Skip to main content
POST
/
v2
/
parse
/
upload
# Step 1: Create job and get presigned URL
RESPONSE=$(curl -s -X POST https://prod.visionapi.unsiloed.ai/v2/parse/upload \
  -H "api-key: your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "file_name": "report.pdf",
    "use_high_resolution": true,
    "layout_analysis": "smart_layout_detection",
    "ocr_strategy": "auto_detection",
    "extract_strikethrough": false,
    "merge_tables": false
  }')

JOB_ID=$(echo "$RESPONSE" | jq -r '.job_id')
UPLOAD_URL=$(echo "$RESPONSE" | jq -r '.upload_url')

# Step 2: Upload file
curl -X PUT "$UPLOAD_URL" \
  -H "Content-Type: application/pdf" \
  --data-binary @report.pdf

# Step 3: Poll for results
curl -X GET "https://prod.visionapi.unsiloed.ai/parse/$JOB_ID" \
  -H "api-key: your-api-key"

{
  "job_id": "a3f1c2d4-7e8b-4a9f-b2c1-123456789abc",
  "upload_url": "https://upload.visionapi.unsiloed.ai/uploads/a3f1c2d4.../report.pdf?signature=...",
  "expires_at": "2025-10-22T07:06:16Z",
  "upload_method": "PUT",
  "upload_headers": {
    "Content-Type": "application/pdf"
  },
  "credit_used": 1,
  "quota_remaining": 1000
}

​
Overview

The v2 presigned upload endpoint decouples document delivery from job creation. Instead of uploading your file through the API server, you:
  1. POST to /v2/parse/upload with your configuration: the API creates a parse job and returns a short-lived presigned URL.
  2. PUT your file directly to the presigned URL: the API server is never in the transfer path.
  3. Once the upload completes, the job is automatically enqueued for processing.
  4. Poll GET /parse/{job_id} to track progress and retrieve results (the same endpoint as v1).
This is the recommended endpoint for large files and high-throughput workloads. It supports faster uploads, larger file sizes, and higher concurrency than the standard Parse Document endpoint.
The job status starts as AwaitingUpload. It transitions to Queued once the upload completes, then to Processing, and finally Succeeded or Failed. See Get Parse Job Status for the full response schema and polling examples.

