https://github.com/itsabhishekm/stock_analyst
Agentic application which uses live stock analysis, financial metrics, and web search to help research about financial analysis of any stock in the market.
https://github.com/itsabhishekm/stock_analyst
fastapi-framework llama3 phidata-framework
Last synced: about 1 month ago
JSON representation
Agentic application which uses live stock analysis, financial metrics, and web search to help research about financial analysis of any stock in the market.
- Host: GitHub
- URL: https://github.com/itsabhishekm/stock_analyst
- Owner: itsabhishekm
- License: mit
- Created: 2025-05-30T16:28:02.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-06-03T07:15:17.000Z (about 1 year ago)
- Last Synced: 2025-06-24T13:42:41.827Z (12 months ago)
- Topics: fastapi-framework, llama3, phidata-framework
- Language: Python
- Homepage:
- Size: 8.79 KB
- Stars: 1
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Stock Analyst
An Agentic, multi-agent system that combines real-time stock analysis, financial metrics, and web search using **Phidata**, **Groq LLaMA3**, and **yFinance**. Built for investors and analysts to research about financial analysis of any stock in the market.
> This is powered by Groq’s LLaMA3 · Built with Phidata · Streamlined with FastAPI ·
---
## Features
- **Web Search Agent** – Retrieves live financial news using DuckDuckGo.
- **Finance Agent** – Provides stock fundamentals, analyst ratings, ratios, and trends.
- **Multi-Agent Collaboration** – Agents work in tandem to deliver structured insights.
- **Playground Mode** – Visual interface powered by Phidata's playground on `localhost:7777`.
---
## General Info
| Tool | Purpose |
| ----------------- | -------------------------------------- |
| **Phidata** | Agent framework for building, deploying, and monitoring AI agents |
| **Groq (LLaMA3)** | Transformer-based LLM |
| **YFinance** | Stock data: prices, ratios, indicators |
| **DuckDuckGo** | Fetches latest news and articles |
| **FastAPI** | Playground deployment support |
| **dotenv** | Secure key management |
---
## File Structure
```
Stock_Analyst/
├── financial_agent.py # AI agents
├── phidata_playground.py # Launches Phidata UI (http://localhost:7777)
├── .env # API keys
├── requirements.txt # Dependencies
├── LICENSE # Project license
└── README.md # You are here!
```
---
## Setup Instructions
### Clone the Repository
```
git clone https://github.com/itsabhishekm/Stock_Analyst.git
cd Stock_Analyst
```
### Create a Virtual Environment & Install Dependencies
```
python -m venv venv
venv\Scripts\activate
pip install -r requirements.txt
```
### Seting Up Environment Variables
Create a .env file in the root directory and past your API KEYS:
```
PHI_API_KEY="your-phidata-api-key"
GROQ_API_KEY="your-groq-api-key"
OPENAI_API_KEY="your-openai-api-key"
```
### Run Agents in CLI Mode
```
python financial_agent.py
```
This will trigger both the web search and financial agents to respond to a sample query like:
"Summarize analyst recommendations and share the latest news for NVDA"
### Launch Phidata Playground (Web UI)
```
python phidata_playground.py
```
Then login to your Phidata account, and select localhost:7777 from the endpoint list.