Default attachment settings

To begin, take note of the generated email address that is unique to this specific flow. Copy the email address to your clipboard to start using this dedicated email address yourself or to share with others.

The File Type is set to CSV / TSV, though you can also receive XLS / XLSX, PDF, or JSON files.

The Delimiter is set to comma (,), but can also be adjusted to tab (\t) and semicolon (;). If needed, the default of Quote Character set to Double quote ( " " ) can be changed to single quote ( ' ' ).

Custom settings

This step contains optional Advanced settings, where you can tell Parabola to skip a certain number of rows or columns when receiving the attached file.

Auto-forwarding emails into a Parabola flow

To auto-forward a CSV attachment to an email outside of your domain, you may need to verify the @inbound.parabola.io email address. The below example shows how to set this up in Gmail.

Video overview

Step-by-step instructions

1. Prepare Your Extract from Email Step in Parabola

1. In your Parabola Flow, drag in a new Extract from Email step.
2. Configure it to pull in email content, not just attachments.
3. Click Update Results to generate the Parabola forwarding email address.

💡 You’ll use this address to forward emails into your Parabola Flow. Don't forget to copy this email address.

2. Set Up Forwarding in Gmail

1. Go to Gmail → click the gear icon → See all settings.
2. Navigate to the Forwarding and POP/IMAP tab.
3. Click “Add a forwarding address.”
4. Paste the email address from your Parabola step and click Next → Proceed.

3. Confirm the Gmail Forwarding Request via Parabola

1. Back in Parabola, refresh the Extract from Email step.
2. Look for an email with subject: Gmail Forwarding Confirmation.
3. Open the body and find the sentence:
   “Please click the link below to confirm the request.” It maybe easier to copy and paste the entire body content into a word doc or text editor for easier copy and pasting.
4. Copy the confirmation URL from the body, paste it in a browser, and click Confirm.

✅ Gmail will now recognize the Parabola address as a valid forwarding destination.

4. Create a Gmail Filter to Automatically Forward Specific Emails

1. In Gmail, go to Settings → Filters and Blocked Addresses → Create a new filter.
2. Set criteria such as:
   • From: nycwarehouse@gmail.com
   • Subject: New York City Warehouse Inventory
   • Has attachment: ✅
3. Click Create filter, then:
   • Check Forward it to and select your verified Parabola email address.
   • Click Create filter.

5. Clean up your Flow (If necessary)

1. If you created a temporary Extract from Email step just for the verification, you can now delete it.
2. Your Parabola Flow will continue to receive the filtered, auto-forwarded emails daily.

Other troubleshooting tips

• If you do not see the email content come into the Flow after a few minutes, double-check the email settings on that step/Flow. Click on the gear icon in the lefthand side of the step where it says "View all Flow email settings". Make sure the checkbox "Reject emails that do not contain valid attachments" is unchecked.
• If it is already checked, check your email inbox for an email with the subject line, "Sorry, we were unable to process your email attachment". The verification link from gmail should be available in the email content of this email. Click on the verification link and you should have successful verified this forwarding address!

Pull multiple file attachments

By default, Flows will run with the first valid attached file. If you want the Flow to run through multiple attached files (multiple attachments on one email), open the “Email trigger settings” modal and change the setting to “Run the Flow once per attachment:”

(Access these settings from the Extract from email step, or from the Flow trigger settings on the published Flow page.)

For emails with multiple files attached, the Flow will run once per file received, sequentially.

• Files must be of the same type (CSV, XLS, PDF, or JSON) for the runs to process.
• The file type is defined in the initial step settings (”File type” dropdown).
• Any files received that are of a different type will cause a Flow run error.

Pull from email content

We also support the ability to pull in additional information about an email.The default behavior pulls:

• Subject
• Body (plain text)
• CC
• From
• Attached file name

Additional fields:

• Body (HTML)
• Body (all URLs)
• Attached file URL

To access these fields, you can toggle the “Pull data from" field to ‘Email content’. If you'd like to pull both an attachment and the subject and body, select ‘Email content and attachment’.

Extract data from the body of an email with AI

Use the “Extract data with AI” option to automatically extract tables and key values from email bodies to create structured output.

Enable this option under "Parsing settings" when pulling in the “Email content”.

‍

Pull a sheet from an Excel file based on file position

Use the "position is" option when pulling in an attached Excel document to specify which sheet to pull data from by its position, rather than its name. This is great for files that have key data in consistent sheet positions, but may not always have consistent sheet names.