​
Request

​
file_name
string
required
File name with extension (e.g. "report.pdf"). Determines the MIME type for the presigned URL. Supported formats: PDF, images (PNG, JPG/JPEG, TIFF/TIF, WebP), office documents (DOC, DOCX, PPT, PPTX, XLS, XLSX), and HTML (HTML/HTM).
​
use_high_resolution
boolean
Enhanced image quality: enables high-resolution processing with upscaling algorithms. Improves OCR accuracy on low-quality scans by enhancing clarity and contrast. Latency penalty: ~2–3 seconds per page. Defaults to false.
​
layout_analysis
string
Layout analysis strategy: smart_layout_detection (default), page_by_page, or advanced_layout_detection.
  • "smart_layout_detection" (default): Identifies document structure, headers, sections, and content relationships across the entire document using bounding boxes.
  • "page_by_page": Analyzes each page independently as a single segment. Faster for simple documents.
  • "advanced_layout_detection": Higher-accuracy layout detection for complex pages — multi-column layouts, dense tables/figures. Slower than smart_layout_detection.
​
ocr_strategy
string
OCR strategy: auto_detection (default) or force_ocr.
  • "auto_detection" (default): Intelligently detects bad quality PDFs, scanned documents, and images, then applies OCR only where needed.
  • "force_ocr": Runs OCR on the entire document regardless of quality.
​
ocr_engine
string
OCR engine to use for text recognition: UnsiloedHawk (default, recommended), UnsiloedBeta, or UnsiloedStorm.
  • "UnsiloedHawk" (Recommended, default): Higher accuracy for complex layouts and mixed content.
  • "UnsiloedBeta": Handles rotated/warped text and irregular bounding boxes.
  • "UnsiloedStorm": Enterprise-grade accuracy optimized for 50+ languages.
​
agentic_ocr
string
Per-segment OCR enhancement: re-runs a dedicated agentic OCR model on each detected segment after layout detection for higher accuracy. Omit or leave empty to disable.
  • "standard": Good balance of speed and accuracy.
  • "advanced": Higher quality, best for complex layouts, rotated text, and mixed-language content.
​
extract_strikethrough
boolean
Strikethrough detection: detects and preserves strikethrough formatting in HTML and Markdown output. Defaults to false.
​
merge_tables
boolean
Cross-page table consolidation: detects and combines table segments across page breaks. Reconstructs complete table structure by matching headers and columns. Defaults to false.
​
merge_batch_size
integer
Maximum number of tables per merge group. Groups larger than this are split. Defaults to 20; values below 2 are clamped to 2.
​
enhance_reading_order
boolean
Fix the reading order of detected segments. Useful for multi-column layouts. Defaults to false.
​
detect_pii
boolean
Run a PII pre-check before parsing. If PII is found at the configured severity, the task is rejected without parsing. Defaults to false.
​
pii_block_severity
string
Severity threshold to block on when detect_pii is enabled: any (default), low, medium, or high. any blocks on any PII found; low adds quasi-identifiers (names, dates, locations); medium blocks on contact PII (email, phone) or higher; high blocks only on direct identifiers (SSN, passport, credit card). Ignored if detect_pii is false.
​
pii_engine
string
PII detector engine: standard (default) or advanced (higher precision, additional processing cost). Any other value falls back to standard. Ignored if detect_pii is false.
​
extract_links
boolean
Attach hyperlink URLs from PDF annotations to OCR results. Defaults to false.
​
extract_colors
boolean
Transfer text color from the PDF text layer to OCR results. Defaults to false.
​
xml_citation
boolean
Citation extraction: extracts academic citations from PDF documents and hyperlinks them in the markdown output. Generates structured bibliography metadata. PDFs only. Defaults to false.
​
page_range
string
Specify which pages to process. Leave empty to process all pages.Examples: "1-5" (pages 1 to 5), "2,4,6" (specific pages), "[1,3,5]" (array format), "1-3,7,10-15" (combination).
​
expires_in
integer
Seconds the returned presigned upload URL stays valid. Defaults to 15 minutes (900 seconds). Once the client uploads the file, the task’s expiry is cleared and the task lifetime is no longer bounded by this value.
​
export_format
array
Export format(s) to generate after processing. Supported: ["docx", "markdown", "json"]. The exported files are available via the exports field in the task response.
​
segment_type_naming
string
Segment type naming convention. "Unsiloed" (default) uses names like PageHeader, ListItem, Picture. "Other" uses alternative names like Header, List Item, Figure.
​
segment_filter
string
Comma-separated segment types to keep in the output, or "all" to include every type. Defaults to "all".
​
validate_segments
array
Segment validation: uses a vision model to validate and correct segment types, fixing misclassified segments. Example: ["Table", "Formula", "Picture"]. Defaults to ["Table", "Picture"]; an empty or unparseable value also falls back to that default, so Table and Picture validation runs even when this field is omitted.
​
validate_table_segments
boolean
Legacy option to validate table segments using a vision model. Prefer validate_segments instead.
​
chunk_processing
object
JSON object controlling how segments are grouped into chunks. See the v1 parse endpoint for full schema details.
​
segment_processing
object
Configure how different segment types are processed: table models, image descriptions, and formula processing.
On this endpoint the field is named segment_processing. The v1 alias segment_analysis is not accepted here and is silently ignored.
{
  "Table": {"html": "VLM", "markdown": "VLM", "model_id": "us_table_v2"},
  "Picture": {"html": "VLM", "markdown": "VLM", "model_id": "nova"},
  "Formula": {"html": "Auto", "markdown": "VLM", "model_id": "nova"}
}
Options per segment type:
  • html / markdown: "VLM" or "Auto"
  • model_id (Table): "astra", "us_table_v1", "us_table_v2"
  • model_id (Picture/Formula): "nova", "luna", "sol"
  • use_table_ocr (Table only): Advanced OCR for bordered cells and complex table layouts.
  • vlm: Custom prompt for the VLM model. Use this to give the model specific instructions for extracting or describing these segment types.
  • translation: Optional per-segment translation, e.g. {"provider": "Auto", "target_language": "en"}. provider is "Auto" for fast machine translation or "VLM"/"LLM" for model-based translation; target_language is an ISO 639-1 code, or "auto" to auto-detect the source and translate to English.
For full details, see Parse Document (v1).
​
llm_processing
object
JSON object for LLM processing configuration.
​
output_fields
object
JSON object controlling which fields are included in the output. Set fields to false to exclude them and reduce response size. Available fields: html, markdown, ocr, image, content, bbox, confidence, embed, chart_data. All default to true. Ignored when response_profile is slim or full (the profile wins).
​
response_profile
string
Response shape selector: slim, full, or custom. Omit to return the full shape.
  • "slim": Returns only the essentials per chunk — embed, bbox, page_number, segment_id, segment_type, and HTML for tables / Markdown for everything else. Drops content, image, ocr, confidence, chart_data, page_height, page_width. Best for embedding-only workflows where you want the smallest payload.
  • "full": Every field returned (equivalent to omitting this param).
  • "custom": Honor output_fields verbatim.
When both response_profile and output_fields are provided, the profile wins — output_fields is only consulted for custom or when the profile is omitted.
​
error_handling
string
How to handle per-page errors during processing. "Continue" (default) skips failed pages and continues processing the rest. "Fail" aborts the entire job on the first error.

