This project provides a streamlined method for summarizing scientific articles using advanced natural language processing capabilities. By leveraging Google Generative AI and fine-tuned prompt engineering, the application generates structured summaries of uploaded scientific articles.
- Automatic Summarization: Converts uploaded articles into structured summaries.
- Detailed Outputs: Includes key findings, objectives, methods, results, conclusions, and key concepts.
- User-Friendly Input: Users can upload files for seamless summarization.
- Powered by Generative AI: Utilizes Google's Gemini AI model for content generation.
Ensure you have the following installed:
- Python 3.8 or higher
pip
(Python package manager)
Install the required libraries using:
pip install streamlit python-dotenv google-generativeai PyPDF2
- Create a
.env
file in the project directory. - Add your Google Generative AI API key to the file:
API_KEY=your_api_key_here
- Save the code in a Python script file (e.g.,
app.py
). - Run the script:
python app.py
- Upload a scientific article file (PDF or text format).
- The program will process the file and generate a structured summary.
The summarization prompt used in the application ensures a consistent structure:
# Structured Summary
# Key Findings
# Objectives
# Methods
# Results
# Conclusions
# Key Concepts
The .env
file is used to securely load the API key.
summarize(file)
: Generates the summary using the Google Generative AI model.main()
: Entry point of the application.
Contributions are welcome. Please fork the repository and submit a pull request.
This project is licensed under the MIT License. See the LICENSE
file for details.