Parse Document - Unsiloed AI

Overview

The Parse Document endpoint processes PDFs, images (PNG, JPEG, TIFF), and office files (PPT, DOCX, XLSX) documents and breaks them into meaningful sections with detailed analysis including text extraction, image recognition, table parsing, and OCR data. You can provide documents either by direct file upload or by presigned URL. This endpoint supports advanced customization options for fine-tuning the parsing behavior to match your specific use cases.

This endpoint returns a job ID for asynchronous processing. Use the GET PARSE JOB STATUS endpoint to check status and retrieve results when processing is complete.

Request

You must provide either file or url parameter. Both cannot be provided simultaneously.

file

Document file to process. Supported formats: PDF, images (PNG, JPEG, TIFF), and office documents (PPT, PPTX, DOC, DOCX, XLS, XLSX). Required if url is not provided.

url

string

Presigned URL of the document to process. The URL must be publicly accessible or a valid presigned URL from cloud storage (S3, GCS, Azure Blob, etc.). Supported formats: PDF, images (PNG, JPEG, TIFF), and office documents (PPT, PPTX, DOC, DOCX, XLS, XLSX). Required if file is not provided.

use_high_resolution

boolean

Whether to use high-resolution images for cropping and post-processing. (Latency penalty: ~2-3 seconds per page). Default: false

segmentation_method

string

Document segmentation strategy:

"smart_layout_detection" (default): Analyzes pages for layout elements using bounding boxes
"page_by_page": Treats each page as a single segment

ocr_mode

string

OCR processing strategy:

"auto_ocr" (default): Automatically determine when to use OCR
"full_ocr": Process all text elements with OCR

merge_tables

boolean

Whether to merge tables that span across multiple pages into a single unified table structure. When enabled, consecutive table segments with matching headers will be consolidated. Default: false

validate_table_segments

boolean

Whether to use our Vision Language Model (Judge) to validate and correct table segment classifications. When enabled, segments that may have been misclassified (e.g., tables detected as text or pictures) are validated and corrected(add 4-5s Latency per page).

keep_segment_types

string

Filter output to include only specific segment types. Accepts a comma-separated list of segment types or “all” to include everything. Examples: "table", "picture", "table,picture", "table,formula". Default: “all”Available segment types:

table: Tabular data segments
picture: Image and graphic segments
formula: Mathematical equations
text: Regular text content
sectionheader: Section headers
title: Document titles
listitem: List items
caption: Image captions
footnote: Footnotes
pageheader: Page headers
pagefooter: Page footers

output_fields

string

JSON configuration object to control which fields are included in the response. By default, all fields are included. Set fields to false to exclude them and reduce response size. Example: {"html": false, "markdown": true, "ocr": false}. Available fields: html, markdown, ocr, image, llm, content, bbox, confidence, embed.

segment_analysis

string

JSON configuration object to customize how different segment types are processed. Allows you to control HTML/Markdown generation strategies, specify which field should populate the content field for each segment type, and configure the AI model for table processing. Example: {"Table": {"html": "LLM", "markdown": "LLM", "content_source": "HTML", "model_id": "us_table_v2"}}.

Parameter Details

File Input Options

The API supports two methods for providing the document to process:

Direct File Upload (file parameter): Upload the document file directly as multipart/form-data
Presigned URL (url parameter): Provide a publicly accessible URL or presigned URL to the document

Important Notes:

You must provide either file or url, but not both
When using url, the document will be downloaded from the provided URL before processing
Presigned URLs are ideal for documents already stored in cloud storage (S3, GCS, Azure Blob, etc.)
The URL must be publicly accessible or include necessary authentication parameters (e.g., S3 presigned URLs with signatures)
Supported formats are the same for both methods: PDF, images (PNG, JPEG, TIFF), and office documents (PPT, PPTX, DOC, DOCX, XLS, XLSX)

Use Cases for Presigned URLs:

Documents already stored in cloud storage
Avoiding duplicate file uploads
Integration with existing document management systems
Processing large files without upload overhead

Segmentation Method

The segmentation_method parameter controls how the document is analyzed and segmented:

"smart_layout_detection" (default): Analyzes pages for layout elements (e.g., Table, Picture, Formula, etc.) using bounding boxes. Provides fine-grained segmentation and better chunking for complex documents.
"page_by_page": Treats each page as a single segment. Faster processing, ideal for simple documents without complex layouts.

OCR Mode

The ocr_mode parameter controls optical character recognition processing:

"auto_ocr" (default): Intelligently determines when OCR is needed based on the document content. Balances accuracy and performance.
"full_ocr": Applies OCR to all text elements in the document. Use this for scanned documents or when maximum text extraction is required.

