[FYI] Gravity Connect OpenAI Supports Vision and Attachments

General Discussion
, ,
1

This may have slipped under the radar — our OpenAI connection now supports Vision and Attachments.

This means that you can use GC OpenAI to “view” images and read files and then answer questions about them.

Here are a few neat ways to put this to work:

  1. Extract text from images – Get totals from receipts, addresses from correspondence, product information from tags.
  2. Custom reporting – Attach raw sales data to your Assistant and then let privileged users ask questions about that data to glean insights.
  3. Document comparison – Let users upload two different documents and have OpenAI highlight the differences.

Here’s a quick demo our founder recorded where he extracts text from a meme.

We’re continuing to add firepower to this little beast — you can learn more about text generation, image generation, audio transcription, and other features here.

1 Like