A powerful AI-powered application that combines web search and financial analysis capabilities using Groq LLM and Phi framework.
- Web Search Agent: Performs comprehensive web searches and generates NYT-style articles
- Finance Agent: Analyzes stock market data and provides financial insights
- Multi-Agent System: Combines both agents for complex queries
- Interactive Playground: Web interface to interact with the agents
Make sure you have Python installed and the following packages:
- pandas
- cassandra-driver
- phidata
- python-dotenv
- yfinance
- duckduckgo-search
- fastapi
- uvicorn
- groq
- os-sys
- dotenv
- python-docx (optional , if you face error)
- Clone the repository:
git clone https://github.com/nottarun7/Finance_Agent_Using_Phidata.git
- Install dependencies:
pip install -r requirements.txt
- Create a
.env
file in the root directory with your API keys:
GROQ_API_KEY="your_groq_api_key"
PHI_API_KEY="your_phi_api_key"
- Usage
python playground.py
This will start a local server with the playground interface where you can interact with both agents.
from agent import web_search_agent, finance_agent, multi_agent
web_search_agent.print_response("Your query here")
finance_agent.print_response("Get NVIDIA stock analysis")
multi_agent.print_response("Summarize analyst recommendation and share the latest news for NVIDIA")
- Searches for top 5 relevant links
- Extracts and analyzes article content
- Generates NYT-style articles
- Includes source citations
- Real-time stock price information
- Analyst recommendations
- Stock fundamentals analysis
- Data presented in markdown tables
This project is licensed under the MIT License - see the LICENSE file for details.
Never commit your API keys to version control. Always use environment variables or a secure secrets management system.