Display PythonREPL graphics with Streamlit

Using Streamlit
1

So I’m trying to create a multi agent LLM application using Langgraph and Streamlit. With Langgraph’s official jupyter notebook, the chart_generator agent is able to produce and execute python code using PythonREPL. The graphics/plot display correctly on JupyterNotebook but when I try to use st.write() and st.image() to display the graphics/plot, it’s not showing up. Would love to get some pointers if anyone has any idea.

If you’re creating a debugging post, please include the following info:

  1. Are you running your app locally or is it deployed?
  2. If your app is deployed:
    a. Is it deployed on Community Cloud or another hosting platform?
    b. Share the link to the public deployed app.
  3. Share the link to your app’s public GitHub repository (including a requirements file).
  4. Share the full text of the error message (not a screenshot).
  5. Share the Streamlit and Python versions.
2

Hi @Lujia

If you can save the chart to file, you could use st.image() and you could also try one of several other methods mentioned in Chart elements - Streamlit Docs

3

Thanks for the speedy response.
But if you look into the code, the LLM agent is executing the Python code



@tool
def python_repl(
    code: Annotated[str, "The python code to execute to generate your chart."],
):
    """Use this to execute python code. If you want to see the output of a value,
    you should print it out with `print(...)`. This is visible to the user."""
    try:
        result = repl.run(code)
    except BaseException as e:
        return f"Failed to execute. Error: {repr(e)}"
    result_str = f"Successfully executed:\n```python\n{code}\n```\nStdout: {result}"
    return (
        result_str + "\n\nIf you have completed all tasks, respond with FINAL ANSWER."
    )```

Output in JupyterNotebook
![image|555x500](upload://p8ss67BnjmJW6VIltWniwwIIkW0.jpeg)

I haven't been able to find a way to save the chart and not sure how JupyterNotebook is displaying it.
4

In your tool instruct it to use plotly or st graphing functions not matplotlib