Hugging Face's logo

Spaces:
krinya
/
smart_routing_with_render_example
Sleeping

App Files Community
smart_routing_with_render_example / README.md
krinya's picture
krinya
Fix broken links in README and app.py for live demo and documentation
12e3d57
preview code
|
Raw
History Blame Contribute Delete
2.86 kB
metadata 
title: AI Chatbot with Smart Routing
emoji: πŸ€–
colorFrom: blue
colorTo: purple
sdk: docker
pinned: false
license: mit
app_port: 7860

πŸ€– Financial AI Chatbot with Smart Routing & RAG

A demo GenAI app that demonstrates smart routing using LangChain

πŸš€ Try It Live

🎯 What This Demonstrates

This project shows how to create a complete GenAI product:

1. 🧠 Smart Routing with LangChain

Intelligently routes financial questions about 5 major companies (Apple, Google, Amazon, Tesla, Intel):

  • πŸ” FAQ Route: Quick facts (CEO names, founding dates)
  • πŸ“š RAG Route: Financial data from 2024 annual reports (revenue, profits)
  • 🧠 LLM Route: General explanations and financial concepts

2. πŸ“Š RAG Implementation

  • Vector Storage: ChromaDB with processed financial documents (full annual reports)
  • Retrieval System: Semantic search for relevant information
  • Smart Fallbacks: Multiple sources with quality scoring

3. πŸ—οΈ Production Architecture

  • Backend: Python FastAPI with LangChain, deployed on Render
  • Frontend: Gradio UI deployed on Hugging Face Spaces
  • Separation: Backend API + Frontend UI for scalability

πŸ› οΈ How This Shows GenAI Product Development

Complete workflow: Backend β†’ Deploy β†’ Frontend

  1. Write Backend (Python + LangChain)

    • FastAPI with smart routing logic
    • RAG pipeline with vector storage
    • Deploy on Render cloud platform

  2. Create Frontend (Gradio + Hugging Face)

    • Interactive chat interface
    • Real-time routing insights
    • Deploy on Hugging Face Spaces

  3. Connect & Scale

    • Backend API serves multiple frontends
    • Docker containerization
    • Production-ready architecture

πŸ”§ Tech Stack

  • AI: OpenAI GPT-4o-mini + LangChain orchestration
  • Backend: Python FastAPI deployed on Render
  • Frontend: Gradio deployed on Hugging Face Spaces
  • Storage: ChromaDB vector database
  • Data: 2024 financial reports (Apple, Google, Amazon, Tesla, Intel)

οΏ½ Example Queries

Try these in the live demo:

  • "Who is the CEO of Tesla?" β†’ FAQ route
  • "What was Apple's revenue in 2024?" β†’ RAG route
  • "How do you calculate P/E ratio?" β†’ LLM route

🎯 Key Learning: This demonstrates the complete GenAI development stack from data processing to production deployment!