app.py

import os
from slack_bolt import App, Assistant, BoltContext, Say, SetSuggestedPrompts, SetStatus
from slack_bolt.adapter.socket_mode import SocketModeHandler
import logging 
from slack_sdk import WebClient
from slack_sdk.errors import SlackApiError
from transformers import (
    load_tool,
    ReactCodeAgent,
    HfApiEngine,
    stream_to_gradio,
)

logging.basicConfig(level=logging.INFO)

logging.info('App loading again..\n\n')

# Import tool from Hub
hf_token = os.environ.get("HF_TOKEN")

llm_engine = HfApiEngine(model="Qwen/Qwen2.5-72B-Instruct", token=hf_token)

# Initialize the agent with the image generation tool
agent = ReactCodeAgent(
    tools=[], llm_engine=llm_engine, additional_authorized_imports=['requests', 'bs4', "html5lib"], add_base_tools=True
)

logging.info('App initialized \n')

# Initializes your app with your bot token and socket mode handler
app = App(token=os.environ.get("SLACK_BOT_TOKEN"))

assistant = Assistant()

# This listener is invoked when a human user opened an assistant thread
@assistant.thread_started
def start_assistant_thread(say: Say, set_suggested_prompts: SetSuggestedPrompts):
    # Send the first reply to the human who started chat with your app's assistant bot
    say(":wave: Hi, how can I help you today?")

    # Setting suggested prompts is optional
    set_suggested_prompts(
        prompts=[
            # If the suggested prompt is long, you can use {"title": "short one to display", "message": "full prompt"} instead
           {"title" : "Summarize latest post from Slack engineering blog", 
            "message": "Read blog post https://slack.engineering/slack-audit-logs-and-anomalies/ and summarize it in 200 words"}
        ],
    )

# This listener is invoked when the human user sends a reply in the assistant thread
@assistant.user_message
def respond_in_assistant_thread(
    payload: dict,
    logger: logging.Logger,
    context: BoltContext,
    set_status: SetStatus,
    client: WebClient,
    say: Say,
):
    try:
        # Tell the human user the assistant bot acknowledges the request and is working on it
        set_status("is hard at work...")

        query = payload['blocks'][0]['elements'][0]['elements'][0]['text']
        
        # Pass the latest prompt and chat history to the LLM (call_llm is your own code)
        agent_gen = agent.run(task=query, stream=True, url="https://slack.engineering/slack-audit-logs-and-anomalies/")

        for val in agent_gen:
            if 'final_answer' in val:
                say(f":tada: *Final Answer* : {val['final_answer']}")
            elif 'rationale' in val:
                say(f":thinking_face: {val['rationale']}")

    except Exception as e:
        logger.exception(f"Failed to respond to an inquiry: {e}")
        # Don't forget sending a message telling the error
        # Without this, the status 'is typing...' won't be cleared, therefore the end-user is unable to continue the chat
        say(f":warning: Sorry, something went wrong during processing your request (error: {e})")

# Enable this assistant middleware in your Bolt app
app.use(assistant)

# # Start your app
# if __name__ == "__main__":
#     logging.info('Listening on socket mode \n')
#     SocketModeHandler(app, os.environ["SLACK_APP_TOKEN"]).start()