/* --- title: "Batch Cite" openapi: "/api-reference/openapi.json POST /batch/cite" playground: "simple" description: "Process multiple PDF documents with structured data extraction using JSON schema" --- ## Overview The Batch Cite endpoint processes multiple PDF files simultaneously, extracting structured data according to a provided JSON schema. This endpoint is designed for high-throughput document processing with citations and structured output. This endpoint processes files in batches and returns a batch job ID for tracking progress. Use the batch status endpoint to monitor processing and retrieve results. ## Response Unique identifier for the batch processing job Initial batch job status (typically "QUEUED") Total number of files submitted for processing Status message about the batch job creation ## Request Examples ```bash cURL curl -X POST "https://prod.visionapi.unsiloed.ai/batch/cite" \ -H "accept: application/json" \ -H "api-key: your-api-key" \ -H "Content-Type: multipart/form-data" \ -F "pdf_files=@document1.pdf" \ -F "pdf_files=@document2.pdf" \ -F "pdf_files=@document3.pdf" \ -F 'schema_data={"type":"object","properties":{"company_name":{"type":"string","description":"Name of the company"},"board_members":{"type":"array","items":{"type":"string"},"description":"List of board members"}},"required":["company_name"],"additionalProperties":false}' \ -F "batch_size=10" ``` ```python Python import requests import json url = "https://prod.visionapi.unsiloed.ai/batch/cite" headers = { "accept": "application/json", "api-key": "your-api-key" } # Define the extraction schema schema = { "type": "object", "properties": { "company_name": { "type": "string", "description": "Name of the company" }, "board_members": { "type": "array", "items": {"type": "string"}, "description": "List of board members" }, "revenue": { "type": "number", "description": "Annual revenue" } }, "required": ["company_name"], "additionalProperties": False } # Prepare files files = [ ("pdf_files", ("document1.pdf", open("document1.pdf", "rb"), "application/pdf")), ("pdf_files", ("document2.pdf", open("document2.pdf", "rb"), "application/pdf")), ("pdf_files", ("document3.pdf", open("document3.pdf", "rb"), "application/pdf")) ] # Prepare form data data = { "schema_data": json.dumps(schema), "batch_size": 10 } response = requests.post(url, headers=headers, files=files, data=data) if response.status_code == 200: result = response.json() print(f"Batch job created: {result['batch_id']}") print(f"Status: {result['status']}") print(f"Total files: {result['total_files']}") else: print("Error:", response.status_code, response.text) # Close files for _, (_, file_obj, _) in files: file_obj.close() ``` ```javascript JavaScript const formData = new FormData(); // Add PDF files const fileInputs = document.querySelectorAll('input[type="file"]'); fileInputs.forEach((input) => { if (input.files[0]) { formData.append('pdf_files', input.files[0]); } }); // Define extraction schema const schema = { type: "object", properties: { company_name: { type: "string", description: "Name of the company" }, board_members: { type: "array", items: { type: "string" }, description: "List of board members" }, revenue: { type: "number", description: "Annual revenue" } }, required: ["company_name"], additionalProperties: false }; // Add schema and batch size formData.append('schema_data', JSON.stringify(schema)); formData.append('batch_size', '10'); const response = await fetch('https://prod.visionapi.unsiloed.ai/batch/cite', { method: 'POST', headers: { 'accept': 'application/json', 'api-key': 'your-api-key' }, body: formData }); if (response.ok) { const result = await response.json(); console.log(`Batch job created: ${result.batch_id}`); console.log(`Status: ${result.status}`); console.log(`Total files: ${result.total_files}`); } else { console.error('Batch processing failed:', response.status, await response.text()); } ``` ## Response Examples ```json Success Response { "batch_id": "batch_f7e8d9c2-4a5b-6c7d-8e9f-0a1b2c3d4e5f", "status": "QUEUED", "total_files": 3, "message": "Batch job created successfully. Processing will begin shortly." } ``` ```json Error Response - Invalid Files { "detail": [ { "type": "value_error", "loc": ["body", "pdf_files", 0], "msg": "Value error, Expected UploadFile, received: ", "input": "string", "ctx": { "error": {} } } ] } ``` ```json Error Response - Invalid Schema { "detail": "Invalid schema data: Not a valid JSON" } ``` ```json Error Response - Invalid Batch Size { "detail": "Batch size must be a positive integer" } ``` ## Schema Format The `schema_data` parameter must be a valid JSON schema that defines the structure of data to extract from your PDFs. ### Basic Schema Example ```json { "type": "object", "properties": { "company_name": { "type": "string", "description": "Name of the company from the document" }, "date": { "type": "string", "description": "Document date in YYYY-MM-DD format" }, "amount": { "type": "number", "description": "Total amount or value mentioned" } }, "required": ["company_name"], "additionalProperties": false } ``` ### Complex Schema Example ```json { "type": "object", "properties": { "board_of_directors": { "type": "array", "description": "List of board members", "items": { "type": "object", "properties": { "name": { "type": "string", "description": "Full name of board member" }, "title": { "type": "string", "description": "Title or position" } }, "required": ["name"], "additionalProperties": false } }, "financial_data": { "type": "object", "properties": { "revenue": { "type": "number", "description": "Annual revenue" }, "profit": { "type": "number", "description": "Net profit" } }, "additionalProperties": false } }, "required": ["board_of_directors"], "additionalProperties": false } ``` ## Monitoring Batch Progress After creating a batch job, use the batch status endpoint to monitor progress: ```python import requests import time def monitor_batch_progress(batch_id, api_key): """Monitor batch processing progress""" headers = {"api-key": api_key} status_url = f"https://prod.visionapi.unsiloed.ai/batch/status/{batch_id}" while True: response = requests.get(status_url, headers=headers) if response.status_code == 200: status_data = response.json() print(f"Batch Status: {status_data['status']}") if 'statistics' in status_data: stats = status_data['statistics'] print(f"Progress: {stats['completed_jobs']}/{stats['total_jobs']} completed") print(f"Failed: {stats['failed_jobs']}") print(f"Processing: {stats['processing_jobs']}") if status_data['status'] in ['COMPLETED', 'COMPLETED_WITH_FAILURES']: print("Batch processing finished!") return status_data elif status_data['status'] == 'FAILED': print("Batch processing failed!") return status_data else: print(f"Error checking status: {response.status_code}") time.sleep(10) # Check every 10 seconds # Usage batch_id = "your-batch-id" final_status = monitor_batch_progress(batch_id, "your-api-key") ``` ## Error Handling ### Common Error Scenarios 1. **Invalid File Format**: Only PDF files are supported 2. **Invalid Schema**: Schema must be valid JSON with proper structure 3. **Invalid Batch Size**: Must be a positive integer 4. **Authentication Error**: Invalid or missing API key 5. **File Size Limits**: Individual files may have size restrictions */ "use strict"; const {Fragment: _Fragment, jsx: _jsx} = arguments[0]; const {useMDXComponents: _provideComponents} = arguments[0]; function _createMdxContent(props) { return _jsx(_Fragment, {}); } function MDXContent(props = {}) { const {wrapper: MDXLayout} = { ..._provideComponents(), ...props.components }; return MDXLayout ? _jsx(MDXLayout, { ...props, children: _jsx(_createMdxContent, { ...props }) }) : _createMdxContent(props); } return { default: MDXContent };

Core Endpoints

Job Management