The Edit API allows you to programmatically modify documents using natural language instructions, enabling automated document transformations and updates.
Basic Usage
from reducto import Reducto
client = Reducto()
response = client.edit.run(
document_url="https://example.com/document.pdf",
edit_instructions="Replace all instances of 'Company A' with 'Company B'"
)
print(response)
import asyncio
from reducto import AsyncReducto
client = AsyncReducto()
async def main():
response = await client.edit.run(
document_url="https://example.com/document.pdf",
edit_instructions="Replace all instances of 'Company A' with 'Company B'"
)
print(response)
asyncio.run(main())
Method Signature
client.edit.run(
document_url: str,
edit_instructions: str,
edit_options: dict | None = None,
form_schema: list | None = None,
priority: bool | None = None
) -> EditResponse
Parameters
The URL of the document to edit. You can provide:
- A publicly available URL
- A presigned S3 URL
- A
reducto:// prefixed URL from the /upload endpoint
Natural language instructions describing the edits to make to the document.
Additional options to control the editing process.
Form schema for PDF forms. List of widgets with their types, descriptions, and bounding boxes. Only works for PDFs.
If true, attempts to process the job with priority if the user has priority processing budget available. By default, sync jobs are prioritized above async jobs.
Text Replacement
Replace text throughout the document:
from reducto import Reducto
client = Reducto()
response = client.edit.run(
document_url="https://example.com/contract.pdf",
edit_instructions="""
1. Replace 'John Doe' with 'Jane Smith'
2. Update the date from '2023-01-01' to '2024-01-01'
3. Change the contract value from '$100,000' to '$150,000'
"""
)
# Download the edited document
print(response.output_url)
import asyncio
from reducto import AsyncReducto
client = AsyncReducto()
async def main():
response = await client.edit.run(
document_url="https://example.com/contract.pdf",
edit_instructions="""
1. Replace 'John Doe' with 'Jane Smith'
2. Update the date from '2023-01-01' to '2024-01-01'
3. Change the contract value from '$100,000' to '$150,000'
"""
)
# Download the edited document
print(response.output_url)
asyncio.run(main())
from reducto import Reducto
client = Reducto()
response = client.edit.run(
document_url="https://example.com/form.pdf",
edit_instructions="Fill in the form with the following information: Name: Alice Johnson, Date: 2024-03-15, Amount: $5000",
form_schema=[
{
"type": "text",
"description": "Name field",
"bbox": [100, 100, 300, 120]
},
{
"type": "text",
"description": "Date field",
"bbox": [100, 150, 300, 170]
},
{
"type": "text",
"description": "Amount field",
"bbox": [100, 200, 300, 220]
}
]
)
print(f"Edited form: {response.output_url}")
Content Redaction
Redact sensitive information from documents:
from reducto import Reducto
client = Reducto()
response = client.edit.run(
document_url="https://example.com/confidential.pdf",
edit_instructions="""
Redact all of the following:
- Social Security Numbers
- Phone numbers
- Email addresses
- Credit card numbers
Replace them with '[REDACTED]'
"""
)
print(f"Redacted document: {response.output_url}")
from reducto import Reducto
client = Reducto()
response = client.edit.run(
document_url="https://example.com/report.pdf",
edit_instructions="""
1. Make all section headings bold
2. Add page numbers to the footer
3. Change the font of body text to Arial 11pt
4. Add a table of contents on page 2
""",
edit_options={
"preserve_layout": True
}
)
Priority Processing
Use priority processing for urgent edits:
from reducto import Reducto
client = Reducto()
response = client.edit.run(
document_url="https://example.com/urgent.pdf",
edit_instructions="Update the delivery date to 2024-03-20",
priority=True
)
Async Job Processing
For large documents or batch processing, use async jobs:
from reducto import Reducto
client = Reducto()
# Start an async edit job
job = client.edit.run_job(
document_url="https://example.com/large-document.pdf",
edit_instructions="Apply corporate branding updates throughout the document",
webhook={
"url": "https://example.com/webhook"
}
)
print(f"Job ID: {job.job_id}")
# Poll for results
result = client.job.get(job.job_id)
print(f"Edited document: {result.output_url}")
Batch Edits Example
Apply consistent edits across multiple documents:
from reducto import Reducto
client = Reducto()
documents = [
"https://example.com/doc1.pdf",
"https://example.com/doc2.pdf",
"https://example.com/doc3.pdf"
]
edit_instructions = """
Update company branding:
1. Replace old logo with new logo
2. Update company address to '123 New Street, City, State 12345'
3. Change contact email to 'info@newdomain.com'
"""
jobs = []
for doc_url in documents:
job = client.edit.run_job(
document_url=doc_url,
edit_instructions=edit_instructions
)
jobs.append(job)
print(f"Started {len(jobs)} edit jobs")
# Check job statuses
for job in jobs:
result = client.job.get(job.job_id)
print(f"Job {job.job_id}: {result.status}")
Upload and Edit
Upload a local file and edit it:
from reducto import Reducto
from pathlib import Path
client = Reducto()
# Upload the document
upload_response = client.upload(
file=Path("/path/to/document.pdf")
)
# Edit the uploaded document
edit_response = client.edit.run(
document_url=upload_response.url,
edit_instructions="Remove all comments and track changes from the document"
)
print(f"Cleaned document: {edit_response.output_url}")