Feature request: Reading plots and tables from documents #3

Closed
opened 2026-02-16 03:17:15 -05:00 by yindo · 2 comments
Owner

Originally created by @itsalissonsilva on GitHub (Jul 5, 2025).

Originally assigned to: @AstraBert on GitHub.

It would be very useful if NotebookLlama could detect, extract, and interpret plots and tables embedded in documents so that fast/simple analysis can be carried directly in it.

Originally created by @itsalissonsilva on GitHub (Jul 5, 2025). Originally assigned to: @AstraBert on GitHub. It would be very useful if NotebookLlama could detect, extract, and interpret plots and tables embedded in documents so that fast/simple analysis can be carried directly in it.
yindo closed this issue 2026-02-16 03:17:15 -05:00
Author
Owner

@AstraBert commented on GitHub (Jul 6, 2025):

Hey there, if you want to try out this functionality, you can checkout the branch associated to #9, and then run:

uv sync
streamlit run src/notebookllama/Home.py

It is still in preview and thus not the best, but curious of knowing what are your opinions on it!

@AstraBert commented on GitHub (Jul 6, 2025): Hey there, if you want to try out this functionality, you can checkout the branch associated to #9, and then run: ```bash uv sync streamlit run src/notebookllama/Home.py ``` It is still in preview and thus not the best, but curious of knowing what are your opinions on it!
Author
Owner

@itsalissonsilva commented on GitHub (Jul 6, 2025):

Running on some utf encoding issues:

Error processing file: 'utf-8' codec can't decode byte 0xe7 in position 149: invalid continuation byte
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xe7 in position 149: invalid continuation byte
Traceback:

File "C:\Users\Lenovo\Downloads\notebookllama-clelia-citation-finder-and-interactive-tables\notebookllama-clelia-citation-finder-and-interactive-tables\src\notebookllama\pages\3_Interactive_Table_and_Plot_Visualization.py", line 98, in <module>
    image_paths, dataframes = get_plots_and_tables_sync(file_bytes)
                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Lenovo\Downloads\notebookllama-clelia-citation-finder-and-interactive-tables\notebookllama-clelia-citation-finder-and-interactive-tables\src\notebookllama\pages\3_Interactive_Table_and_Plot_Visualization.py", line 42, in get_plots_and_tables_sync
    return loop.run_until_complete(get_plots_and_tables(file_path=fl.name))
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python311\Lib\asyncio\base_events.py", line 654, in run_until_complete
    return future.result()
           ^^^^^^^^^^^^^^^
File "C:\Users\Lenovo\Downloads\notebookllama-clelia-citation-finder-and-interactive-tables\notebookllama-clelia-citation-finder-and-interactive-tables\src\notebookllama\utils.py", line 243, in get_plots_and_tables
    _, images, tables = await parse_file(
                        ^^^^^^^^^^^^^^^^^
File "C:\Users\Lenovo\Downloads\notebookllama-clelia-citation-finder-and-interactive-tables\notebookllama-clelia-citation-finder-and-interactive-tables\src\notebookllama\utils.py", line 158, in parse_file
    analyzer = MarkdownAnalyzer(tmp_file.name)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python311\Lib\site-packages\mrkdwn_analysis\markdown_analyzer.py", line 414, in __init__
    self.text = f.read()
                ^^^^^^^^
File "<frozen codecs>", line 322, in decode

Gonna try fixing it a bit later.

@itsalissonsilva commented on GitHub (Jul 6, 2025): Running on some utf encoding issues: ``` Error processing file: 'utf-8' codec can't decode byte 0xe7 in position 149: invalid continuation byte UnicodeDecodeError: 'utf-8' codec can't decode byte 0xe7 in position 149: invalid continuation byte Traceback: File "C:\Users\Lenovo\Downloads\notebookllama-clelia-citation-finder-and-interactive-tables\notebookllama-clelia-citation-finder-and-interactive-tables\src\notebookllama\pages\3_Interactive_Table_and_Plot_Visualization.py", line 98, in <module> image_paths, dataframes = get_plots_and_tables_sync(file_bytes) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Lenovo\Downloads\notebookllama-clelia-citation-finder-and-interactive-tables\notebookllama-clelia-citation-finder-and-interactive-tables\src\notebookllama\pages\3_Interactive_Table_and_Plot_Visualization.py", line 42, in get_plots_and_tables_sync return loop.run_until_complete(get_plots_and_tables(file_path=fl.name)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python311\Lib\asyncio\base_events.py", line 654, in run_until_complete return future.result() ^^^^^^^^^^^^^^^ File "C:\Users\Lenovo\Downloads\notebookllama-clelia-citation-finder-and-interactive-tables\notebookllama-clelia-citation-finder-and-interactive-tables\src\notebookllama\utils.py", line 243, in get_plots_and_tables _, images, tables = await parse_file( ^^^^^^^^^^^^^^^^^ File "C:\Users\Lenovo\Downloads\notebookllama-clelia-citation-finder-and-interactive-tables\notebookllama-clelia-citation-finder-and-interactive-tables\src\notebookllama\utils.py", line 158, in parse_file analyzer = MarkdownAnalyzer(tmp_file.name) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Lenovo\AppData\Local\Programs\Python\Python311\Lib\site-packages\mrkdwn_analysis\markdown_analyzer.py", line 414, in __init__ self.text = f.read() ^^^^^^^^ File "<frozen codecs>", line 322, in decode ``` Gonna try fixing it a bit later.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: run-llama/notebookllama#3