source information, timestamps, and details. content: $ref: '#/components/schemas/PrivateDocumentContent' description: >- **Returned by URL** - Document content including title, body blocks, entities, and sentences. profiling: description: '**Returned by URL** - Processor timestamps for collection.' type: object properties: collection: type: object properties: processor_in_timestamp_utc: type: string example: '2025-10-22 22:57:42.170' processor_out_timestamp_utc: type: string example: '2025-10-22 22:57:42.170' analytics: description: >- **Returned by URL** - Document-level analytics, events array, and entities array. type: object properties: document: type: object description: >- Document-level analytics (analytics_version, document_type, document_sentiment, etc.). events: type: array description: >- Detected events with topic, type, relevance, roles, and sentiment. entities: type: array description: >- Detected entities with entity_type, entity_name, relevance, and sentiment. required: - url examples: api_response: summary: API Response description: The endpoint returns a pre-signed URL. value: url: >- https://content.bigdata.com/classified-documents/E0618D0E9D3A960C1731A620EDE56B5C.json?Expires=1770304237&Signature=abc123...&Key-Pair-Id=K34UQS1JQ2RLGM document_from_url: summary: Document (returned by URL) description: >- When you access the URL, you receive the complete document in JSON format: document metadata, content (title and body blocks), profiling, and analytics (document-level metrics, events array, entities array). Same structure as Fetch Document; see that endpoint for the full example including TABLE, LIST_ORDERED, LIST_UNORDERED body types and analytics. value: document: rp_document_id: E0618D0E9D3A960C1731A620EDE56B5C source: rp_source_id: DA0F7F name: User Uploaded Content rank: 1 timestamp: '2026-02-03T08:43:02Z' metadata: file_name: Weekly summary report.eml content_type: message/rfc822 content: title: text: 'Tesla Inc: Q1 2025 Earnings Call' sentences: - start: 0 end: 31 sentiment: '0.00' sentiment_confidence: '1.00' entities: - rp_entity_id: DD3BB1 start: 0 end: 9 body: - type: TEXT text: The first quarter results were announced today. normalized_coordinates: [] sentences: - start: 0 end: 46 sentiment: '0.01' sentiment_confidence: '0.94' entities: - rp_entity_id: DD3BB1 start: 4 end: 17 - type: TABLE rows: - cells: - type: CELL_HEADER content: - text: Quarter - type: CELL_VALUE content: - text: Q1 2025 - type: LIST_UNORDERED entries: - key: • content: - text: Unordered dummy point - type: LIST_ORDERED entries: - key: '1' content: - text: Ordered dummy point profiling: collection: processor_in_timestamp_utc: '2025-10-22 22:57:42.170' processor_out_timestamp_utc: '2025-10-22 22:57:42.170' analytics: document: analytics_version: '2.0' analytics_revision_number: 0 document_type: TRANSCRIPT-RAW document_record_count: 257 title_similarity_key: 0A4AD1E8BF251E1A90E3B2376E471E07 document_sentiment: 0.21 document_sentiment_confidence: 0.65 composite_sentiment_score: 0.04 sentiment_impact_projection: -0.2 stock_tone_sentiment: 0 earnings_tone_sentiment: 0 commentary_sentiment: 1 mergers_acquisitions_sentiment: 0 corporate_actions_sentiment: 0 earnings_release_sentiment: 0 product_key: EDGE realtime: 'Y' events: - event_similarity_key: E7913FBE641945AC0670EEF684B6D8E0 topic: business group: products-services type: business-contract event_relevance: 77 roles: - rp_entity_id: DD3BB1 category: business-contract fact_level: fact document_record_index: 6 match_type: TEMPLATE event_sentiment: 0.49 event_risk: 0.24 sustainability_sentiment: 0.24 credit_sentiment: 0.25 interest_rate_sentiment: 0 event_detection_distance: 0 event_text: 'Tesla: we entered into new contracts' rp_event_detected_entity_id: DD3BB1 event_detected_entity_name: Tesla Inc. entities: - rp_entity_id: 4A6F00 entity_type: COMP entity_name: Alphabet Inc. country_code: US document_record_index: 217 entity_hierarchy_level: 1 entity_detection_type: direct entity_detection_distance: 0 entity_relevance: 26 entity_sentiment: 0.25 entity_sentiment_confidence: 0.05 entity_text_sentiment: 0.25 entity_text_sent_confidence: 0.05 analyst_ratings_sentiment: 0 multi_stock_sentiment: 0 '401': description: Unauthorized - Invalid or missing API key. '403': description: You do not have permission to access this document. '404': description: No document found with this content_id. components: schemas: PrivateDocument: type: object description: Document metadata returned when accessing the annotated document URL. properties: rp_document_id: type: string description: Internal document identifier example: E0618D0E9D3A960C1731A620EDE56B5C source: $ref: '#/components/schemas/PrivateDocumentSource' timestamp: type: string format: date-time description: Document timestamp in ISO format example: '2026-02-03T08:43:02Z' metadata: $ref: '#/components/schemas/PrivateDocumentMetadata' required: - rp_document_id - source - timestamp - metadata PrivateDocumentContent: type: object description: >- Structured content extracted from the document including title and body blocks. properties: title: $ref: '#/components/schemas/ContentTitleBlock' body: type: array description: Array of content blocks extracted from the document items: $ref: '#/components/schemas/ContentBlock' required: - title - body PrivateDocumentSource: type: object description: Information about the document source. properties: rp_source_id: type: string description: Identifier of the source system example: DA0F7F name: type: string description: Source display name example: User Uploaded Content rank: type: integer description: Ranking classification of the source example: 1 required: - rp_source_id - name - rank PrivateDocumentMetadata: type: object description: Additional document metadata. properties: file_name: type: string description: Original file name of the uploaded document example: Weekly summary report.eml content_type: type: string description: MIME type of the document example: message/rfc822 user_id: type: string description: ID of the user who uploaded the document example: user_id_001 org_id: type: string description: ID of the organization example: org_id_001 ContentTitleBlock: type: object description: Title content block representing the document title. properties: text: type: string description: Extracted document title example: Weekly summary report sentences: type: array description: Sentence segmentation with sentiment analysis items: $ref: '#/components/schemas/Sentence' entities: type: array description: Entities detected in the title text items: $ref: '#/components/schemas/TextEntity' required: - text ContentBlock: type: object description: A content block (TEXT, TABLE, LIST, etc.) properties: type: type: string description: Type of content block enum: - TEXT - TABLE - LIST_ORDERED - LIST_UNORDERED - HEADING - FOOTER example: TEXT text: type: string description: Text content (for TEXT blocks) example: The Federal Reserve will meet this week to discuss interest rates. normalized_coordinates: type: array description: Normalized coordinates for the block position items: type: number sentences: type: array description: Sentence segmentation with sentiment items: $ref: '#/components/schemas/Sentence' entities: type: array description: Entities detected in the text items: $ref: '#/components/schemas/TextEntity' rows: type: array description: Table rows (for TABLE blocks) items: type: object entries: type: array description: List entries (for LIST blocks) items: type: object required: - type Sentence: type: object description: Sentence segmentation information with sentiment analysis. properties: start: type: integer description: Start character index of the sentence example: 0 end: type: integer description: End character index of the sentence example: 67 sentiment: type: string description: Sentiment score from -1.00 (negative) to 1.00 (positive) example: '0.01' sentiment_confidence: type: string description: Confidence score for sentiment analysis (0.00 to 1.00) example: '0.94' required: - start - end TextEntity: type: object description: An entity detected within the text. properties: rp_entity_id: type: string description: Bigdata.com unique entity identifier example: 4A1B9C name: type: string description: Display name of the entity example: Federal Reserve type: type: string description: Entity type classification enum: - COMPANY - PERSON - PLACE - PRODUCT - ORGANIZATION - ETF example: ORGANIZATION start: type: integer description: Start character index of the entity example: 4 end: type: integer description: End character index of the entity example: 19 required: - rp_entity_id - start - end securitySchemes: ApiKeyAuth: type: apiKey in: header name: X-API-KEY description: >- Your API key. Include it in every request as the X-API-KEY header. Create and manage keys in the Developer Platform. ````