README.md

metadata

title: Multi Agent Finance Assistant
emoji: 🚀
colorFrom: blue
colorTo: red
sdk: gradio
sdk_version: 5.31.0
app_file: app.py
pinned: false

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

🚀 Multi-Agent Finance Assistant

A sophisticated AI-powered financial analysis system that delivers spoken market briefs through an intuitive Gradio interface. Built with multiple specialized agents and powered by Google's Gemini 2.0 Flash.

🏗️ Architecture Overview

Agent Ecosystem

┌─────────────────┐    ┌─────────────────┐    ┌─────────────────┐
│   API Agent     │    │ Scraping Agent  │    │ Retriever Agent │
│ Real-time Data  │    │ News & Filings  │    │ Vector Search   │
└─────────────────┘    └─────────────────┘    └─────────────────┘
         │                       │                       │
         └───────────────────────┼───────────────────────┘
                                 │
                    ┌─────────────────┐
                    │  Orchestrator   │
                    │   (FastAPI)     │
                    └─────────────────┘
                                 │
┌─────────────────┐    ┌─────────────────┐    ┌─────────────────┐
│ Analysis Agent  │    │ Language Agent  │    │  Voice Agent    │
│ Risk Metrics    │    │ Gemini 2.0 Flash│    │ STT/TTS Pipeline│
└─────────────────┘    └─────────────────┘    └─────────────────┘

🎯 Key Features

• 🤖 Multi-Agent Architecture: Six specialized agents working in harmony
• 🎤 Voice Interface: Speech-to-text and text-to-speech capabilities
• 📊 Real-time Data: Live market data via Yahoo Finance API
• 🔍 Smart Retrieval: Vector search with FAISS embeddings
• 🧠 Advanced AI: Powered by Google Gemini 2.0 Flash
• 📱 Modern UI: Attractive Gradio interface with dark mode support
• ☁️ Cloud Ready: Deployable on Hugging Face Spaces

🚀 Quick Start

Local Development

1. Clone the repository

git clone <your-repo-url>
cd multi-agent-finance-assistant

2. Install dependencies

pip install -r requirements.txt

3. Set environment variables

export GEMINI_API_KEY="your-gemini-api-key"
export ALPHA_VANTAGE_KEY="your-alphavantage-key"  # Optional

4. Run the application

python app.py

Hugging Face Spaces Deployment

1. Create a new Space on Hugging Face
2. Upload all files to your Space repository
3. Add secrets in Space settings:
   • GEMINI_API_KEY: Your Google AI Studio API key
4. Set Space to Gradio framework
5. Deploy and share!

📋 Use Case Example

Morning Market Brief Query:

"What's our risk exposure in Asia tech stocks today, and highlight any earnings surprises?"

AI Response:

"Today, your Asia tech allocation is 22% of AUM, up from 18% yesterday. TSMC beat estimates by 4%, Samsung missed by 2%. Regional sentiment is neutral with a cautionary tilt due to rising yields