Table Merging

The merge_tables parameter enables intelligent merging of tables that span across multiple pages: How It Works:

Analyzes consecutive table segments across pages
Identifies tables with matching column headers
Merges them into a single unified table structure
Preserves table formatting and data integrity

When to Use:

Multi-Page Financial Statements: Consolidate P&L statements or balance sheets spanning multiple pages
Large Data Tables: Merge inventory lists, transaction records, or data sets split across pages
Reports with Continuation Tables: Automatically combine tables marked with “continued on next page”

Example:

{
  "merge_tables": true
}

Benefits:

Simplified Data Processing: Work with complete tables instead of fragments
Better Context: Maintain full table context for analysis and extraction
Reduced Post-Processing: Eliminates need for manual table stitching

Content Type Filtering

The keep_segment_types parameter allows you to filter the output to include only specific segment types, reducing response size and focusing on relevant content: How It Works:

Accepts a comma-separated list of segment types (case-insensitive)
Filters segments after processing is complete
Removes chunks that have no segments after filtering

Available Options:

"all" (default): Include all segment types
"table": Only table segments
"picture": Only image/graphic segments
"table,picture": Tables and pictures only
"table,formula": Tables and formulas only
Custom combinations using any segment type

Supported Segment Types:

table, picture, formula, text, sectionheader, title, listitem, caption, footnote, pageheader, pagefooter

Example Usage:

{
  "keep_segment_types": "table,picture"
}

Use Cases:

Tables Only: Extract only tabular data from financial documents
Pictures Only: Extract charts, graphs, and diagrams for visual analysis
Tables + Pictures: Get structured data and visualizations, skip text content
Custom Combinations: Mix any segment types based on your needs

Benefits:

Reduced Response Size: Filter out unwanted content before receiving results
Faster Processing: Less data to transfer and parse
Focused Extraction: Get only the content types you need
Cost Optimization: Smaller responses reduce bandwidth usage

Output Fields Configuration

The output_fields parameter allows you to control which fields are included in the API response. This is useful for reducing response size, improving performance, and optimizing bandwidth usage when you don’t need all available data. Available Fields:

html (default: true): Include HTML representation of segments
markdown (default: true): Include Markdown representation of segments
ocr (default: true): Include OCR results with bounding boxes and confidence scores
image (default: true): Include cropped segment images (base64 encoded)
llm (default: true): Include LLM-generated content and descriptions
content (default: true): Include text content of segments
bbox (default: true): Include bounding box coordinates
confidence (default: true): Include confidence scores for segments
embed (default: true): Include embed text in chunk responses

Usage: Set fields to false to exclude them from the response. Fields not specified default to true for backward compatibility. Example Configuration:

{
  "html": false,
  "markdown": true,
  "ocr": false,
  "image": false,
  "llm": false,
  "content": true,
  "bbox": true,
  "confidence": false,
  "embed": true
}

Benefits:

Reduced Response Size: Excluding large fields like image and html can significantly reduce payload size
Faster Processing: Less data to serialize and transfer
Cost Optimization: Smaller responses reduce bandwidth costs
Selective Data: Only retrieve the fields you need for your use case

When to Use:

Minimal Response: Set most fields to false when you only need basic content
Text-Only Processing: Exclude image, ocr, and llm when processing text content
Embedding Generation: Include only content and embed when generating embeddings
Full Analysis: Keep all fields enabled (default) for comprehensive document analysis

Segment Analysis Configuration

The segment_analysis parameter allows you to customize how different segment types are processed, including HTML/Markdown generation strategies and which field should populate the content field. Available Segment Types: You can configure processing for any of the following segment types:

Table: Tabular data segments
Picture: Image and graphic segments
Formula: Mathematical equations
Title: Document titles
SectionHeader: Section headers
Text: Regular text content
ListItem: List items
Caption: Image captions
Footnote: Footnotes
PageHeader: Page headers
PageFooter: Page footers
Page: Full page segments

Configuration Options: For each segment type, you can specify:

html: Generation strategy for HTML representation
- "Auto" (default): Automatically determine the best method
- "LLM": Use LLM to generate HTML
markdown: Generation strategy for Markdown representation
- "Auto" (default): Automatically determine the best method
- "LLM": Use LLM to generate Markdown
content_source: Defines which field should populate the content field in the response
- "OCR" (default): Use OCR text for content
- "HTML": Use HTML representation as content
- "Markdown": Use Markdown representation as content
model_id (Table segments only): Specifies which AI model to use for table processing
- "us_table_v1": Standard table processing model
- "us_table_v2": Enhanced table processing model with improved accuracy

