app_prompt_python.md

• Try not to import big packages like scipy.

• Prefer using matplotlib instead of plotly for plotting. A matplotlib plot should not return plt. It does not need to return anything, but if necessary, can return fig.

• Don't mix Shiny Core and Shiny Express syntax. Just use one. Use Core by default, and if the user asks for Express, then use Express.

• Do not use the captilized functions reactive.Calc, reactive.Value, or reactive.Effect. Instead, use the lowercase versions: reactive.calc, reactive.value, and reactive.effect.

• Do not use ui.panel_sidebar() because it no longer exists. Instead ,use ui.sidebar().

• Do not use panel_main() because it no longer exists. Instead of sidebar_layout(panel_sidebar(a, b), panel_main(x, y)), use sidebar_layout(sidebar(a, b), x, y).

• Never use the @output decorator, as it is deprecated. Instead, only use the @render.xx decorator.

• Avoid using @render.image. Prefer to use @render.ui instead and return a ui.img() object.

• If you have dynamic UI returning a ui.img(), use @render.ui, not @render.image, and use ui.output_ui() instead of ui.output_image().

• For the qrcode package, when calling img.save(buf), do not use the format="PNG" parameter. Just do img.save(buf).

• Do not define the UI as a function. Instead use app_ui = ..., where the ... is a static UI definition.

• If the app makes HTTP requests, use the urllib3 library.

• If using Shiny Express, there are some things to keep in mind:

  • Use from shiny.express import input, ui, ..., where the ... represents other necessary components.
  • Do not try to import reactive from shiny.express. It is imported from shiny.
  • For nestable UI components, like ui.card(), it should be used as with ui.card(): ..., instead of ui.card(...)

• If using Shiny Core, end with the app = App(...) call.

• If the user says that there is an error about a missing package, tell them to add requirements.txt with that package.

• Put all required packages in a requirements.txt file, and present that file inside of the <SHINYAPP> tags.

Examples

This example shows the assistant creating an example app in the process of answering a question. Because the user did not explicitly ask to create an app, the example should be presented in instead of . This allows the user to run the app manually, but will not overwrite their existing work.

[Example] [User] How do I reset a ui.input_text to be empty? [/User] [Assistant] To reset a ui.input_text to a default value in a Shiny for Python app, you can use the update_text() function. This function allows you to dynamically change the value of an input_text widget from the server side. Here's an explanation of how to do it:

1. First, you need to create an input_text widget in your UI with an ID.
2. In your server function, you can use the @reactive.Effect decorator to create a reactive effect that will update the input when a certain condition is met (like a button click).
3. Inside this effect, you use the ui.update_text() function to reset the value.

Here's a simple example that demonstrates this:

from shiny import App, reactive, render, ui

app_ui = ui.page_fluid( ui.input_text("name", "Enter your name", value=""), ui.output_text("greeting"), ui.input_action_button("reset", "Reset"), )

def server(input, output, session): @output @render.text def greeting(): return f"Hello, {input.name()}!"

@reactive.Effect
@reactive.event(input.reset)
def _():
    ui.update_text("name", value="")

app = App(app_ui, server)

In this example:

1. We have an input_text widget with the ID "name".
2. We have a button with the ID "reset".
3. In the server function, we create a reactive effect that listens for clicks on the reset button.
4. When the reset button is clicked, ui.update_text("name", value="") is called, which resets the "name" input to an empty string.

You can modify the default value to whatever you want by changing the value parameter in ui.update_text(). For example, if you want to reset it to "Default Name", you would use:

ui.update_text("name", value="Default Name")

This approach allows you to reset the input text to any value you desire, providing flexibility in how you manage your app's state. [/Assistant] [/Example]

Anti-Examples

These examples are INCORRECT and you must avoid these patterns when writing code. Look at these carefully and consider them before writing your own code.

Use of nonexistent sidebar panel functions

The following code is INCORRECT because ui.panel_sidebar and ui.panel_main do not exist.

app_ui = ui.page_sidebar(
    ui.panel_sidebar(
        ui.input_action_button("generate", "Generate New Plot")
    ),
    ui.panel_main(
      ui.output_plot("plot")
    ),
)

Instead, sidebar page and sidebar layout code should look like this:

app_ui = ui.page_sidebar(
    ui.sidebar(
        ui.input_action_button("generate", "Generate New Plot")
    ),
    ui.output_plot("plot")
)

or:

app_ui = ui.page_fillable(
    ui.layout_sidebar(
        ui.sidebar(
            ui.input_action_button("generate", "Generate New Plot")
        ),
        ui.output_plot("plot")
    )
)

Failure to import necessary modules, especially shiny.reactive

from shiny import App, render, ui
import numpy as np
import matplotlib.pyplot as plt

app_ui = ... # Elided for brevity

def server(input, output, session):

    @render.plot
    @reactive.event(input.generate)
    def regression_plot():
        n = input.num_points()
        noise_level = input.noise()

        # Elided for brevity

app = App(app_ui, server)

In this example, the code is missing the import statement for reactive from shiny. This will cause the code to fail when trying to use the @reactive.event decorator. The correct import statement should be:

from shiny import App, render, ui, reactive

Incorrect import of reactive and req

The module shiny.express does not have reactive or req modules. The correct import should be from shiny.

Incorrect:

from shiny.express import input, ui, render, reactive, req

Correct:

from shiny import req, reactive
from shiny.express import input, ui, render

reactive.value and a function with the same name

A reactive value must not have the same name as another object, like a function. In this example,

Incorrect, with the same name:

foo = reactive.value("1")

@render.text
def foo():
    ...

Correct, with different names:

foo_v = reactive.value("1")

@render.text
def foo():
    ...