Overview
inboxparser Advanced OCR is a powerful Google Sheets add-on that transforms PDF documents, images, spreadsheets, and Word files into structured data in Google Sheets. Using Azure's industry-leading OCR algorithms, inboxparser can extract text from both handwritten and computer-generated documents with exceptional accuracy.
Template-First Extraction
Unlike traditional OCR tools that simply convert documents to text and preserve their original layout, inboxparser uses a template-first approach:
- You define the data structure you need - Create a schema that specifies exactly what information matters to your business
- inboxparser extracts only what you need - Our AI identifies and pulls just the relevant data points
- Get consistent, structured output every time - No matter what format your input documents use
Example: Accounting professionals processing invoices from multiple vendors, each with different layouts and formats. With inboxparser, you define the key data points once (invoice number, date, amount, vendor name, etc.), and get uniform, structured data ready for analysis - regardless of which vendor format you're processing.
Supported Document Types
inboxparser works with virtually any document type you need to process:
PDF Documents
- Digital native PDFs
- Scanned documents
- Forms and structured documents
Images
- JPG/JPEG
- PNG
- Screenshots
Microsoft Office Documents
- Word (.doc, .docx)
- Excel (.xls, .xlsx)
inboxparser has these Text Recognition Capabilities built-in:
- Machine-printed text
- Handwritten text
- Tables and structured data
- Multi-page documents
Installation
Follow these steps to get started with inboxparser Google Sheets Add-on:
- Install directly from Google Workspace Marketplace
- Sign up and create an account with inboxparser directly from Google Sheets to receive a 3-page free trial with advanced functionalities
Table Configuration
Setting up a new table in inboxparser is now easier than ever. Just define the columns you want to extract, and inboxparser will automatically extract every relevant row from your documents.
Getting Started in Google Sheets
- Open a new Google Sheet
- Notice the yellow "table not configured" notification in the side panel
- Rename your Sheet to give your table a descriptive name
- Click the gear icon "Configure" to set up your table
Define Your Table Schema
After clicking "Configure", you will be prompted to select a destination for your table. The dropdown will show "Create new table: [Sheet Name]" as the first option. Click "Confirm selection" to create a new table on the current sheet. Once you create a template, you can reuse it on other sheets by selecting it from this same dropdown menu.
When creating a new template, you have two options:
- Add columns and define them manually
- Choose from pre-built templates for common use cases
For example, selecting the receipt template automatically adds common receipt fields (date, amount, vendor, etc.), which you can then customize to match your specific requirements.
Adding Columns
- Click "Add column" in the configuration panel
- Choose each column’s data type (text, number, yes/no)
- Use clear and descriptive column names (e.g., "Transaction Date", "Amount", "Description")
- Optionally, add sample values or notes to improve extraction accuracy
- Hit "Save and sync with inboxparser" when you're done
Note: Once configured, inboxparser will automatically extract **all rows** matching your schema—no extra setup needed, even for multi-row documents like bank statements or invoices.
Example Use Cases
Bank Statement
- Columns: Transaction Date (text), Amount (number), Description (text)
- Result: Each row in the bank statement becomes a row in your Sheet automatically
Receipt Line Item Extraction
- Columns: Receipt Number, Item Name/Description, Quantity, Unit Price, Line Total
- Result: One row per item—no extra steps required
You no longer need to create or manage templates separately in the web app. Everything can be done directly in Google Sheets, with automatic multi-row extraction handled by default.
Uploading and Parsing Documents
Once you are done with table configuration, inboxparser offers two methods for uploading documents:
Local files
- Drag/drop or select files/folders from your computer
Google Drive
- Pick files/folders from your Google Drive directly from the add-on
After uploading, click "Extract data" and wait for your sheet to populate with the extracted information.
Metadata Extraction
In addition to extracting data from document content, inboxparser can capture file metadata such as file names and URLs. This is particularly useful for tracking document sources and maintaining audit trails.
Setting Up Metadata Columns
- Go to table configuration by clicking the gear icon "Configure"
- Add two new columns to your template: File Name (text type) and File URL (text type)
- Click "Save and sync with inboxparser"
Linking Metadata Fields
After saving your template, you need to configure the metadata field mappings:
- Open table configuration again
- Configure the File Name column: Unlink from current field (e.g. rows.file_name) and link to extra.file_name
- Configure the File URL column: Unlink from current field (e.g. rows.file_url) and link to extra.url
- Save your configuration
Note: File URLs are only captured when using Google Drive file selection.
Privacy and Support
All uploaded files are deleted from our servers once processing is complete.
For questions or improvement suggestions, contact us or email help@inboxparser.io.
