Retab has long enabled teams to extract structured data from the world’s messiest unstructured documents — from PDFs and Excel sheets to Word files and PowerPoint decks. Now, we’re unlocking the other half of intelligent document automation: writing back into your documents with precision, context awareness, and minimal configuration.

Whether you’re automating form completion, generating dynamic reports, or batch-processing standardized templates, Retab Edit turns hours of manual effort into a single API call.

What Is Retab Edit?

The Edit API in Retab’s document processing suite empowers developers to automatically fill in forms and templates across multiple formats using natural language instructions or structured JSON. Powered by large language models and intelligent document understanding, Retab Edit handles everything from detecting fillable fields to preserving original layout and formatting.

Unlike traditional templating systems that require rigid schemas or manual tagging, Retab Edit requires zero field mapping up front — simply describe the values you want filled in plain text or JSON, and the API figures out the rest.

Multi-Format Support — One Unified API

Retab Edit works seamlessly across the most common office and document formats:

• PDF (.pdf) — Detect form fields via OCR and fill text fields, checkboxes, and more.

• Word (.docx, .doc, .odt) — Edit the native XML to insert content while preserving formatting.

• Excel (.xlsx, .xls, .ods) — Populate cells and tables using structured data.

• PowerPoint (.pptx, .ppt, .odp) — Replace placeholders and text in slides with dynamic content.

This multi-format capability means developers can unify workflows that span across file types without stitching together different tools or services.

How It Works

At its core, Retab Edit takes two inputs:

1. A document — either uploaded, referenced by URL, or provided as Base64 (MIMEData).

2. Filling instructions — a natural language description or structured JSON that tells Retab what values to insert.

Once submitted, the Edit API intelligently:

• Identifies fillable elements in the document

• Matches your instructions to fields

• Populates values while preserving the original format

• Returns the filled document as MIMEData and a list of filled fields for inspection.

A Real Example

Here’s a Python snippet illustrating a simple form fill:

from retab import Retab
import base64

client = Retab()

result = client.documents.edit(
    document=”application-form.pdf”,
    filling_instructions=”“”
    Full Name: Jane Smith
    Date of Birth: March 15, 1985
    Email: jane.smith@example.com
    Phone: (555) 123-4567
    “”“,
)

if result.filled_document:
    base64_content = result.filled_document.url.split(”,”)[1]
    filled_bytes = base64.b64decode(base64_content)
    with open(”filled-application.pdf”, “wb”) as f:
        f.write(filled_bytes)

print(f”Filled {len(result.form_data)} fields”)

This snippet fills a PDF with user details, saves the filled version, and prints how many form fields were populated.

Why Retab Edit Matters

Retab was built to handle the full lifecycle of document-based automation — from parsing and extraction to evaluation and deployment. Edit fills a critical gap by enabling automated document generation, broadening Retab’s utility beyond read-only extraction.

A few benefits:

• Zero templates or manual tagging — Let the AI discover fields automatically.

• Natural language instructions — Describe what you want in plain English or JSON.

• Preserved formatting — Office docs retain original layout and styles.

• Batch and dynamic workflows — Fill many forms programmatically with varying data.

Get Started Today

Retab Edit is part of the Retab document automation platform — available via API and supported SDKs like Python and JavaScript. Whether you’re building internal tools or powering a production pipeline, Edit brings dynamic document writing into reach with minimal overhead.

Explore the playground and try it for yourself — we can’t wait to see what you build.