When using this option, only the number of sheets that are in the last emailed file will show in the dropdown. If a Flow using these settings is run and there is no sheet in the specified position, the step will error.

Helpful tips

• This step will run every time the dedicated email address receives a new attached file. This is useful for triggering your flow to run automatically, outside of a dedicated schedule or webhook.
• If your XLS file has multiple sheets, this step auto-selects the first sheet but can be set to look for a specific sheet.
• This step can handle attached files that are up to 5MB.
• Each run of a Flow uses one file. If your Flow has multiple Extract from email steps, they will all access the same email / file.
• What happens when multiple emails are received by your flow: If your flow is processing and another email (or multiple) comes in, then they will queue up to be pulled into your flow in the order they were received. All emails sent to a flow (up to 1,000 total) will be queued up and processed.
• By default, emails that are sent to Flow email addresses must have a valid attachment. You can disable that, and allow emails without attachments, by accessing the email trigger management modal and disabling the checkbox.
• This step can only ingest data from an email, not download a file. To generate and download a CSV from a link in an email, take the following steps:
  
  • Extract the CSV’s URL from the email content using Extract from email
  • Pass the URL into a Run another Flow step at the end of the Flow
  • Begin your destination Flow with Pull from file queue
  • End the destination Flow with a Generate CSV file step

‍

Understanding your Excel data

When extracting data from an Excel file, use the settings to extract a table, or individual values (or both)

• Tables should be composed of columns and rows, with a row representing the names of the columns
• Individual values are single pieces of data that are applicable to the entire document. For example, a date at the top of a document or an invoice number
• Columns and individual values can be given additional information to ensure the tool is identifying and returning the correct information - more on that below!

Step Configuration

Selecting Excel extraction

Once you have an Excel file in your flow, select "Extract data with AI". You will see options to add details to "Extract a table" and/or "Extract individual values".

Clicking on either of those will show additional fields to fill out. Each step can extract 1 table and any number of individual values.

Extract a table

Once you enable table extraction, do the following:

1. Give your table a description - this is used by AI to find the table so it's important to be clear and precise, especially if many tables are present.
2. Define your columns - each column can be named, given example values, and additional instructions. If a column is conceptually clear (i.e. "Item description") then a name might be all you need. But if the name of the column is ambiguous, or its values are ambiguous, it is best practice to add example cell values, as well as additional instructions describing what this column represents and how an AI should find it.

Extract individual values

Once you enable individual value extraction, do the following:

1. Define your value - each value can be named, given example values, and additional instructions. If a value is conceptually clear (i.e. "Port of entry") then a name might be all you need. But if the name of the column is ambiguous, or its values are ambiguous, it is best practice to add example cell values, as well as additional instructions describing what this value represents and how an AI should find it.

Choosing the "type" for a column or individual value

Columns and individual values are Text by default. But you can change that to improve accuracy:

• Text - anything
• True / False - results in either "True" or "False", can be used to detect checkmarks and other indicators
• Number - will remove trailing zeros on any number
• Currency -converts the currency to a number
• Date - uses "2022-09-27T18:00:00.000" format
• Signature - converts signatures to text
• List of options - chooses from a list of possible options you provide

Understanding your PDF data

Parabola’s Pull from PDF file step can be configured to return Columns or Keys

• Columns are parts of tables that are likely to have more than one row associated with them
• Keys are single pieces of data that are applicable to the entire document. As an example - “Total” rows or fields like dates that only appear once at the top of a document are best expressed as keys
• Sometimes AI can interpret something as a column or a key that a human might consider the other. If the tool is not correctly pulling a piece of information, you might try experimenting with columns versus keys for that data point
• Both columns and keys can be given additional information from you to ensure the tool is identifying and returning the correct information - more on that below!

Step Configuration

Selecting PDF Data

Once you have a PDF file in your flow, you will see a prompt for the second step - “Select table columns,” where you will provide information to the tool to determine what fields it should extract from the file. Parabola offers three methods for this configuration -

1. Use an auto-detected table (default)
2. Define a custom table
3. Extract all data

First, we’ll outline how these choices will impact your results and then we will discuss tips and best practices for fine tuning these results:

