Chatbots

Create AI chatbots with customizable personalities and RAG integration.

What You'll Learn

• Overview - What chatbots are and when to use them
• Creating Chatbots - Configure chatbot settings
• Chatting - Interact with your chatbots
• Managing - Update and maintain chatbots
• Examples - Integration examples in multiple languages

Overview

Chatbots are pre-configured AI assistants with:

• Custom personalities - Define system prompts and behavior
• RAG integration - Connect to your document knowledge base
• Model selection - Choose appropriate LLM models
• Conversation memory - Track message history
• Fallback responses - Handle unknown queries

Chatbots vs. Raw LLM API

Feature	Chatbots	Raw LLM API
Personality	Built-in system prompt	Manual system message each request
Conversation memory	Automatic	Manual message tracking
RAG access	One-click enable	Manual document search and context injection
Multi-tenancy	Multiple bots, isolated	Single configuration

Use Cases

Use Case	Recommended Approach
Customer support	Chatbot with RAG from documentation
Internal Q&A	Chatbot with company knowledge base
General assistant	Simple chatbot with personality
Domain expert	Chatbot with specialized system prompt

Next Steps

• Create Your First Chatbot - Set up a chatbot
• RAG Documentation - Build your knowledge base first
• Examples - See how to integrate

Quick Example

Create a customer support bot with RAG:

import requests

# Create chatbot
create_response = requests.post(
    "http://localhost/api/v1/chatbot/create",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "name": "Support Bot",
        "model": "gpt-3.5-turbo",
        "system_prompt": "You are a helpful customer support agent.",
        "use_rag": True,
        "rag_collection": "docs_collection",
        "rag_top_k": 5
    }
)

chatbot_id = create_response.json()["id"]

# Chat with it
chat_response = requests.post(
    "http://localhost/api/v1/chatbot/chat",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "chatbot_id": chatbot_id,
        "message": "How do I reset my password?"
    }
)

print(chat_response.json()["response"])