Supported Document Types

Feathery Document Intelligence handles a variety of document and media types.

Feathery Document Intelligence handles a variety of document and media types.

PDFs

Feathery leverages both the information directly embedded in the file as well as PDF metadata to return accurate information about the document. Make sure to set the Uploaded File Type field to Documents or images.

Document and Image Extractions

Images

Feathery leverages computer vision and optical character analysis to analyze the context of the document. Make sure to set the Uploaded File Type field to Documents or images.

Document and Image Extractions

Word Docs

Feathery leverages both the information directly embedded in the file as well as Word doc metadata to return accurate information about the document. Make sure to set the Uploaded File Type field to Documents or images.

Document and Image Extractions

CSVs and Spreadsheets

Make sure to set the Uploaded File Type field to CSVs or Spreadsheets. Feathery AI can pull data from semantically relevant columns and specific cells as well.

Spreadsheet and CSV Extractions

Direct AI Queries

Query Feathery AI directly with field data formatted into an open-ended prompt rather than read from a pre-defined medium. Set the Uploaded File Type field to Free-Form Query.

Free-form Extractions

Emails

To have Feathery process emails directly, enable the inbox integration which will run on relevant email threads. Make sure to also toggle the relevant extraction queries that you would like to run on the email. If relevant data isn't found on the email for a given query, it will fall back to looking in the documents attached to the email thread.

To extract from an email or document attached in an email, forward it to [email protected] from a domain or email address enabled in the Integrations tab within the AI product.

Voice

Leverage Feathery's call integration or upload voice files directly into Feathery. Feathery extractions handle both the process of transcribing the audio and extracting semantically meaningful information out of the audio. (Demo)

Audio Extractions