1. Use an auto-detected table
   • This selection, which is the default, will send the file through our PDF parsing pipeline, where our LLM will identify tables within the document, identify posible columns, name them, and extract available values.
   • Once this step finishes its first calculation, you should see a table selected with a set of columns. You can always add more columns to this original list - see the Manual Inputs selection below for more info!
   • Note that initial auto-detection does not provide any keys, however there is an option to do a full document or key specific auto-detect to have the tool provide this values
2. Define a custom table
   • If you don’t want for the step to take a first pass at auto-detection, or, if the auto-detection is excluding columns you were hoping to extract, you can manually define a specific table. This is an advanced feature that can extract data from tables that are not obvious to the AI. Auto-detected Tables are easier to work with, but if the AI did not find your table, try defining it with this custom setting.
3. Extract all data
   • This option will use primarily use OCR instead of an LLM to process your file. As a result of this, it is discouraged for most use cases.
   • Should you want to use this option, however, we provide four options for how you’d like your data returned:
     • All data: this will return all of the data in the PDF, listed as one value per row
     1. Table data: this will return only data from OCR-identified tables within the PDF file.– If your file has multiple tables, each will have a unique ID (which you can use to later filter results, for example), and results will be returned sequentially (e.g. table 1, then table 2, and so on). Note: tables that span multiple pages will be broken into individual tables for each page
     2. Key-Value pairs: this will return all identifiable key/value pairs – things that are clearly associated or labeled, such as “color: red” or “Customer name- Parabola”
     3. Raw text: this will return all of the PDF data, in a single cell (one cell per file page). This format is most useful if you plan to apply an AI step, like Extract or Categorize

Manual Inputs

• Parabola’s ability to make informed predictions on what fields you might be expecting from any PDF file is incredibly powerful, but you can always provide additional inputs to the tool to increase accuracy and ensure the output is aligned with your needs. Generally speaking, the more input you provide, the more accurate the results!
• Adding columns or keys is as easy as clicking the “+ Add column” or “+ Add key” button, which will open a prompt box. Here are a few tips for best results:
  1. Column and key names can be descriptive or instructive, and do not need to match exactly what the PDF says. However, you should try to ensure the name is something that the underlying AI can associate with the desired column of data
  2. Providing examples is the best way to increase the accuracy of column (or key) parsing
  3. The “Additional instructions to find this value” field is not required, however, here you can input further instructions on how to identify a value as well as instructions on how to manipulate that value. For example in a scenario where you want to make two distinct columns out of a singular value in the file, say an order number in the format “ABC:123". You might use the prompt - “Take the order ID and extract all of the characters before the “:” into a new column”

See below how in this case with handwriting, with more instructions the tool is able to determine if there is writing next to the word “YES” or “NO”

Fine Tuning

• In addition to column or key specific inputs, you can use the “Fine Tuning” to more holistically explain the type of document you are providing as well as additional information on the expected outcome. As always, if you have an expected outcome that is not being auto-generated, more examples and inputs should always help to improve accuracy

Advanced Settings

Parabola’s Pull from PDF step has four additional configurations:

1. Use advanced text extraction. Defaults to FALSE. If toggled on, this step will use a more sophisticated version of OCR text extraction that can be helpful for complex documents such as those with handwriting. This more advanced model will also result in the tool running slower, and as a result, we suggest only toggling this on if you are not satisfied with the results from simple text extraction. Note that if a run fails with simple text extraction, Parabola uses advanced extraction by default in re-trying
2. Retry step on error. Defaults to TRUE. LLMs can occasionally return unexpected errors and often times, re-running the step will resolve the issue. When checked, this step will automatically attempt to re-run one time when encountering an unexpected error
3. Auto-update prompt versions. Defaults to FALSE. Occasionally Parabola updates step prompts in order to make parsing results more accurate/reliable. These updates may change output results, and as a result, auto-updating is turned off by default. Enable this setting to always use the most reset prompt versions.
4. Page Filtering. Defaults to FALSE. Allows for user to define the specific pages of a document to run through the Pull from PDF step. If you only need specific values that are consistently on the same page(s), this can drastically improve run time.

Usage tips & Other Notes

• This step can take many minutes to run! Grab a coffee and relax while the AI does the work for you. The more document pages that are needed for parsing, the longer it may take. To expedite this process, you can configure the step to only review certain pages from your file. The fewer the pages, the faster the results!
• If you need to pull data across multiple tables (from a single file), you will likely need multiple steps – one per table.
• File size: PDF files must be <500 MB and 30 pages
• PDFs cannot be password protected
• We recommend always auditing the results returned in Parabola to ensure that they’re complete

Using child columns

Mark columns as “Child columns” if they contain rows that have values unique from the parent columns:

Before

After marking “Size” as a child column