​
Response

​
job_id
string
Unique identifier for the parse job. Use this with GET /parse/{job_id} to poll status and retrieve results.
​
upload_url
string
Presigned PUT URL. Upload your file directly to this URL; no api-key header is needed for the upload itself. Valid until expires_at.
​
expires_at
string
RFC 3339 timestamp when upload_url expires. Upload must complete before this time. The presigned URL is valid for 15 minutes by default; when expires_in is set (and positive), the upload URL lifetime is set to that same value, which can shorten or extend the window.
​
upload_method
string
Always "PUT". Use an HTTP PUT request when uploading to upload_url.
​
upload_headers
object
Key-value headers you MUST include in your PUT request. Always includes Content-Type set to the MIME type inferred from file_name.
​
credit_used
integer
Number of page credits deducted as an initial reservation, reconciled on upload.
​
quota_remaining
integer
Remaining page credits after deduction.

​
Step-by-Step Guide

​
Step 1: Create the parse job

POST to /v2/parse/upload with your file name and configuration. The API returns a job_id and a short-lived presigned URL. 
import requests

API_KEY = "your-api-key"
BASE_URL = "https://prod.visionapi.unsiloed.ai"

response = requests.post(
    f"{BASE_URL}/v2/parse/upload",
    headers={"api-key": API_KEY, "Content-Type": "application/json"},
    json={
        "file_name": "report.pdf",
        "use_high_resolution": True,
        "layout_analysis": "smart_layout_detection",
        "ocr_strategy": "auto_detection",
        "extract_strikethrough": False,
        "merge_tables": False,
    },
)
response.raise_for_status()
data = response.json()

job_id = data["job_id"]
upload_url = data["upload_url"]
upload_headers = data["upload_headers"]

print(f"Job ID: {job_id}")
print(f"Upload URL expires: {data['expires_at']}")
The response contains the presigned URL and required headers: 
{
  "job_id": "a3f1c2d4-7e8b-4a9f-b2c1-123456789abc",
  "upload_url": "https://upload.visionapi.unsiloed.ai/uploads/a3f1c2d4.../report.pdf?signature=...",
  "expires_at": "2025-10-22T07:06:16Z",
  "upload_method": "PUT",
  "upload_headers": {
    "Content-Type": "application/pdf"
  },
  "credit_used": 1,
  "quota_remaining": 1000
}

​
Step 2: Upload the file

Use the upload_url and upload_headers from the response to PUT your file. No API key is needed for this request. 
with open("report.pdf", "rb") as f:
    put_response = requests.put(upload_url, headers=upload_headers, data=f)
put_response.raise_for_status()

print("Upload complete, job is now queued for processing")
You must include every header listed in upload_headers. A missing or mismatched Content-Type will cause the upload to be rejected with a 403.

