This project is a Streamlit web application that acts as a research assistant. It uses Google's Gemini model to conduct research on a given topic, synthesizes the findings, and generates a comprehensive report in Markdown format.

Here's a walkthrough of the application:

1. Enter API Keys and Topic: Provide your Serper and Google Gemini API keys, along with the research topic.

2. Run Research: The agent conducts searches and generates the report.

3. View Report: The generated report is displayed directly in the app.

4. Download Report: You can download the report as a Markdown file.

• Frontend: Streamlit
• Language Model: Google Gemini
• Search: Serper for Google Search results
• Core Logic: CrewAI
• Language: Python

To run this project on your local machine, follow these steps:

1. Clone the repository:

   git clone https://github.com/CodebyKumar/Simple_Research_Agent.git
   cd Simple_Research_Agent

2. Install dependencies: It's recommended to use a virtual environment.

   python -m venv venv
   source venv/bin/activate  # On Windows, use `venv\Scripts\activate`
   pip install -r requirements.txt

3. Set up environment variables: Create a .env file in the root of the project and add your API keys:

   SERPER_API_KEY="your_serper_api_key"
   GOOGLE_API_KEY="your_google_api_key"
   

4. Run the Streamlit app:

   streamlit run app.py

This application is deployed on Streamlit Cloud and is available here: https://researchagent-kk.streamlit.app/

A simple research automation tool that uses web search and Google Gemini to generate comprehensive research reports on any topic.

• Automated web search using Serper API
• AI-powered report generation using Google Gemini
• Markdown report output, ready for sharing or publishing
• Clean, modular Python codebase

• Python 3.8+
• Serper API key
• Google Gemini API key
• Install dependencies:

pip install -r requirements.txt

1. Clone this repository.
2. Create a .env file in the project root with the following content:

   SERPER_API_KEY=your_serper_api_key_here
   GOOGLE_API_KEY=your_google_gemini_api_key_here

3. (Optional) Create a reports/ directory, or let the script create it automatically.

Run the research agent from the command line:

python main.py "Your research topic here"

python main.py "The Impact of Artificial Intelligence on the Future of Work"

The generated report will be saved in the reports/ directory as a Markdown file.

• The report is saved as a clean Markdown file (no code block markers).
• Example output file: reports/research_report_The_Impact_of_Artificial_Intelligence_on_the_Futur_20250614_222627.md

main.py
requirements.txt
reports/
utils/
    agent.py
    gemini_agent.py
    serper_api.py
    helpers.py

• Make sure your API keys are valid and have sufficient quota.
• The tool does not log or save any information except the generated report.
• If you encounter issues, check your .env file and API key validity.

MIT License