README.md

metadata

title: AMO CRM Sales Assistant
emoji: 🤖
colorFrom: blue
colorTo: purple
sdk: docker
pinned: false

AMO CRM Sales Assistant

This project is a sophisticated, AI-powered sales assistant designed to work with the AMO CRM. It uses a modular architecture built around a LangGraph-based orchestrator to provide intelligent, context-aware responses to user queries. The assistant can help with a variety of tasks, including generating daily work plans, preparing personalized offers, updating the CRM with new information, and analyzing sales data.

Key Features

• Modular Architecture: The project is divided into several independent modules, each responsible for a specific task (e.g., data access, customer monitoring, offer generation). This makes the system easy to maintain and extend.
• Intelligent Orchestrator: At the core of the project is an orchestrator that uses a large language model (LLM) to understand user intent and route requests to the appropriate tool. It supports contextual follow-up questions and can ask for clarification when a query is ambiguous.
• Idempotent Tool Execution: The tool registry includes a caching mechanism that ensures that repeated calls with the same arguments do not cause redundant executions, making the system more efficient.
• Robust Data Handling: The project uses pandas and pyarrow for efficient in-memory data manipulation, with a dedicated data access layer that provides a clean and safe interface to the CRM data.

Getting Started

Prerequisites

• Python 3.10 or higher
• An OpenAI API key

Installation

1. Clone the repository:

   git clone <repository-url>
   cd <repository-name>
   

2. Create and activate a virtual environment (recommended):

   python -m venv venv
   source venv/bin/activate  # On Windows, use `venv\Scripts\activate`
   

3. Install the required dependencies:

   pip install -r requirements.txt
   

4. Set up your environment variables:

   Create a .env file in the root of the project and add your OpenAI API key:

   OPENAI_API_KEY='your-api-key-here'
   

Running the Application

The main entry point for the application is the app.py file, which starts a web server. To run it, use the following command:

python app.py