​
Step 3: Poll for results

Once the upload completes, the job transitions from AwaitingUpload → Queued → Processing → Succeeded. Poll GET /parse/{job_id} using the same endpoint as v1. 
import time

while True:
    status_response = requests.get(
        f"{BASE_URL}/parse/{job_id}",
        headers={"api-key": API_KEY},
    )
    status_response.raise_for_status()
    job = status_response.json()
    print(f"Status: {job['status']}")

    if job["status"] == "Succeeded":
        print(f"Done! {job['total_chunks']} chunks extracted.")
        break
    elif job["status"] == "Failed":
        raise RuntimeError(f"Job failed: {job.get('message')}")

    time.sleep(5)
See Get Parse Job Status for the full response schema. 
# Step 1: Create job and get presigned URL
RESPONSE=$(curl -s -X POST https://prod.visionapi.unsiloed.ai/v2/parse/upload \
  -H "api-key: your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "file_name": "report.pdf",
    "use_high_resolution": true,
    "layout_analysis": "smart_layout_detection",
    "ocr_strategy": "auto_detection",
    "extract_strikethrough": false,
    "merge_tables": false
  }')

JOB_ID=$(echo "$RESPONSE" | jq -r '.job_id')
UPLOAD_URL=$(echo "$RESPONSE" | jq -r '.upload_url')

# Step 2: Upload file
curl -X PUT "$UPLOAD_URL" \
  -H "Content-Type: application/pdf" \
  --data-binary @report.pdf

# Step 3: Poll for results
curl -X GET "https://prod.visionapi.unsiloed.ai/parse/$JOB_ID" \
  -H "api-key: your-api-key"

{
  "job_id": "a3f1c2d4-7e8b-4a9f-b2c1-123456789abc",
  "upload_url": "https://upload.visionapi.unsiloed.ai/uploads/a3f1c2d4.../report.pdf?signature=...",
  "expires_at": "2025-10-22T07:06:16Z",
  "upload_method": "PUT",
  "upload_headers": {
    "Content-Type": "application/pdf"
  },
  "credit_used": 1,
  "quota_remaining": 1000
}

​
Why Use v2

Featurev1 (POST /parse)v2 (POST /v2/parse/upload)
File deliveryThrough API serverDirect via presigned URL
Max file sizeLimited by server uploadUp to 5 GB via direct PUT
Upload speedBottlenecked by API serverFull client bandwidth
ConcurrencyShared server capacityNo server contention
Best forQuick uploads, small filesLarge files, high volume

​
Error Handling

StatusCauseAction
400Invalid or missing file_name, unsupported extensionFix file_name and retry
401Missing or invalid api-keyCheck your API key
402Insufficient quota or expired creditsAdd page credits to your account or renew your plan
403Access has been revokedContact support
429Rate limit exceededBack off and retry after 1 second
500Internal server errorRetry with exponential backoff
503Job queue is at capacityBack off and retry after the Retry-After header value
403 on uploadMissing or wrong headers, expired URLCheck upload_headers, get a new URL
Job status FailedProcessing errorCheck message field in the status response
A job can move from Queued straight to Failed without ever reaching Processing: after the upload, the document is page-counted and rejected if it exceeds the page limit (default 2000 pages; split large documents first) or if the remaining page quota cannot cover it.

Authorizations

​
Authorization
string
header
required

API key for authentication. Use 'Bearer <your_api_key>'

Body

application/json

Request body for POST /v2/parse/upload. Configuration fields mirror the existing /parse multipart form fields.

​
file_name
string
required

File name with extension. Required. Determines content-type.

​
agentic_ocr
string | null

Enable per-segment agentic OCR for higher accuracy. Pass "standard" or "advanced".

​
chunk_processing
any

JSON object for chunk processing configuration.

​
detect_pii
boolean | null
default:false

Run a PII pre-check before parsing. When enabled, the document is scanned for personally identifiable information before any extraction work happens. If PII is found at or above pii_block_severity, the task is rejected and no parsing occurs (the job ends in a failed state with a PII reason). Defaults to false.

​
enhance_reading_order
boolean | null

Fix the reading order of detected segments. Useful for multi-column layouts. Defaults to false.

​
error_handling
string | null

Error handling strategy: Continue (default) or Fail.

​
expires_in
integer<int32> | null

Seconds the returned presigned upload URL stays valid. Defaults to the PRESIGNED_UPLOAD_EXPIRY_SECS env value (typically 900 / 15 min). Once the client uploads the file, the task's expires_at is cleared and the task lifetime is no longer bounded by this value.

