Document Classifier#

Leverage AI to analyze the text of input documents and classify them into categories such as invoices, orders, or industry-specific types. This feature is particularly useful for quickly identifying the source of a document. It also allows for the implementation of custom classification rules to tailor the analysis to specific needs.

Make Step

Input#

Name	Description	Required
Import Options	Choose the input source, either `Upload a File` or `Import PDF or Image from URL`.	Yes

**Upload a File**#
Name	Description	Required
Data	Upload a file using raw binary data from another module. Note: This requires additional credits as it first uploads to PDF.co Temporary Files Storage.	Yes

**Import PDF or Image from URL**#
Name	Description	Required
URL	Provide the URL to the source PDF document, or a `filetoken://` link from PDF.co Built-In Files Storage. If you use another cloud service such as Google Drive or Dropbox ensure the link is publicly accessible.	Yes

Name	Description	Required
Set custom rules	Optionally, define classification rules in CSV format. Each row should be formatted as `classname,logic,keyword1,keyword2`. Example: `Amazon,AND,Amazon AWS,AWS Invoice`. For detailed instructions, refer to PDF Classifier.	No
Load custom rules from CSV via url	Provide a link to a CSV containing custom classification rules. Each row should be formatted as `classname,logic,keyword1,keyword2`. Example: `Amazon,AND,Amazon AWS,AWS Invoice`. For detailed instructions, refer to PDF Classifier.	No
Case Sensitive Custom Rules Enabled	Specify whether the keywords in custom rules should be case sensitive.	No
Execution Mode	Select Sync for small tasks up to `10` seconds. Choose Async for standard jobs, or Async For Large Docs for tasks over `30` seconds. Use Job Check module for retrieving results in large tasks.	No
Profiles	Add custom options for the process in a `JSON` string format. See API Profiles for more details.	No

Integrating External File Sources#

Note

Streamline your Make workflows with external file sources like Google Drive and Dropbox using their unique actions. Discover efficient integration strategies in our guide: File Source Integrations in Make.

Output#

Name	Description
`url`	This is the temporary URL provided by the PDF.co file server.
`Body`	Contains the identified document categories, listed in a `classes` string array.
`Status`	Indicates the response status code. A `success` status is returned if the operation is successful.
`outputLinkValidTill`	Specifies the timestamp until which the `url` remains accessible.
`error`	Provides details about any errors encountered during the process, if applicable.
`File Name`	The designated name of the output file.
`Job Id`	A unique identifier assigned to the job.
`credits`	The amount of credits utilized for the process.
`Remaining Credits`	Displays the balance of credits available in your account.
`duration`	The duration of time the process took to complete.

Was this page helpful?