virgil-ai/README.md

Lolly AI

A FastAPI-based insurance AI assistant that integrates with talestorm-ai for chat capabilities and provides insurance estimation services.

Features

• Insurance Chat: AI-powered chat interface for insurance-related questions
• Insurance Estimation: Comprehensive underwriting and pricing estimation
• Integration: Seamless integration with talestorm-ai API
• Modern API: Built with FastAPI for high performance and automatic documentation

Quick Start with Docker Compose

The easiest way to run lolly-ai is using Docker Compose, which will set up both lolly-ai and its dependency talestorm-ai.

Prerequisites

• Docker and Docker Compose installed
• talestorm-ai repository cloned in the same parent directory as lolly-ai

Setup

1. Clone both repositories:

git clone <talestorm-ai-repo-url> ../talestorm-ai
git clone <lolly-ai-repo-url> lolly-ai
cd lolly-ai

2. Create a .env file with your configuration:

# Database Configuration (for talestorm-ai)
POSTGRES_USER=postgres
POSTGRES_PASSWORD=password
POSTGRES_DB=talestorm
PUBLIC_POSTGRES_PORT=5432

# talestorm-ai Configuration
PUBLIC_TALESTORM_PORT=8000
ADMIN_API_KEY=changeme-admin-key
OPENAI_API_KEY=your-openai-api-key-here

# lolly-ai Configuration
PUBLIC_LOLLY_PORT=7310
TALESTORM_API_KEY=your-talestorm-api-key-here
TALESTORM_AGENT_ID=your-talestorm-agent-id-here
INSURANCE_API_BASE_URL=https://apilolly.cyberpug.ru

# Server Configuration
HOST=0.0.0.0
PORT=7310
DEBUG=false

# CORS Configuration
CORS_ORIGINS=*

# Logging
LOG_LEVEL=INFO

3. Start the services:

docker compose up -d

4. Access the services:

• lolly-ai API: http://localhost:7310
• talestorm-ai API: http://localhost:8000
• lolly-ai docs: http://localhost:7310/docs
• talestorm-ai docs: http://localhost:8000/docs

Development with Docker Compose

For development, you can mount the source code:

docker compose up -d

The source code is automatically mounted, so changes will be reflected immediately.

Stopping the services

docker compose down

To remove volumes as well:

docker compose down -v

API Endpoints

All API endpoints are versioned under /api/v1/:

/api/v1/sessions (POST)

Create a new chat session.

Query Parameters:

• agent_id (optional): Specific agent ID to use for the session

Response:

{
  "session_id": "session-uuid"
}

/api/v1/sessions (GET)

List all available sessions.

Response:

{
  "sessions": [
    {
      "id": "session-uuid",
      "organization_id": "org-uuid",
      "agent_id": "agent-uuid",
      "created_at": "2024-01-01T00:00:00Z"
    }
  ]
}

/api/v1/sessions/{session_id} (GET)

Get details of a specific session.

Response:

{
  "id": "session-uuid",
  "organization_id": "org-uuid",
  "agent_id": "agent-uuid",
  "created_at": "2024-01-01T00:00:00Z"
}

/api/v1/agents (GET)

List available AI agents.

Response:

{
  "agents": [
    {
      "id": "agent-uuid",
      "name": "Insurance Assistant",
      "model_name": "gpt-3.5-turbo",
      "model_provider": "openai",
      "enable_rag_search": true,
      "instructions": "You are an insurance expert..."
    }
  ]
}

/api/v1/insurance_chat (POST)

Handles insurance-related chat requests.

Request Body:

{
  "message": "What does my health insurance cover?",
  "session_id": "optional-session-id"
}

Response:

{
  "session_id": "session-uuid",
  "answer": "Your health insurance covers...",
  "sources": [
    {
      "plan_name": "Cigna 1000 Classic",
      "chunk_number": 0,
      "content_chunk": "This plan covers preventive care, doctor visits, and prescription drugs..."
    }
  ],
  "history": [
    {
      "role": "user",
      "message": "What does my health insurance cover?"
    },
    {
      "role": "assistant", 
      "message": "Your health insurance covers..."
    }
  ]
}

/api/v1/estimation (POST)

Handles insurance estimation and underwriting requests.

Request Body:

{
  "uid": "application-id",
  "applicants": [
    {
      "firstName": "John",
      "dob": "15/03/1985",
      "weight": 70,
      "heightFt": 5,
      "heightIn": 10,
      "applicant": 1
    }
  ],
  "plans": [
    {
      "coverage": 1
    }
  ],
  "phq": {
    "effectiveDate": "01/01/2024",
    "medications": [],
    "conditions": [],
    "issues": []
  },
  "income": 50000,
  "address": {}
}

Response:

{
  "uid": "application-id",
  "status": "submitted",
  "data": {
    "results": [...],
    "combined": {
      "tier": 2.0,
      "total_price": 243,
      "dtq": false,
      "message": "Final assigned tier is 2.0"
    }
  },
  "external": {...}
}