​
export_format
enum<string>[] | null

Export format(s) to generate after processing. Supported: ["docx", "markdown", "json"].

File format for exporting parsed results. When specified in a parse request, the pipeline generates the requested export file after processing completes. The exported file is available via the exports field in the task response.

Available options:
docx,
markdown,
json
​
extract_colors
boolean | null

Transfer text color from the PDF text layer to OCR results. Defaults to false.

​
extract_links
boolean | null

Attach hyperlink URLs from PDF annotations to OCR results. Defaults to false.

​
extract_strikethrough
boolean | null

Preserve strikethrough formatting in HTML/Markdown output. Defaults to false.

​
layout_analysis
string | null

Layout analysis strategy: smart_layout_detection (default), page_by_page, or advanced_layout_detection (higher-accuracy layout detection for complex pages — multi-column layouts, dense tables/figures; slower than the default).

​
llm_processing
any

JSON object for LLM processing configuration.

​
merge_batch_size
integer<int32> | null

Maximum number of tables per merge group. Groups larger than this are split. Defaults to 20.

​
merge_tables
boolean | null

Merge tables that span multiple pages into a single unified structure. Defaults to false.

​
ocr_engine
string | null

OCR engine: UnsiloedHawk (default, recommended), UnsiloedBeta, or UnsiloedStorm.

​
ocr_strategy
string | null

OCR strategy: auto_detection (default) or force_ocr.

​
output_fields
any

JSON object filtering which fields appear on each segment / chunk. Each key defaults to true; set a key to false to drop the field. Keys: bbox, chart_data, confidence, content, embed, html, image, markdown, ocr. Ignored when response_profile is slim or full.

​
page_range
string | null

Page range to process. Formats: "1-5", "2,4,6", "[1,3,5]". Defaults to all pages.

​
pii_block_severity
string | null
default:any

Severity threshold at which a detected PII finding blocks the task. Ignored when detect_pii is false. Findings strictly below the threshold are allowed through; findings at or above it reject the task.

  • any (default) — block on any detection, regardless of severity.
  • low — block on low, medium, or high severity findings.
  • medium — block on medium or high severity findings.
  • high — block only on high severity findings.
​
pii_engine
string | null
default:standard

PII detector engine to use when detect_pii is true. Ignored otherwise.

  • standard (default) — fast pattern-based detector; low latency, well-suited to bulk pre-screening.
  • advanced — model-based detector; slower but catches contextual cases that pattern matching misses (e.g. handwritten names, partially redacted IDs, document-style references to a person).
​
response_profile
string | null

Response shape selector: slim, full, or custom.

  • slim: chunk embed + bbox + page_number + segment_id + segment_type + HTML for tables / Markdown otherwise. Drops content/image/ocr/confidence/chart_data/page_height/page_width.
  • full: every field returned (equivalent to omitting this param).
  • custom: honor output_fields verbatim.

When both response_profile and output_fields are provided, the profile wins.

Example:

"slim"

​
segment_filter
string | null

Segment filter: comma-separated segment types to keep, or "all". Defaults to "all".

​
segment_processing
any

JSON object for segment processing/analysis configuration.

​
segment_type_naming
string | null

Segment type naming convention: Unsiloed (default) or Other.

​
use_high_resolution
boolean | null

Use high-resolution images for cropping and post-processing. Defaults to true.

​
validate_segments
any

JSON array of segment types to validate with VLM. Example: ["Table","Formula"].

​
validate_table_segments
boolean | null

Legacy: validate table segments using VLM. Prefer validate_segments instead.

​
xml_citation
boolean | null

Extract and hyperlink bibliography citations in the markdown output. Defaults to false.

Response

Upload URL created

Response from POST /v2/parse/upload.

​
credit_used
integer<int32>
required

Number of page credits deducted (initial reservation, reconciled on upload).

​
expires_at
string
required

RFC 3339 timestamp when upload_url expires.

​
job_id
string
required

Use this ID to poll GET /parse/{job_id} for status.

​
quota_remaining
integer<int32>
required

Remaining page credits after deduction.

​
upload_headers
object
required

Headers the client MUST include in the PUT request.

​
upload_method
string
required

Always "PUT".

​
upload_url
string
required

S3 presigned PUT URL. Valid until expires_at.