Lumir AI Multi-Image PDF Support#28
Conversation
- Update `backend/lumir/engine.py` to store received images in a list instead of overwriting the previous one. - Update `backend/lumir/utilities.py` to replace `convert_image_to_pdf` with `convert_images_to_pdf`, which combines multiple images into a single PDF using Pillow. - Update legacy commands (Passport, OCR, Compress) to use the last received image. - Clear image memory after processing PDF, Passport, OCR, or Compression commands. - Update AI response to indicate the number of images received. Co-authored-by: DivyanshuChipa <211708943+DivyanshuChipa@users.noreply.github.com>
|
👋 Jules, reporting for duty! I'm here to lend a hand with this pull request. When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down. I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job! For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with New to Jules? Learn more at jules.google/docs. For security, I will only act on instructions from the user who triggered this task. |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 4463c6848b
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
…addressing - Update `backend/lumir/engine.py` to store received images in a list instead of overwriting the previous one. - Update `backend/lumir/utilities.py` to replace `convert_image_to_pdf` with `convert_images_to_pdf`, which combines multiple images into a single PDF using Pillow. - Update legacy commands (Passport, OCR, Compress) to use the last received image. - Clear image memory after processing PDF, Passport, OCR, or Compression commands. - Update AI response to indicate the number of images received. - Fix user addressing issue by passing the `sender` argument to the `ask_ai` function in `backend/lumir/engine.py`. Co-authored-by: DivyanshuChipa <211708943+DivyanshuChipa@users.noreply.github.com>
…addressing - Update `backend/lumir/engine.py` to store received images in a list instead of overwriting the previous one. - Update `backend/lumir/utilities.py` to replace `convert_image_to_pdf` with `convert_images_to_pdf`, which combines multiple images into a single PDF using Pillow. - Update legacy commands (Passport, OCR, Compress) to use the last received image. - Clear image memory after processing PDF, Passport, OCR, or Compression commands. - Update AI response to indicate the number of images received. - Fix user addressing issue by passing the `sender` argument to the `ask_ai` function in `backend/lumir/engine.py`. Co-authored-by: DivyanshuChipa <211708943+DivyanshuChipa@users.noreply.github.com>
…g-in-pdf-assembly [Follow-up to #28] Fix file descriptor leak in multi-image PDF conversion
1 participant
This PR updates the Lumir AI backend to support processing multiple images.
Previously, sending a new image would overwrite the last one in the bot's memory. Now, images are appended to a list.
The
###topdf###command has been upgraded to convert all accumulated images into a single multi-page PDF.Legacy commands like
###passport###,###ocr###, and###compress###have been updated to operate on the most recently sent image, preserving backward compatibility.PR created automatically by Jules for task 10169340627586131963 started by @DivyanshuChipa