Spaces:
Sleeping
Sleeping
| title: Financial & Market AI Assistant | |
| emoji: π | |
| colorFrom: blue | |
| colorTo: green | |
| sdk: gradio | |
| sdk_version: 6.0.1 | |
| app_file: app.py | |
| pinned: false | |
| license: mit | |
| # Financial & Market AI Assistant | |
| A streamlined Gradio-based AI assistant that integrates **SEC financial data** and **real-time market information** through two MCP servers. | |
| ## β¨ Features | |
| - π€ **Intelligent AI Assistant**: Powered by **Qwen/Qwen2.5-72B-Instruct:novita** (supports tool calling) | |
| - π **Dual Data Sources**: | |
| - **SEC Financial Reports**: Official 10-K/10-Q data (revenue, earnings, cash flow, etc.) | |
| - **Market & Stock Data**: Real-time stock quotes and news (powered by Finnhub) | |
| - π οΈ **Automatic MCP Tool Calling**: AI automatically uses 6 tools across 2 MCP servers | |
| - π¬ **Natural Language Interface**: Just ask questions naturally | |
| - π **Smart Analysis**: AI provides data-driven insights, not just raw data | |
| ## π Quick Start | |
| ### Prerequisites | |
| - Python 3.9+ | |
| - Hugging Face API token (get one at https://huggingface.co/settings/tokens) | |
| ### Installation | |
| 1. Clone the repository | |
| 2. Install dependencies: `pip install -r requirements.txt` | |
| 3. Create a `.env` file with your HF token: | |
| ``` | |
| HF_TOKEN=your_token_here | |
| ``` | |
| 4. Run: `python app.py` | |
| ### Usage | |
| Just start asking questions! The AI will automatically fetch data from the right source: | |
| **Financial Questions:** | |
| - "What's Apple's latest revenue and profit?" | |
| - "Show me NVIDIA's 3-year financial trends" | |
| - "Compare Microsoft's latest earnings with its operating expenses" | |
| **Market Questions:** | |
| - "How is Tesla's stock performing today?" | |
| - "Get the latest market news about crypto" | |
| - "What's the current price of AAPL?" | |
| **Combined Analysis:** | |
| - "Compare Microsoft's latest earnings with its current stock price" | |
| - "Show me Amazon's financial performance and recent news" | |
| ## π οΈ Available MCP Tools | |
| **SEC Financial Reports MCP:** | |
| 1. `advanced_search_company` - Find US companies by name/ticker | |
| 2. `get_latest_financial_data` - Get latest 10-K/10-Q data | |
| 3. `extract_financial_metrics` - Get 3-year or 5-year trends | |
| **Market & Stock Data MCP (Finnhub):** | |
| 4. `get_quote` - Real-time stock price, volume, change | |
| 5. `get_market_news` - Latest market news (general/forex/crypto/merger) | |
| 6. `get_company_news` - Company-specific news with date range | |
| ## πΎ Data Sources | |
| - **SEC Financial Data**: https://huggingface.co/spaces/JC321/EasyReportDateMCP | |
| - **Market & Stock Data**: https://huggingface.co/spaces/JC321/MarketandStockMCP (Finnhub API) | |
| ## π οΈ Technology Stack | |
| - **Frontend**: Gradio 6.0.1 (ChatInterface) | |
| - **AI Model**: Qwen/Qwen2.5-72B-Instruct:novita (Hugging Face Inference API) | |
| - **MCP Protocol**: 2 MCP Servers (HTTP + SSE transports) | |
| - **Data Sources**: | |
| - SEC EDGAR (official financial filings) | |
| - Finnhub API (real-time market data) | |
| ## π‘ Tips | |
| - Ask about **financials** (revenue, profit) or **market data** (stock price, news) | |
| - AI understands context and can combine data from both sources | |
| - Both company names and ticker symbols work ("Apple" or "AAPL") | |
| - The AI shows which tools it used for transparency | |
| ## π Supported Companies | |
| All US-listed companies in SEC EDGAR database, including: | |
| - Tech: Apple, Microsoft, NVIDIA, Google, Meta, Amazon, Tesla | |
| - Finance: JPMorgan, Bank of America, Goldman Sachs | |
| - Retail: Walmart, Target, Costco | |
| - And many more... | |