Multi-Agent Research System

A powerful Multi-Agent Research System built with Python, Streamlit, LangChain, and Google Gemini. The application uses multiple AI agents to perform research, gather information, analyze findings, and generate structured outputs.

Features

• Multi-agent workflow for research and analysis
• Powered by Google Gemini models
• Interactive Streamlit web interface
• Modular architecture with separate agents and tools
• Environment variable-based configuration
• Easy local setup and deployment

---

Project Structure

Multi-agent-research-system/
│
├── app.py                # Streamlit application entry point
├── agents.py             # Agent definitions
├── pipeline.py           # Agent workflow pipeline
├── tools.py              # Custom tools and utilities
├── requirements.txt      # Project dependencies
├── .env.example          # Environment variables template
└── README.md

---

Prerequisites

Before running the project, ensure you have:

• Python 3.10 or higher
• Git
• Google Gemini API Key

---

Installation

1. Clone the Repository

git clone <your-repository-url>
cd Multi-agent-research-system

2. Create a Virtual Environment

Windows

python -m venv venv
venv\Scripts\activate

Linux/macOS

python -m venv venv
source venv/bin/activate

3. Install Dependencies

pip install -r requirements.txt

---

Environment Variables

Create a .env file in the root directory.

Example:

GEMINI_API_KEY=""

TAVILY_API_KEY=your_tavily_api_key_here

You can copy the template:

cp .env.example .env

or on Windows:

copy .env.example .env

---

Running the Application

Start the Streamlit application:

streamlit run app.py

Alternatively:

python -m streamlit run app.py

After starting, Streamlit will display a local URL similar to:

Local URL: http://localhost:8501

Open the URL in your browser.

---

Using Google Gemini

This project is configured to use Google Gemini through LangChain.

Example configuration:

from langchain_google_genai import ChatGoogleGenerativeAI

llm = ChatGoogleGenerativeAI(
    model="gemini-2.5-flash",
    temperature=0
)

You can also use:

model="gemini-2.5-pro"

for more advanced reasoning capabilities.

---

Troubleshooting

Streamlit Not Found

ModuleNotFoundError: No module named 'streamlit'

Solution:

pip install streamlit

---

Missing Environment Variables

Ensure your .env file exists and contains all required API keys.

---

Dependency Issues

Update pip and reinstall dependencies:

python -m pip install --upgrade pip
pip install -r requirements.txt

---

Tech Stack

• Python
• Streamlit
• LangChain
• Google Gemini
• dotenv

---

Contributing

Contributions, issues, and feature requests are welcome.

1. Fork the repository
2. Create a feature branch
3. Commit your changes
4. Push to your branch
5. Open a pull request

---

License

This project is intended for educational and research purposes. Feel free to modify and extend it according to your needs.