Options Analytics Agent Langgraph

# Options Analytics Agent with LangGraph

> Skill by [ara.so](https://ara.so) — Data Skills collection.

A sophisticated LangGraph-based agent that automates financial options analysis with real-time data from Polygon.io, smart caching via ChromaDB, persistent memory, and professional-grade analysis. Built for creating intelligent trading assistants with RAG capabilities and microservice architecture.

## What It Does

This project provides a complete AI agent system for:
- **Real-time options data retrieval** from Polygon.io with intelligent caching
- **RAG-powered knowledge base** using ChromaDB for semantic search
- **Persistent conversation memory** across sessions via SQLite
- **Professional options analysis** with Greeks, sentiment, and anomaly detection
- **Multi-format exports** (CSV, charts, reports)
- **LangGraph orchestration** for multi-agent workflows
- **FastAPI microservice** deployment

## Installation

### Prerequisites

```bash
# Python 3.10+
python --version

# Create virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
```

### Install Dependencies

```bash
pip install -r requirements.txt
```

**Key dependencies:**
```
langchain>=0.3.0
langgraph>=0.2.45
langchain-openai>=0.2.6
langchain-chroma>=0.1.4
chromadb>=0.5.20
fastapi>=0.115.5
uvicorn>=0.32.1
pandas>=2.2.3
matplotlib>=3.9.2
tavily-python>=0.5.0
```

### Environment Configuration

Create `.env` file in project root:

```bash
# Required
OPENAI_API_KEY=your_openai_api_key
POLYGON_API_KEY=your_polygon_io_api_key

# Optional
TAVILY_API_KEY=your_tavily_api_key  # For web search
LANGCHAIN_API_KEY=your_langchain_api_key  # For tracing
LANGCHAIN_TRACING_V2=true
```

### Verify Installation

```python
# Test import
from agent_main import create_agent_workflow
from config.settings import validate_api_keys

# Validate API keys
validate_api_keys()
print("✓ Installation successful")
```

## Project Structure

```
project/
├── agent_main.py              # Main agent entry point
├── config/settings.py         # Configuration management
├── tools/
│   ├── search/               # Options search tools
│   ├── export/               # Data export tools
│   └── analysis/             # Analysis tools
├── rag/                      # RAG knowledge base
├── monitoring/               # Performance tracking
└── microservice/             # FastAPI deployment
```

## Core Usage

### Basic Agent Interaction

```python
from agent_main import create_agent_workflow
from langchain_core.messages import HumanMessage

# Create agent
workflow = create_agent_workflow()
app = workflow.compile()

# Simple query
config = {"configurable": {"thread_id": "session_1"}}
query = "Search for AAPL options expiring this week"

result = app.invoke(
    {"messages": [HumanMessage(content=query)]},
    config=config
)

print(result["messages"][-1].content)
```

### Interactive Chat Loop

```python
from agent_main import create_agent_workflow
from langchain_core.messages import HumanMessage

def chat():
    workflow = create_agent_workflow()
    app = workflow.compile()
    session_id = "user_session_1"
    
    print("Options Analytics Agent (type 'exit' to quit)")
    
    while True:
        user_input = input("\nYou: ").strip()
        if user_input.lower() in ['exit', 'quit']:
            break
            
        config = {"configurable": {"thread_id": session_id}}
        result = app.invoke(