I need help to add image recognition in my Voiceflow chat. Users upload Images or documents and based on that the bot responds. Can anyone give me any suggestions?
To add images to your Voiceflow chat assistant, you can follow these steps:
Image Step for Uploading Images
Voiceflow allows you to include images in your chat assistants using the Image Step. Here's how you can add images:
For Chat-based Assistants: Visuals will show up as in-line visuals within the chat dialog.
For Voice-based Assistants: Visuals will appear on your device's screen, in parallel with voice-based interactions.
### 2. Uploading Images To upload an image:
Navigate inside an Image Step.
Drag-and-drop your desired image or GIF into the editor, or click Browse to select one from your computer.
The uploaded file will have an auto-generated hosted image link by Voiceflow.
### 3. Previewing Images Once your image is uploaded, the preview modal on the Canvas-view updates and resizes to the image properties. You can hover over the image to preview it in full-sized view.
Using Image Links
You can also use a direct link to an image hosted online. Paste the link directly into the 'Link' tab of the Image Step. You can use a variable (using '{') to host the image link for dynamic image feeds.
Please note that the information about integrating image recognition is not supported by the provided source documents. For further assistance, you may want to refer to the official Voiceflow documentation or support.
Just go to Claude or chat gpt and ask it to create you replit endpoint that launches a web UI with an image / file uploader on it. Hit the endpoint with an api from Voiceflow or even embed it in an iframe? Lots of options from there. All really quick and easy if you’re familiar with replit. Ask an AI agent to talk you through it if not.