LuminaCRM HCP Module - AI-First Log Interaction Screen

This project is a Customer Relationship Management (CRM) module tailored for Healthcare Professionals (HCP) sales representatives in the life sciences sector. It features a modern, premium Log Interaction Screen offering representatives the ability to log visits conversationally using an AI chat agent or via a traditional structured form, with instant real-time synchronization between the two.

🚀 Features

• Structured Interaction Logger: Comprehensive form capture including date/time, attendees, topics, sentiment selector, materials shared, and sample distribution widgets.
• AI Conversational Assistant: Conversational agent powered by LangGraph & Groq (llama-3.3-70b-versatile or gemma2-9b-it) that parses conversation, extracts entities, and calls sales tools automatically.
• 5 LangGraph Agent Tools:
  1. search_hcp: Search HCPs by name, specialty, or clinic.
  2. get_hcp_details: Fetch full HCP profile data.
  3. get_interaction_history: Check historical logs for a given HCP.
  4. log_interaction: Log a new interaction with inferred sentiment and entity extraction.
  5. edit_interaction: Modify details of an existing log.
• Voice Note Simulation: Transcribe and extract structured fields from simulated representative voice notes instantly.
• Interaction History Timeline Feed: Color-coded timeline list of interactions with inline edit and delete functionality.
• Modern Premium Theme: Developed with vanilla CSS, implementing Google Inter typography, glassmorphism, visual highlights for sentiments, and micro-animations.

---

🛠️ Technology Stack

• Frontend: React, Redux Toolkit (state management), Lucide Icons, Vite (build tool), Vanilla CSS.
• Backend: Python, FastAPI, SQLAlchemy ORM, Uvicorn server.
• AI Agent Framework: LangGraph, LangChain Core, LangChain Groq.
• Database: PostgreSQL (running on port 5432) with SQLite fallback support.

---

💻 Installation and Setup

1. Prerequisites

• Python 3.10+
• Node.js v18+ & NPM
• PostgreSQL database (or automatic fallback to SQLite crm_hcp.db if PostgreSQL is not configured/accessible)

2. Backend Setup

1. Open a terminal and navigate to the backend directory:

   cd backend

2. Install the required Python packages:

   pip install -r requirements.txt

3. Configure environment variables. Edit the backend/.env file and insert your Groq API key:

   DATABASE_URL=postgresql://postgres:postgres@localhost:5432/crm_hcp
   GROQ_API_KEY=YOUR_GROQ_API_KEY

   Note: If PostgreSQL is not active, the database module automatically sets up a fallback SQLite database, allowing the backend to start up without additional database servers.

4. Launch the FastAPI server:

   uvicorn main:app --host 127.0.0.1 --port 8000 --reload

   The backend will seed mock data on startup and run at http://127.0.0.1:8000.

3. Frontend Setup

1. Open a new terminal and navigate to the frontend directory:

   cd frontend

2. Install the dependencies:

   npm install

3. Launch the Vite dev server:

   npm run dev

   The frontend application will boot up at http://localhost:3000.