Introducing FastRTC, a new way to build real-time AI apps

Read More
  1. Helpers
  2. RetryData

New to Gradio? Start here: Getting Started

See the Release History

To install Gradio from main, run the following command:

pip install https://gradio-builds.s3.amazonaws.com/373007b3e9d019ee41589d1dbb09a7511a024a51/gradio-5.20.1-py3-none-any.whl

*Note: Setting share=True in launch() will not work.

RetryData

gradio.RetryData(ยทยทยท)

Description

The gr.RetryData class is a subclass of gr.Event data that specifically carries information about the .retry() event. When gr.RetryData is added as a type hint to an argument of an event listener method, a gr.RetryData object will automatically be passed as the value of that argument. The attributes of this object contains information about the event that triggered the listener.

Example Usage

import gradio as gr

def retry(retry_data: gr.RetryData, history: list[gr.MessageDict]):
    history_up_to_retry = history[:retry_data.index]
    new_response = ""
    for token in api.chat_completion(history):
        new_response += token
        yield history + [new_response]

with gr.Blocks() as demo:
    chatbot = gr.Chatbot()
    chatbot.retry(retry, chatbot, chatbot)
demo.launch()

Attributes

Parameters
๐Ÿ”—
index: int | tuple[int, int]

The index of the user message that should be retried.

๐Ÿ”—
value: Any

The value of the user message that should be retried.