Frequently Asked Questions

General Questions

What file formats are supported?

We support PDF, DOC, DOCX, PPT, PPTX, JPG, JPEG, and PNG formats.

What are the file size limits?

• Trial users: Maximum 5MB per file, first page only
• Paid users: Maximum 200MB per file, up to 600 pages

Note:

• Single file size cannot exceed 200MB
• File pages cannot exceed 600 pages
• Due to network restrictions, foreign URLs like github, aws may timeout
• Direct file upload is not supported, you need to provide an accessible file URL

How long does parsing take?

• Small files (< 10 pages): Usually 5-15 seconds
• Medium files (10-50 pages): Usually 30-60 seconds
• Large files (50-600 pages): Usually 2-10 minutes

API Questions

How do I get an API key?

1. Register an account
2. Go to the dashboard
3. Navigate to API Keys section
4. Click "Create New Key"
5. Copy the generated key and store it securely

How do I authenticate API requests?

All API requests require an Authorization header in the HTTP request:

Authorization: Bearer YOUR_API_KEY

Format is Bearer + space + your API key.

What are the API endpoints?

Base URL: /api/v1/extract

Create Task: POST /api/v1/extract/task

Get Task: GET /api/v1/extract/task/{taskId}

What is the rate limit?

• Trial: 10 requests per minute
• Pro: 60 requests per minute
• Enterprise: Customizable

Do you support webhooks?

Yes, you can provide a callback parameter when creating a task, and we will send a POST request to that URL when parsing is complete.

Notes:

• The callback endpoint must support POST method, UTF-8 encoding, and Content-Type: application/json
• When using callback, you must also provide the seed parameter for signature verification
• Return HTTP 200 status code to indicate successful reception
• If reception fails, the system will retry up to 5 times

See Webhooks documentation for details.

How do I handle errors?

All API responses include code and message fields:

• code = 0 indicates success
• code != 0 indicates failure, message contains error information

Common Error Codes:

What are the task states?

Task states include:

• pending: Queued
• running: Parsing in progress
• converting: Format conversion in progress
• done: Parse completed
• failed: Parse failed

What formats are included in the parse results?

After parsing is complete, you can get the full parse result package via fullZipUrl, which includes:

• Markdown format document content (default format)
• JSON format structured data (default format)
• Optional exports in docx, html, latex formats (set extraFormats parameter)

Billing Questions

How is usage calculated?

Usage is calculated by the number of pages processed, not the number of API calls.

Will I be charged for failed parsing?

No. Only successfully parsed pages are counted. If task creation fails or parsing fails, your quota will not be deducted.

Can I get an invoice?

Yes, you can apply for invoices in the Invoices section of your dashboard.

Is there a daily parsing quota limit?

Each account enjoys 2000 pages of highest priority parsing quota per day. Portions exceeding 2000 pages may have reduced priority.

Technical Questions

How can I improve parsing accuracy?

1. Use high-quality original documents: Avoid scanned documents or low-resolution images
2. Enable OCR function: For scanned documents or image formats, set is_ocr: true
3. Select the correct language: Specify document language in the request (language parameter), default is Chinese (ch)
4. Ensure document format is correct: Avoid corrupted or encrypted files
5. Enable formula and table recognition: Set enable_formula: true and enable_table: true

How do I specify parsing specific pages?

You can use the pageRanges parameter when creating a task to specify page ranges, formatted as comma-separated strings:

• "1-5": Pages 1 to 5
• "2,4-6": Page 2, pages 4 to 6
• "2--2": From page 2 to the second-to-last page

Do you support batch parsing?

Currently the API only supports single file parsing. For batch processing, please call the create task API in a loop.

Security & Privacy

Is my document secure?

Yes, we take data security very seriously:

• All API communications use HTTPS encryption
• Documents are automatically deleted after processing
• We will not use your documents for other purposes

Can I delete parse results immediately?

Yes, you can manually delete parse results in the user center or contact our support team.

Do you support private deployment?

Enterprise edition supports private deployment. Please contact our sales team for details.

Getting Help

Have more questions?

If you have other questions, you can:

• Check Complete API documentation
• Contact support: support@parse4ai.com
• Join our community discussion group

How do I report a bug?

Please send an email to support@parse4ai.com with the following information:

• Detailed problem description
• Reproduction steps
• Related task ID or trace_id
• Error message screenshots