# Discord

4 Items are Needed for this tutorial:

1. Discord Bot Token
2. API Key from Stammer.ai
3. Chatbot UUID from Stammer.ai
4. (Optional) White Label URL from Stammer.ai

{% embed url="<https://youtu.be/7m4nf-1A2kA>" %}

### Instructions

1\. Set up Discord account and server:\
&#x20;  \- Create a Discord account (if you don’t have one)\
&#x20;  \- Create a new server or use an existing one

2\. Create Discord application:\
&#x20;  \- Go to <https://discord.com/developers/applications>\
&#x20;  \- Click “New Application”\
&#x20;  \- Name your application\
&#x20;  \- Go to “Bot” tab and click “Add Bot”

3\. Get bot token:\
&#x20;  \- In “Bot” tab, find token section\
&#x20;  \- Click “Copy” to copy bot token to paste into Replit\
&#x20;  \- Keep this token secret!

4\. Invite bot to server:\
&#x20;  \- Go to “OAuth2" tab\
&#x20;  \- In “Scopes” section, select “bot”\
&#x20;  \- Choose desired permissions\
&#x20;  \- Copy generated URL and open in new tab\
&#x20;  \- Select server and authorize bot on the channels you want it to access

5\. Create New Replit:\
&#x20;  \- Create new Python file\
&#x20;  \- Paste in the template code\
&#x20;  \- Paste in the Discord bot code on line 68\
&#x20;  \- Update the Stammer Authorization key on line 10\
&#x20;  \- Update the chatbot UUID on line 11\
&#x20;  \- (Optional) Update the URL to be your white label API URL on line 14

6\. Running the AI Agent:\
&#x20;  \- Run the code in Replit\
&#x20;  \- Go to your Discord channel and ask your bot a question by tagging its name

**Code for Replit:**

```python
import discord
from discord.ext import commands
import requests

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

bot = commands.Bot(command_prefix='!', intents=intents)

stoken = 'YOUR-STAMMER-KEY'
chatbot_uuid = 'SOME_UUID'

def send_message_to_ai_agent(message):
    url = "https://app.stammer.ai/en/chatbot/api/v1/message/"
    headers = {
        'Authorization': f'Token {stoken}',
        'Content-Type': 'application/json'
    }
    data = {
        "chatbot_uuid": chatbot_uuid,
        "query": message,
        "user_key": "discord_user",  # You can change this if needed
    }

    try:
        response = requests.post(url, headers=headers, json=data)
        response.raise_for_status()

        if response.status_code == 200:
            return response.json().get('data', {}).get('answer', 'No response from AI agent.')
        else:
            return f"Unexpected response: {response.text}"

    except requests.exceptions.RequestException as e:
        return f"Error: {str(e)}"

@bot.event
async def on_ready():
    print(f'{bot.user} has connected to Discord!')

@bot.event
async def on_message(message):
    # Ignore messages sent by the bot itself
    if message.author == bot.user:
        return

    # Check if the bot is mentioned in the message
    if bot.user.mentioned_in(message):
        # Get the content of the message without the bot mention
        content = message.content.replace(f'<@!{bot.user.id}>', '').strip()
        content = content.replace(f'<@{bot.user.id}>', '').strip()

        if content:
            # Send the message to the AI agent and get the response
            ai_response = send_message_to_ai_agent(content)
            await message.channel.send(ai_response)
        else:
            await message.channel.send("You mentioned me, but didn't say anything!")

    # Process commands if any
    await bot.process_commands(message)

@bot.command(name='hello')
async def hello(ctx):
    await ctx.send('Hello World!')

# Replace 'YOUR_BOT_TOKEN' with your actual bot token
bot.run('YOUR_DISCORD_BOT_TOKEN')
```


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.stammer.ai/stammer.ai-docs/chat-ai-agents/integrations/discord.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.