How To Export Custom Plots from Deep Research Citations

In a Deep Research chat where you have created a custom chart or graph, you can export the interactive chart as a static image following these instructions:

First, if you want to make adjustments to how the chart looks, ask Deep Research a follow-up question in the chat thread asking it to make the changes you would like. 

Once you have a visual you are satisfied with, locate the "Creating chart" citation or activity item in the purple "Research completed" banner just below the blue "Save as..." box.

• The "Input" box will contain the python code for a function named "llm_make_figure"
  • This will include the data that will be incorporated in the graphic(s) itself, not necessarily the raw data e.g. if the average values are being graphed, the code likely only contains the averages, not the datapoints from which they were derived. 
  • You can insert this function into any python context and perform actions on the figure including exporting to several image formats. 
  • For example, if you would like a higher resolution version of a chart(s) you can export to .svg by:
    • Windows
      • Open a blank file in "Notepad" or another text editing or IDE application. 
      • Copy and paste the "Input:" from the "Creating chart" activity
      • Replace return fig on the last row with fig.write_image("chart.svg")
        • Replace .svg with .png etc to save to another supported format.
      • Open command prompt or powershell (or another application able to run python such as Visual Studio Code) 
      • Type python then "return" or "enter" (you should now see >>>)
      • Copy and paste in your modified code from above then "return" or "enter" until you again see see >>>
      • Type llm_make_figure() then "return" or "enter"
      • The image file should now be in the directory where you were when you started the terminal, by default typically your user's home folder (where Documents and Desktop are usually located)
      • [To exit, type exit() or quit the command prompt app]
    • Mac, Linux
      • Open a blank file in "Textedit" or another text editing or IDE application. 
      • Copy and paste the "Input:" from the "Creating chart" activity
      • Replace return fig on the last row with fig.write_image("chart.svg")
        • Replace .svg with .png etc to save to another supported format.
      • Open "Terminal" (or another application able to run python such as Visual Studio Code) 
      • Type python then "return" or "enter" (you should now see >>>)
      • Copy and paste in your modified code from above then "return" or "enter" until you again see see >>>
      • Type llm_make_figure() then "return" or "enter"
      • The image file should now be in the directory where you were when you started the terminal, by default typically your user's home folder (where Documents and Desktop are usually located)
      • [To exit, type exit() or quit the command prompt app]
    • Jupyter notebook (including cloud-based options such as Google Colab)
      • Create a new notebook
      • Create a new code block
      • [You may need to run a few commands such as 
        • !pip install -U kaleido
        • import kaleido
        • kaleido.get_chrome_sync() 
      • and run them first in a seperate code block -- the error messages should guide you through this one-time setup.]
      • Copy and paste the "Input:" from the "Creating chart" activity
      • Replace return fig on the last row with fig.write_image("chart.svg")
        • Replace .svg with .png etc to save to another supported format.
      • Click "Run All" or "Run Cell"
      • The File should now be available in your "Files", by default in the /content/ directory.