Introduction: Bring Qwen3 Into Your Team Chats

What if your team could chat with a powerful LLM directly from Slack or Discord?

With Qwen3 models, you can create:

• Private AI assistants

• Company knowledge bots

• Workflow automation agents

This guide shows you how to deploy a Qwen3-powered chatbot into Slack or Discord, hosted locally or in the cloud.

---

1. Prerequisites

Optional: Use ngrok or Cloudflare Tunnel for public access.

---

2. Deploy Qwen3 Model with vLLM

Use Qwen/Qwen1.5-7B-Chat or Qwen1.5-14B-Chat.

bash
                           
pip install vllm

python -m vllm.entrypoints.openai.api_server \
  --model Qwen/Qwen1.5-7B-Chat \
  --port 8000

This serves the model on an OpenAI-compatible endpoint.

---

3. Slack Bot Integration

✅ Step-by-Step

1. Go to api.slack.com/apps

2. Create a new app → Enable bot permissions

3. Add chat:write, app_mentions:read

4. Install app to your workspace → Get bot token

Python Bot Code (Slack)

python
                           
from slack_sdk import WebClient
from slack_sdk.rtm_v2 import RTMClient
import openai

openai.api_key = "none"
openai.api_base = "http://localhost:8000"

slack_bot_token = "xoxb-..."  # Your token
client = WebClient(token=slack_bot_token)
rtm = RTMClient(token=slack_bot_token)

@rtm.on("message")
def handle_msg(event_data):
    text = event_data["data"].get("text", "")
    channel = event_data["data"]["channel"]
    
    if "<@your_bot_id>" in text:
        response = openai.ChatCompletion.create(
            model="Qwen1.5-7B-Chat",
            messages=[
                {"role": "system", "content": "You are a helpful assistant."},
                {"role": "user", "content": text}
            ]
        )
        reply = response["choices"][0]["message"]["content"]
        client.chat_postMessage(channel=channel, text=reply)

rtm.start()

---

4. Discord Bot Integration

Step-by-Step

1. Go to discord.com/developers

2. Create a new bot app

3. Get bot token and invite bot to your server

Python Bot Code (Discord)

python
                           
import discord
import openai

openai.api_key = "none"
openai.api_base = "http://localhost:8000"

intents = discord.Intents.default()
intents.message_content = True
client = discord.Client(intents=intents)

@client.event
async def on_ready():
    print(f'Bot connected as {client.user}')

@client.event
async def on_message(message):
    if message.author == client.user:
        return

    if client.user.mention in message.content:
        response = openai.ChatCompletion.create(
            model="Qwen1.5-7B-Chat",
            messages=[
                {"role": "system", "content": "You are a helpful assistant."},
                {"role": "user", "content": message.content}
            ]
        )
        reply = response["choices"][0]["message"]["content"]
        await message.channel.send(reply)

client.run("YOUR_DISCORD_BOT_TOKEN")

---

Customize: Add Slash Commands or Memory

You can also add tools like search, weather, or databases.

---

Security Tips

• Store tokens securely using .env or secrets manager

• Restrict bot access to selected channels

• Log usage for debugging or audit

---

Conclusion: Qwen3 in Your Chat Stack

With this setup:

• Your team can ask questions in Slack/Discord

• Data stays local with Qwen3

• Replies match your tone and domain

Qwen3 brings the power of open-source LLMs into everyday workflows—securely and cost-effectively.

---

Resources

• Qwen Models on Hugging Face

• Slack API Docs

• Discord Bot Docs

• vLLM for Fast Inference