Examples¶

Complete working examples demonstrating dataknobs-bots features.

Available Examples¶

Example	Description	Key Features
Simple Chatbot	Basic conversational bot	LLM integration, basic configuration
Memory Chatbot	Bot with conversation memory	Buffer memory, context management
RAG Chatbot	Knowledge base integration	Document loading, vector search, RAG
ReAct Agent	Tool-using agent	Custom tools, ReAct reasoning
Wizard Bot	Guided conversational wizard	FSM stages, validation, data collection
Multi-Tenant Bot	Multiple clients setup	Bot registry, client isolation
Config-Based Tools	Configuration-driven tools	Tool configuration, XRef system

Running Examples¶

All examples use Ollama for local LLM inference. Follow these steps:

1. Install Ollama¶

Visit https://ollama.ai/ and install Ollama for your platform.

2. Pull Required Models¶

# For basic chatbot examples
ollama pull gemma3:1b

# For agent examples
ollama pull phi3:mini

# For RAG examples (embedding model)
ollama pull nomic-embed-text

3. Install Dependencies¶

# Basic installation
pip install dataknobs-bots

# With FAISS for RAG examples
pip install dataknobs-bots[faiss]

4. Run an Example¶

# Clone the repository
git clone https://github.com/kbs-labs/dataknobs.git
cd dataknobs/packages/bots

# Run an example
python examples/01_simple_chatbot.py

Example Categories¶

Getting Started¶

Perfect for beginners learning dataknobs-bots:

Simple Chatbot - Your first bot
Memory Chatbot - Adding memory

Advanced Features¶

For users building production bots:

RAG Chatbot - Knowledge retrieval
ReAct Agent - Tool integration
Wizard Bot - Guided conversational flows
Multi-Tenant Bot - Multi-tenancy

Configuration Patterns¶

Learn configuration best practices:

Config-Based Tools - Tool configuration

Prerequisites¶

Required¶

Python 3.12+
dataknobs-bots package
Ollama (for local LLM)

Optional¶

FAISS (pip install faiss-cpu) - For RAG examples
PostgreSQL - For production storage examples

Common Patterns¶

Basic Bot Setup¶

from dataknobs_bots import DynaBot, BotContext

config = {
    "llm": {"provider": "ollama", "model": "gemma3:1b"},
    "conversation_storage": {"backend": "memory"}
}

bot = await DynaBot.from_config(config)
context = BotContext(
    conversation_id="example-001",
    client_id="demo"
)

response = await bot.chat("Hello!", context)

Adding Memory¶

config = {
    "llm": {"provider": "ollama", "model": "gemma3:1b"},
    "conversation_storage": {"backend": "memory"},
    "memory": {
        "type": "buffer",
        "max_messages": 10
    }
}

Enabling RAG¶

config = {
    "llm": {"provider": "ollama", "model": "gemma3:1b"},
    "conversation_storage": {"backend": "memory"},
    "knowledge_base": {
        "enabled": True,
        "documents_path": "./docs",
        "vector_store": {"backend": "faiss", "dimension": 384}
    }
}

Adding Tools¶

config = {
    "llm": {"provider": "ollama", "model": "phi3:mini"},
    "conversation_storage": {"backend": "memory"},
    "reasoning": {"strategy": "react"},
    "tools": [
        {"class": "my_tools.CalculatorTool", "params": {}}
    ]
}

Tips¶

Start with Simple Chatbot - Build foundation understanding
Use Ollama - No API keys needed for development
Enable Verbose Mode - Set verbose: True in reasoning config
Check Logs - Enable logging for debugging
Read the Code - All examples are well-commented

Troubleshooting¶

Model Not Found¶

Error: model 'gemma3:1b' not found

Solution: Pull the model first:

ollama pull gemma3:1b

Connection Error¶

Error: Failed to connect to Ollama

Solution: Ensure Ollama is running:

ollama serve

Import Error¶

ModuleNotFoundError: No module named 'dataknobs_bots'

Solution: Install the package:

pip install dataknobs-bots

Next Steps¶

After running the examples:

Read the User Guide for in-depth tutorials
Explore Configuration Reference for all options
Learn Tool Development to create custom tools
Check Architecture for system design

Source Code¶

All example source code is available in the GitHub repository:

https://github.com/kbs-labs/dataknobs/tree/main/packages/bots/examples