Example Configuration:

{
  "Table": {
    "html": "LLM",
    "markdown": "LLM",
    "content_source": "HTML",
    "model_id": "us_table_v2"
  },
  "Picture": {
    "html": "LLM",
    "markdown": "LLM",
    "content_source": "Markdown"
  }
}

How content_source Works: The content_source parameter determines which field’s value will be used to populate the content field in the segment response:

When content_source is set to "HTML", the content field will contain the HTML representation, and the separate html and markdown fields will be empty
When content_source is set to "Markdown", the content field will contain the Markdown representation, and the separate html and markdown fields will be empty
When content_source is set to "OCR" (default), the content field contains OCR text, and html and markdown fields are populated separately
When content_source is set to "LLM", the content field contains LLM-generated content

Use Cases:

HTML as Content: Set content_source: "HTML" for Table segments when you want HTML-formatted table data directly in the content field
Markdown as Content: Set content_source: "Markdown" for Picture segments when you want Markdown-formatted descriptions in the content field
LLM-Enhanced Content: Use "LLM" for both html/markdown generation strategies and set content_source: "LLM" to get AI-enhanced content in the content field

Response

job_id

string

Unique identifier for the parsing job

status

string

Initial job status (typically “Starting”)

file_name

string

Name of the uploaded file

created_at

string

Timestamp when the job was created

message

string

Status message about the job creation

quota_remaining

number

Remaining page quota for the API key

merge_tables

boolean

Whether table merging is enabled for this job

validate_table_segments

boolean

Whether VLM-based table segment validation is enabled for this job

keep_segment_types

string

Segment types filter applied to this job (stored in metadata)

Document Analysis Features

The parsing endpoint provides comprehensive document analysis including:

Text Extraction

Extracts text content with high accuracy, preserving formatting and structure.

Image Recognition

Identifies and analyzes images within documents, providing descriptions and metadata.

Table Parsing

Extracts tabular data with proper structure and formatting.

OCR Processing

Performs optical character recognition on text elements with confidence scores.

Section Detection

Automatically identifies different document sections like headers, body text, and captions.

Bounding Box Information

Provides precise coordinates for all extracted elements.

Advanced Content Processing

LLM-Enhanced Analysis: Uses language models for better content understanding
Multi-Format Output: Generates HTML, Markdown, and plain text versions
Context-Aware Processing: Maintains document context across segments
Intelligent Chunking: Creates semantically meaningful document chunks

curl -X 'POST' \
  'https://prod.visionapi.unsiloed.ai/parse' \
  -H 'accept: application/json' \
  -H 'api-key: your-api-key' \
  -H 'Content-Type: multipart/form-data' \
  -F '[email protected];type=application/pdf' \
  -F 'use_high_resolution=true' \
  -F 'segmentation_method=smart_layout_detection' \
  -F 'ocr_mode=auto_ocr' \
  -F 'merge_tables=true' \
  -F 'validate_table_segments=false' \
  -F 'keep_segment_types=all' \
  -F 'segment_analysis={"Table":{"html":"LLM","markdown":"LLM","extended_context":true,"crop_image":"All","model_id":"us_table_v2"}}'

{
  "job_id": "e77a5c42-4dc1-44d0-a30e-ed191e8a8908",
  "status": "Starting",
  "file_name": "document.pdf",
  "created_at": "2025-07-18T10:42:10.545832520Z",
  "message": "Job created successfully. Use GET /parse/{job_id} to check status and retrieve results.",
  "quota_remaining": 23700,
  "merge_tables": false,
}

Retrieving Results

After the job is created, use the GET /parse/ endpoint to check status and retrieve results:

cURL

curl -X 'GET' \
  'https://prod.visionapi.unsiloed.ai/parse/{job_id}' \
  -H 'accept: application/json' \
  -H 'api-key: your-api-key'

Python

import requests
import time

def get_parse_results(job_id, api_key):
    """Monitor job and retrieve results when complete"""
    
    headers = {"api-key": api_key}
    status_url = f"https://prod.visionapi.unsiloed.ai/parse/{job_id}"
    
    # Poll for completion
    while True:
        response = requests.get(status_url, headers=headers)
        
        if response.status_code == 200:
            status_data = response.json()
            print(f"Job Status: {status_data['status']}")
            
            if status_data['status'] == 'Succeeded':
                return status_data  # Results are included in the same response
                    
            elif status_data['status'] == 'Failed':
                raise Exception(f"Job failed: {status_data.get('message', 'Unknown error')}")
                
        time.sleep(5)  # Check every 5 seconds

# Usage
job_id = "e77a5c42-4dc1-44d0-a30e-ed191e8a8908"
results = get_parse_results(job_id, "your-api-key")

Expected Results Structure

When the job completes successfully, the response contains comprehensive document analysis with enhanced processing:

