Skip to content

Comments

Add file upload support and smart icon selection#6

Draft
google-labs-jules[bot] wants to merge 1 commit intomainfrom
feature/file-upload-icons
Draft

Add file upload support and smart icon selection#6
google-labs-jules[bot] wants to merge 1 commit intomainfrom
feature/file-upload-icons

Conversation

@google-labs-jules
Copy link
Contributor

This PR adds functionality to upload files for content generation and chart data extraction. It also introduces an embedding-based icon selection mechanism.

  1. File Uploads: Users can now upload text-based files (TXT, CSV, Excel) instead of using web search. The content is extracted and passed to the LLM for planning.
  2. Chart Data: Users can upload images or data files for charts. The system extracts structured data (using GPT Vision for images) and uses it to generate charts.
  3. Icons: An IconSelector uses pre-computed embeddings to find the most relevant icon for a given keyword and inserts it into the slide.
  4. UI Updates: The frontend html_ui.py is updated to include upload controls and toggle between "Web Search" and "Upload Files".
  5. Dependencies: Added pandas, openpyxl, scikit-learn, numpy, openai, flask, flask-cors, python-dotenv, Pillow.

PR created automatically by Jules for task 14490717894268034394 started by @nattu22

- Implement FileProcessor for extracting text (txt, csv, xlsx) and chart data (img, csv, xlsx).
- Update frontend to allow file uploads for content and charts.
- Update backend API to handle file uploads and pass extracted content to planning.
- Update PlanGeneratorOrchestrator to utilize extracted content.
- Implement IconSelector using cosine similarity on embeddings.
- Update ExecutionOrchestrator to insert icons and inject chart data.
- Update requirements.txt with necessary dependencies (pandas, openpyxl, Pillow, scikit-learn, etc.).
@google-labs-jules
Copy link
Contributor Author

👋 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 @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!


For security, I will only act on instructions from the user who triggered this task.

New to Jules? Learn more at jules.google/docs.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

0 participants