django-ai-chatbot 0.1.0

AI chatbot assistant for Django/DRF that analyzes your project models and responds to queries

Django AI Chatbot Assistant

An intelligent AI chatbot package for Django/DRF that analyzes your project's models and data to provide context-aware responses. Integrates with HuggingFace LLMs and optional Tavily web search.

Features

• 🤖 HuggingFace Integration: Use any HuggingFace model for responses
• 📊 Auto Model Discovery: Automatically introspects Django models and fields
• 🌐 Web Search: Optional Tavily API integration for current web data
• ⚙️ Easy Configuration: Simple Django settings integration
• 🔒 Model Filtering: Control which models the chatbot can access

Installation

pip install django-ai-chatbot

Quick Start

1. Add to Django Settings

# settings.py

INSTALLED_APPS = [
    # ... other apps
    'ai_chatbot',
]

# Required: HuggingFace Configuration
AI_CHATBOT_HF_API_KEY = 'your-huggingface-api-key'
AI_CHATBOT_HF_MODEL = 'mistralai/Mistral-7B-Instruct-v0.2'  # Optional, this is default

# Optional: Tavily Web Search
AI_CHATBOT_TAVILY_API_KEY = 'your-tavily-api-key'  # Optional

# Optional: Restrict which models the chatbot can access
AI_CHATBOT_ALLOWED_MODELS = [
    'myapp.User',
    'myapp.Product',
    'blog.Post',
]  # If empty or not set, all models are accessible

2. Use in Your Code

from ai_chatbot import AIChatbot

# Initialize chatbot
chatbot = AIChatbot()

# Ask a question about your models
response = chatbot.ask("What fields does the User model have?")
print(response)

# Use web search for current information
response = chatbot.ask(
    "What are the latest trends in Django development?",
    use_web_search=True
)
print(response)

# Customize generation parameters
response = chatbot.ask(
    "Explain the Product model structure",
    max_tokens=1000,
    temperature=0.5
)

3. Example in Django View

from django.http import JsonResponse
from ai_chatbot import AIChatbot

def chatbot_view(request):
    query = request.GET.get('query', '')
    use_web = request.GET.get('web_search', 'false').lower() == 'true'
    
    chatbot = AIChatbot()
    response = chatbot.ask(query, use_web_search=use_web)
    
    return JsonResponse({'response': response})

4. Example in DRF ViewSet

from rest_framework.decorators import action
from rest_framework.response import Response
from rest_framework import viewsets
from ai_chatbot import AIChatbot

class ChatbotViewSet(viewsets.ViewSet):
    @action(detail=False, methods=['post'])
    def ask(self, request):
        query = request.data.get('query')
        use_web = request.data.get('use_web_search', False)
        
        chatbot = AIChatbot()
        response = chatbot.ask(query, use_web_search=use_web)
        
        return Response({'response': response})

Configuration Options

Setting	Required	Default	Description
AI_CHATBOT_HF_API_KEY	Yes	None	Your HuggingFace API key
AI_CHATBOT_HF_MODEL	No	mistralai/Mistral-7B-Instruct-v0.2	HuggingFace model to use
AI_CHATBOT_TAVILY_API_KEY	No	None	Tavily API key for web search
AI_CHATBOT_ALLOWED_MODELS	No	[] (all models)	List of models to expose (format: app.Model)

API Reference

AIChatbot.ask()

chatbot.ask(
    query: str,
    use_web_search: bool = False,
    max_tokens: int = 500,
    temperature: float = 0.7
) -> str

Parameters:

• query: The user's question
• use_web_search: Enable Tavily web search
• max_tokens: Maximum tokens in response
• temperature: LLM temperature (0.0-1.0)

Returns: Generated response string

How It Works

1. Model Introspection: Automatically discovers all Django models and their fields
2. Context Building: Creates a schema context from your models
3. Web Search (optional): Fetches current web data via Tavily
4. LLM Generation: Sends context + query to HuggingFace model
5. Response: Returns AI-generated answer based on your project data

Requirements

• Python >= 3.8
• Django >= 3.2
• huggingface-hub >= 0.19.0
• requests >= 2.31.0

License

MIT License - see LICENSE file for details

Contributing

Contributions welcome! Please open an issue or submit a PR.

Support

For issues and questions: https://github.com/hitenjoshi/django-ai-chatbot/issues