{
  "job_id": "04a7a6d8-5ef7-465a-b22a-8a98e7104dd9",
  "status": "Succeeded",
  "created_at": "2025-10-22T06:51:16.870302Z",
  "started_at": "2025-10-22T06:51:16.966136Z",
  "finished_at": "2025-10-22T06:57:19.821541Z",
  "total_chunks": 25,
  "chunks": [
    {
      "segments": [
        {
          "segment_type": "Title",
          "content": "Disinvestment of IFCI's entire stake in Assets Care & Reconstruction Enterprise Ltd (ACRE)",
          "image": null,
          "page_number": 1,
          "segment_id": "cc5f8dff-31be-4ccf-885d-4f9062fcee17",
          "confidence": 0.90187776,
          "page_width": 1191.0,
          "page_height": 1684.0,
          "html": "<h1>Disinvestment of IFCI's entire stake in Assets Care & Reconstruction Enterprise Ltd (ACRE)</h1>",
          "markdown": "# Disinvestment of IFCI's entire stake in Assets Care & Reconstruction Enterprise Ltd (ACRE)",
          "bbox": {
            "left": 72.92226,
            "top": 62.030334,
            "width": 230.36308,
            "height": 55.395317
          },
          "ocr": [
            {
              "bbox": {
                "left": 63.753525,
                "top": 5.395447,
                "width": 164.45312,
                "height": 42.757812
              },
              "text": "Disinvestment",
              "confidence": 0.9999992
            }
          ]
        },
        {
          "segment_type": "Text",
          "content": "Background and context information about the disinvestment process...",
          "image": null,
          "page_number": 1,
          "segment_id": "9d60e48b-77ba-4a23-a0ac-95ee13c615ec",
          "confidence": 0.88558982,
          "page_width": 1191.0,
          "page_height": 1684.0,
          "html": "<p>Background and context information about the disinvestment process...</p>",
          "markdown": "Background and context information about the disinvestment process...",
          "bbox": {
            "left": 486.9685,
            "top": 139.61847,
            "width": 241.29932,
            "height": 48.451706
          },
          "ocr": [
            {
              "bbox": {
                "left": 50.9729,
                "top": 3.4557495,
                "width": 46.046875,
                "height": 19.734375
              },
              "text": "Background",
              "confidence": 0.99999654
            }
          ]
        }
      ]
    }
  ]
}

Segment Types

The parsing API identifies and processes different types of document segments with enhanced processing:

Picture

Images and graphics within the document, including logos, charts, and illustrations. Enhanced with LLM-based description generation.

SectionHeader

Document headers and titles that define section boundaries. Processed with semantic understanding.

Text

Regular text content including paragraphs, sentences, and individual text elements. Enhanced with context-aware processing.

Table

Tabular data with structured rows and columns. Enhanced with LLM-based formatting and extended context options. You can configure the table processing model using model_id in the segment_analysis parameter:

us_table_v1: Standard table processing model
us_table_v2: Enhanced table processing model with improved accuracy

Caption

Text captions associated with images or figures. Processed with relationship awareness.

Formula

Mathematical equations and expressions. Enhanced with specialized formula processing.

Title

Document titles and main headings. Processed with enhanced formatting.

Footnote

Document footnotes and references. Processed with context linking.

ListItem

Bulleted and numbered list items. Processed with structure preservation. Each segment includes detailed metadata such as confidence scores, bounding boxes, OCR data, and formatted output in both HTML and Markdown with LLM enhancement.

Configuration Best Practices

For High-Accuracy Processing

Use this configuration when accuracy is critical:

{
  "use_high_resolution": true,
  "segmentation_method": "smart_layout_detection",
  "ocr_mode": "full_ocr",
  "merge_tables": true,
  "validate_table_segments": true,
  "segment_analysis": {
    "Table": {
      "html": "LLM",
      "markdown": "LLM",
      "extended_context": true,
      "crop_image": "All",
      "model_id": "us_table_v2"
    }
  }
}

For Fast Processing

Use this configuration when speed is prioritized:

{
  "use_high_resolution": false,
  "segmentation_method": "page_by_page",
  "ocr_mode": "auto_ocr"
}

For Financial Documents (Tables + Charts)

Extract only tables and charts from financial reports:

