Document Intelligence
Extract structured data via natural language from documents, images, and spreadsheets.
Last updated
Was this helpful?
Extract structured data via natural language from documents, images, and spreadsheets.
Last updated
Was this helpful?
Was this helpful?
Feathery Document Intelligence automatically extracts structured data from your documents, either directly uploaded or automatically pulled from your system of record.
Go to the AI tab of your account and click Create Extraction.
Give your extraction a name.
Specify the type of file you're extracting. Feathery supports images & documents, spreadsheets, audio/video, and even free-form AI queries that don't process documents.
Once the extraction is created, you will need to go to the Queries tab of the extraction to specify the data you want to extract from the document.
For each piece of data, you will add a new query (in plain English) that tells Feathery AI what to extract. If no suitable value is found, the field will be left blank.
For each query, you can define the following components:
Frequency: this is how many values you want to extract for a specific query.
One Value returns a single value
Multiple Values returns multiple related values that may have multiple occurrences as well. For example, a table where you want to pull multiple columns of all relevant rows.
Page Numbers pulls a list of page numbers that contain the answer to your query. This can be used in a classification pipeline with another extraction
For example, if you have a composite document, the first extraction can identify the type and range of each subdocument. Then you can leverage the page numbers in the second extraction conditionally to only process the specific subdocument with the extraction tuned for that subdocument.
Entity: the information you want to pull from the document (e.g. stock holding, account balance, etc.)
Details (recommended): additional details or constraints about the entity to be queried that allow Document Intelligence to fine-tune relevant data (e.g. only pull securities that are domestic).
Save To (optional): which form or hidden field to save the extracted values to.
Advanced Options
Programmatic or AI-based page filtering options
Saving the associated file name to a field
On the Settings tab, you have access to additional configurations for the extraction.
Specify file field source(s) if you want files to be uploaded and processed from your Feathery forms.
Specify reviewers for your extraction. They will receive email notifications when new extractions are available for review, and they can review / approve extracted data.
You can have Document Intelligence run on files uploaded to your form or connect it to native Feathery integrations like Gmail, S3, Google Drive, Egnyte, and more to automatically pull in new documents uploaded to specific storage destinations.
Create a form with a file upload field.
In your extraction settings, include the newly created field under File Upload Fields.
In your form, add a button with the AI Document Extraction action and select the Extraction you previously created. Now, any files uploaded to this field and submitted by your users will automatically trigger the Extraction to run. You can also specify if you want your form fillers to wait until the extraction completes so the form populates with extracted data for review / update.
By enabling an integration on the extraction, you can automatically pull new files from your existing file store without needing to manually upload them to Feathery.
You can also trigger an extraction directly from Feathery's public API.
You can set up extraction variants to reuse the same extraction queries and apply them to different forms and fields. In the extraction configuration, go to the variants page in the sidebar and create a new variant. Here you can assign new field mappings to the file source and to each query. Once created, the variant will be accessible when configuring the trigger action.
