Fix returning/yielding chat message from callback

[ahuang11]

Closes #5708

[codecov]

Codecov Report

Merging #5712 (81cc5e5) into main (0067d40) will increase coverage by 1.65%.
The diff coverage is 100.00%.

@@            Coverage Diff             @@
##             main    #5712      +/-   ##
==========================================
+ Coverage   82.45%   84.11%   +1.65%     
==========================================
  Files         288      288              
  Lines       41995    42054      +59     
==========================================
+ Hits        34629    35374     +745     
+ Misses       7366     6680     -686     

Flag	Coverage Δ
ui-tests	40.74% <15.25%> (+2.62%)	⬆️
unitexamples-tests	73.75% <100.00%> (+0.03%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Files	Coverage Δ
panel/chat/feed.py	93.04% <100.00%> (+0.59%)	⬆️
panel/tests/chat/test_feed.py	99.80% <100.00%> (+0.02%)	⬆️

... and 19 files with indirect coverage changes

📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more

[MarcSkovMadsen]

UPDATE: WORKS NOW

I've tested that async and return works.

But async and yield does not seem to work. I see the below error right after uploading a csv file.

import panel as pn
import pandas as pd

agent_user="Pandas Agent"
agent_avatar="🐼"

pn.extension("perspective")

def _create_message(message):
    return pn.chat.ChatMessage(message, user="Pandas Agent", avatar="🐼")

async def callback(contents, user, instance):
    if isinstance(contents, pd.DataFrame):
        instance.active=1
        print("I was here")
        yield _create_message("You uploaded a dataframe. Ask me anything about it")
        

    yield _create_message("That is a great question. I don't know.")

chat_interface = pn.chat.ChatInterface(
    widgets=[pn.widgets.FileInput(name="Upload"), pn.widgets.TextInput(name="Message")],
    renderers=pn.pane.Perspective,
    callback=callback,
    callback_exception="verbose",
)
    
chat_interface.send("I'm your LangChain Pandas Agent!", user="Pandas Agent", avatar="🐼", respond=False)
chat_interface.servable()

[ahuang11]

Should be fixed now.

[MarcSkovMadsen]

Should be fixed now.

I can confirm its fixed.Thanks.