{
  "merge_tables": true,
  "keep_segment_types": "table,picture",
  "segmentation_method": "smart_layout_detection",
  "segment_analysis": {
    "Table": {
      "html": "LLM",
      "markdown": "LLM",
      "model_id": "us_table_v2"
    }
  }
}

For Data Extraction Only (Tables)

Extract only tabular data with minimal response size:

{
  "merge_tables": true,
  "keep_segment_types": "table",
  "output_fields": {
    "html": true,
    "markdown": false,
    "ocr": false,
    "image": false,
    "content": true,
    "bbox": false,
    "confidence": false
  }
}

Output Fields Optimization (Optional)

Optimize response size and performance by selectively including only the fields you need: For Minimal Response Size:

{
  "output_fields": {
    "html": false,
    "markdown": false,
    "ocr": false,
    "image": false,
    "llm": false,
    "content": true,
    "bbox": false,
    "confidence": false,
    "embed": true
  }
}

For Text-Only Processing:

{
  "output_fields": {
    "html": false,
    "markdown": true,
    "ocr": false,
    "image": false,
    "llm": false,
    "content": true,
    "bbox": true,
    "confidence": false,
    "embed": true
  }
}

For Full Analysis (Default): Omit output_fields or set all fields to true to include all available data.

Error Handling

Common Error Scenarios

Invalid API Key: Authentication failed
File Too Large: File exceeds size limits
Invalid Configuration: Malformed processing parameters
Server Error: Internal processing error
Processing Timeout: Task took too long to complete
Missing File or URL: Neither file nor url parameter provided
Both File and URL Provided: Cannot provide both file and url simultaneously
Invalid URL: URL is not accessible or malformed
URL Download Failed: Unable to download document from provided URL

Authorizations

api-key

string

header

required

Body

multipart/form-data

file

required

Supported file types: PDFs, Images (PNG, JPEG, TIFF, BMP) and Office Documents (DOCX, XLSX, PPTX)

use_high_resolution

boolean

default:false

Whether to use high-resolution images for cropping and post-processing (default: false)

segmentation_method

enum<string>

default:smart_layout_detection

Document segmentation strategy

Available options:

smart_layout_detection,

page_by_page

ocr_mode

enum<string>

default:auto_ocr

OCR processing strategy

Available options:

auto_ocr,

full_ocr

merge_tables

boolean

default:false

Whether to merge adjacent table segments (default: false)

keep_segment_types

string

default:all

Filter output to include only specific segment types. Accepts comma-separated list (e.g., 'table', 'picture', 'table,picture') or 'all' for everything (default: 'all')

validate_table_segments

boolean

default:false

Whether to validate and correct table segment types using VLM (default: false)

Response

200 - application/json

Successful response

job_id

string

Unique identifier for the parsing job

status

string

Initial job status (typically 'Starting')

file_name

string

Name of the uploaded file

created_at

string

Timestamp when the job was created

message

string

Status message about the job creation

quota_remaining

number

Remaining page quota for the API key

merge_tables

boolean

Whether table merging is enabled

Parsing

Extraction

Classification

Splitting

PDF Editor

Organization

​Overview

​Request

​Parameter Details

​File Input Options

​Segmentation Method

​OCR Mode

​Table Merging

​Content Type Filtering

​Output Fields Configuration

​Segment Analysis Configuration

​Response

​Document Analysis Features

​Text Extraction

​Image Recognition

​Table Parsing

​OCR Processing

​Section Detection

​Bounding Box Information

​Advanced Content Processing

​Retrieving Results

​Expected Results Structure

​Segment Types

​Picture

​SectionHeader

​Text

​Table

​Caption

​Formula

​Title

​Footnote

​ListItem

​Configuration Best Practices

​For High-Accuracy Processing

​For Fast Processing

​For Financial Documents (Tables + Charts)

​For Data Extraction Only (Tables)

​Output Fields Optimization (Optional)

​Error Handling

​Common Error Scenarios

Authorizations

Body

Response

Overview

Request

Parameter Details

File Input Options

Segmentation Method

OCR Mode

Table Merging

Content Type Filtering

Output Fields Configuration

Segment Analysis Configuration

Response

Document Analysis Features

Text Extraction

Image Recognition

Table Parsing

OCR Processing

Section Detection

Bounding Box Information

Advanced Content Processing

Retrieving Results

Expected Results Structure

Segment Types

Picture

SectionHeader

Text

Table

Caption

Formula

Title

Footnote

ListItem

Configuration Best Practices

For High-Accuracy Processing

For Fast Processing

For Financial Documents (Tables + Charts)

For Data Extraction Only (Tables)

Output Fields Optimization (Optional)

Error Handling

Common Error Scenarios