[PP-1] Image upload feature in AI Chatbot

Created on 27 May 2025, 2 months ago

Overview

🐛 External AI Chatbot Functionality Active Implemented the AI feature in Experience Builder, which currently supports only textual prompts to generate components. This issue aims to enhance the functionality by adding support for image uploads to help generate the desired component.

Proposed resolution

User interface changes

📌 Task
Status

Active

Version

0.0

Component

Page builder

Created by

🇮🇳India narendraR Jaipur, India

Live updates comments and jobs are added and updated live.
Sign in to follow issues

Merge Requests

Comments & Activities

  • Issue created by @narendraR
  • First commit to issue fork.
  • Merge request !1229Resolve #3526717 "Image upload feature" → (Merged) created by utkarsh_33
  • Pipeline finished with Failed
    29 days ago
    Total: 1134s
    #538900
  • 🇮🇳India utkarsh_33

    I'll assign it to me as this still needs some more work.

  • Pipeline finished with Canceled
    26 days ago
    Total: 91s
    #540715
  • Pipeline finished with Failed
    26 days ago
    Total: 1408s
    #540717
  • Pipeline finished with Failed
    26 days ago
    #540734
  • 🇫🇮Finland lauriii Finland

    Here are few examples that we could use to test this:

    Prompt 1:

    I want to build a hero component with heading, text and a slot for buttons. The highlighted part of the heading should use bold from CKEditor.

    Prompt 2:
    I want to build a hero component with heading, text and slot for buttons. There's also an image which is displayed on the right on desktop and hidden on mobile.

  • 🇩🇪Germany marcus_johansson

    I've added som comments - most is just NIT and doesn't actually stop merging.

    The bigger parts more UX questions, that I think laurii should answer if they are needed.

  • 🇮🇳India utkarsh_33

    Thanks for the review @Marcus_Johansson. I have made the changes which does not require inputs from @laurii.Remaining things can be done once we get the confirmation from @laurii.

  • 🇮🇳India utkarsh_33

    The current state of the MR works fine for creating simple code components. but there are some issues when there is an image which are as follows:-

    • When a user uploads an image as mentioned in #8's prompt 2 📌 [PP-1] Image upload feature in AI Chatbot Active It makes it hard for the ai to generate exact similar doodle. It identifies that a doodle is present but does not generate one which is exact similar.
    • When a user uploads an image like this then it does insert an image which is close to this(in this case it inserted and image of forest without the human)

    It does create simple components such as this one very well. Also as discussed with @laurii that if we tell the AI bot to create a component and also which image to insert in the images section then it does take care of that as well.

    @Marcus_Johansson, @laurii we can discuss further what all needs to be taken care of in this issue.

  • Pipeline finished with Failed
    25 days ago
    Total: 1329s
    #541850
  • Pipeline finished with Failed
    25 days ago
    Total: 1046s
    #541868
  • 🇺🇸United States tim.plunkett Philadelphia

    We have four options:

    1. Do nothing, let them overspend
    2. Client-side validation preventing large uploads
    3. Client-side modal informing them it's too big
    4. Convert/downscale the image ourselves before passing to AI
  • 🇮🇳India utkarsh_33

    I have created a follow-up issue which enables the client side validation of size for image uploads 📌 Client-side validation preventing large image uploads to LLM Active .

  • Pipeline finished with Failed
    23 days ago
    Total: 615s
    #543897
  • Pipeline finished with Canceled
    23 days ago
    Total: 168s
    #543908
  • Pipeline finished with Failed
    23 days ago
    Total: 2091s
    #543909
  • Pipeline finished with Failed
    23 days ago
    Total: 1118s
    #543987
  • Pipeline finished with Failed
    23 days ago
    Total: 1136s
    #544028
  • 🇮🇳India utkarsh_33

    Uploading the SS showing how the image upload icon looks like.

  • First commit to issue fork.
  • Pipeline finished with Failed
    23 days ago
    Total: 1131s
    #544193
  • Pipeline finished with Failed
    23 days ago
    Total: 838s
    #544407
  • 🇮🇳India utkarsh_33

    I have merged all the new changes and also tested that no existing scenario is breaking and the new once are working as expected. Marking this NR.

  • Pipeline finished with Failed
    22 days ago
    Total: 1337s
    #544781
  • 🇮🇳India narendraR Jaipur, India
  • 🇮🇳India utkarsh_33

    Addressed feedbacks.

  • Pipeline finished with Failed
    22 days ago
    Total: 1110s
    #544837
  • 🇮🇳India narendraR Jaipur, India

    On attaching image, it seems to be hidden under help text.

    I tested it manually and similar component gets created but it it has image, it is not replaced by a placeholder image as image url is wrong (not sure if this is an issue or not).

  • Pipeline finished with Canceled
    22 days ago
    Total: 1099s
    #544920
  • Pipeline finished with Failed
    22 days ago
    Total: 1151s
    #544938
  • Pipeline finished with Running
    22 days ago
    #545152
  • Pipeline finished with Canceled
    22 days ago
    #545192
  • Pipeline finished with Failed
    22 days ago
    #545195
  • 🇺🇸United States tim.plunkett Philadelphia
  • 🇮🇳India narendraR Jaipur, India

    Created 🐛 XB AI: Image not displaying actual URL in generated component Active for #19 image issue.
    Other changes looks good to me. Moving it to RTBC.

  • Pipeline finished with Failed
    22 days ago
    Total: 1537s
    #545351
  • 🇺🇸United States tim.plunkett Philadelphia

    Merged!

  • Pipeline finished with Failed
    22 days ago
    Total: 1005s
    #545398
  • Automatically closed - issue fixed for 2 weeks with no activity.

  • Status changed to Fixed 4 days ago
  • 🇺🇸United States Kristen Pol Santa Cruz, CA, USA

    unassigning to prep for dashboard: 📌 Unassign closed AI issues and update metadata in prep for dashboard Active

Production build 0.71.5 2024