Skip to content

Simple Chatbot Example

A basic conversational bot demonstrating core dataknobs-bots functionality.

Overview

This example shows how to:

  • Create a basic DynaBot from configuration
  • Use Ollama as the LLM provider
  • Set up in-memory conversation storage
  • Have a simple conversation with the bot

Prerequisites

# Install Ollama: https://ollama.ai/

# Pull the required model
ollama pull gemma3:1b

# Install dataknobs-bots
pip install dataknobs-bots

Key Concepts

Configuration

The bot is configured entirely through a dictionary:

config = {
    "llm": {
        "provider": "ollama",  # Use Ollama for local inference
        "model": "gemma3:1b",  # Lightweight model
        "temperature": 0.7,
        "max_tokens": 500
    },
    "conversation_storage": {
        "backend": "memory"  # Store conversations in memory
    },
    "prompts": {
        "friendly_assistant": "You are a friendly and helpful AI assistant."
    },
    "system_prompt": {
        "name": "friendly_assistant"
    }
}

Bot Context

Each conversation needs a context that identifies:

  • conversation_id - Unique ID for this conversation
  • client_id - Tenant/application identifier
  • user_id - User identifier (optional)
context = BotContext(
    conversation_id="simple-chat-001",
    client_id="example-client",
    user_id="demo-user"
)

Chatting

The chat() method sends a message and returns a response:

response = await bot.chat(
    message="Hello! What can you help me with?",
    context=context
)

Complete Code

01_simple_chatbot.py
"""Simple chatbot example.

This example demonstrates:
- Basic DynaBot configuration
- Using Ollama as the LLM provider
- In-memory conversation storage
- Simple message exchange

Required Ollama model:
    ollama pull gemma3:1b
"""

import asyncio

from dataknobs_bots import BotContext, DynaBot


async def main():
    """Run a simple chatbot conversation."""
    print("=" * 60)
    print("Simple Chatbot Example")
    print("=" * 60)
    print()
    print("This example shows a basic chatbot with no memory.")
    print("Required: ollama pull gemma3:1b")
    print()

    # Configuration for a simple chatbot
    config = {
        "llm": {
            "provider": "ollama",
            "model": "gemma3:1b",
            "temperature": 0.7,
            "max_tokens": 500,
        },
        "conversation_storage": {
            "backend": "memory",
        },
        "prompts": {
            "friendly_assistant": "You are a friendly and helpful AI assistant. "
            "Keep your responses concise and clear."
        },
        "system_prompt": {
            "name": "friendly_assistant",
        },
    }

    print("Creating bot from configuration...")
    bot = await DynaBot.from_config(config)
    print("✓ Bot created successfully")
    print()

    # Create context for this conversation
    context = BotContext(
        conversation_id="simple-chat-001",
        client_id="example-client",
        user_id="demo-user",
    )

    # Example conversation
    messages = [
        "Hello! What can you help me with?",
        "Tell me a fun fact about Python programming.",
        "That's interesting! What makes Python so popular?",
    ]

    for i, user_message in enumerate(messages, 1):
        print(f"User: {user_message}")

        response = await bot.chat(
            message=user_message,
            context=context,
        )

        print(f"Bot: {response}")
        print()

        # Add a small delay between messages
        if i < len(messages):
            await asyncio.sleep(1)

    print("=" * 60)
    print("Conversation complete!")
    print()
    print("Note: This bot has no memory between conversations.")
    print("Each new conversation starts fresh.")


if __name__ == "__main__":
    asyncio.run(main())

Running the Example

# Navigate to the bots package
cd packages/bots

# Run the example
python examples/01_simple_chatbot.py

Expected Output

============================================================
Simple Chatbot Example
============================================================

This example shows a basic chatbot with no memory.
Required: ollama pull gemma3:1b

Creating bot from configuration...
✓ Bot created successfully

User: Hello! What can you help me with?
Bot: Hi! I'm here to assist you with various tasks...

User: Tell me a fun fact about Python programming.
Bot: Python was named after Monty Python's Flying Circus...

User: That's interesting! What makes Python so popular?
Bot: Python's popularity comes from its simplicity...

============================================================
Conversation complete!

Note: This bot has no memory between conversations.
Each new conversation starts fresh.

What's Next?

This example has no memory - the bot doesn't remember previous messages in the conversation.

To add memory, see the Memory Chatbot Example.

Key Takeaways

  1. ✅ Configuration-First - Bot behavior defined entirely through configuration
  2. ✅ Async/Await - All operations are asynchronous
  3. ✅ Context Isolation - Each conversation has its own context
  4. ✅ Local LLMs - No API keys needed with Ollama
  5. ⚠️ No Memory - Bot doesn't remember conversation history

Customization

Change the Model

"llm": {
    "provider": "ollama",
    "model": "llama3.1:8b",  # Use a different model
}

Adjust Response Length

"llm": {
    "provider": "ollama",
    "model": "gemma3:1b",
    "max_tokens": 1000,  # Longer responses
}

Change System Prompt

Using a template name:

"prompts": {
    "custom_assistant": "You are an expert in Python programming."
},
"system_prompt": {
    "name": "custom_assistant"
}

Using inline content directly:

# Multi-line prompts can be specified directly without a prompts library
"system_prompt": """You are an expert Python programming assistant.

Key responsibilities:
- Help users write clean, idiomatic Python code
- Explain Python concepts clearly
- Suggest best practices and design patterns
"""

Or as a dict with content:

"system_prompt": {
    "content": "You are an expert in Python programming. Help users write clean code."
}