https://github.com/jomasego/multiagent_sales
Multiagent sales system consisting of 3 Ai agents using Groq and Google Ai API Keys you need to provide, in the free Tier. Written in Python using Langchain and Streamlit.
https://github.com/jomasego/multiagent_sales
agentic-ai agents ai groq langchain llama3 multiagent-systems sales streamlit
Last synced: 2 months ago
JSON representation
Multiagent sales system consisting of 3 Ai agents using Groq and Google Ai API Keys you need to provide, in the free Tier. Written in Python using Langchain and Streamlit.
- Host: GitHub
- URL: https://github.com/jomasego/multiagent_sales
- Owner: jomasego
- Created: 2025-05-28T14:33:00.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-06-21T16:57:38.000Z (about 1 year ago)
- Last Synced: 2025-07-06T00:01:38.542Z (12 months ago)
- Topics: agentic-ai, agents, ai, groq, langchain, llama3, multiagent-systems, sales, streamlit
- Language: Python
- Homepage:
- Size: 5.86 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 🚗 Advanced Multi-Agent Car Sales System (Groq + Gemini Edition)
[](https://www.python.org/downloads/)
[](https://langchain.com/)
[](https://groq.com/)
[](https://ai.google.dev/)
[](https://streamlit.io/)
> **A sophisticated multi-agent AI system for intelligent car sales, demonstrating advanced agent coordination, real-time research, and professional sales workflows, all powered by high-speed Groq inference.**
---
## 🏗️ Architecture
The system orchestrates three specialized AI agents, each with a distinct role, to create a seamless and intelligent customer experience. LangChain provides the agent framework, Streamlit powers the user interface, and Groq's LPU ensures near-instant responses.
### 🤖 Meet the Agents
| Agent | Model | Role | Specialization |
|-------|-------|------|----------------|
| **🎯 John** | `llama3-70b-8192` (Groq) | Sales Expert | Customer interaction, sales process, negotiation |
| **🔬 Dru** | `gemini-pro` (Google AI) | Research Specialist | Vehicle research, technical analysis, market data |
| **🏢 Boss** | `llama3-70b-8192` (Groq) | Business Coordinator | Inventory management, pricing, business policies |
---
## ✨ Key Features
- **🚀 High-Speed Inference**: Near-instant agent responses powered by Groq's LPU technology.
- **🧠 Intelligent Agent Coordination**: Seamless communication between specialized agents for a comprehensive sales workflow.
- **🔍 Smart Inventory Search**: AI-powered vehicle matching against a local CSV database.
- **🌐 Real-time Research**: On-demand technical details and market data provided by the Gemini-powered research agent.
- **💼 Professional Sales Process**: The system can handle the entire sales funnel, from initial greeting to negotiation.
---
## 🚀 Quick Start
### Prerequisites
- Python 3.8 or higher
- A [Groq API Key](https://console.groq.com/keys)
- A [Google AI (Gemini) API Key](https://ai.google.dev/)
### Installation
1. **Clone the repository:**
```bash
git clone https://github.com/jomasego/multiagent_sales.git
cd multiagent_sales
```
2. **Create a virtual environment:**
```bash
python3 -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
```
3. **Install dependencies:**
```bash
pip install --upgrade pip
pip install -r requirements.txt
```
4. **Configure environment variables:**
Create a file named `.env` in the project root and add your API keys:
```env
GROQ_API_KEY="gsk_..."
GEMINI_API_KEY="AIza..."
```
5. **Run the application:**
```bash
streamlit run app.py
```
6. **Access the interface:**
Open your browser to `http://localhost:8501` and start chatting with John!
---
## 📖 Usage Examples
Once the application is running, you can interact with the sales agent. Here are a few examples:
- **Initial Contact:** `"Hi, I'm looking for a car"`
- **Specific Requirements:** `"I want a red sedan that's less than 2 years old"`
- **Technical Inquiry:** `"What safety features does the Tesla Model 3 have for babies?"`
- **Negotiation:** `"Can you offer any discount on the Ford Mustang?"`
---
## 🛠️ Technical Stack
- **🤖 AI Models**: Groq `llama3-70b-8192`, Google `gemini-pro`
- **🔗 Agent Framework**: LangChain
- **🖥️ Frontend**: Streamlit
- **📊 Data**: Pandas
- **🐍 Language**: Python 3.8+