Loading repository data…
vk22006 / repository
AI-powered system that analyzes scientific papers, generates automated literature reviews, detects contradictions between research findings, and visualizes relationships using interactive knowledge graphs.
A transparent discovery signal based on current public GitHub metadata.
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
An end-to-end tool to accelerate AI research by automatically fetching papers, synthesizing their contents, and organizing them into interactive knowledge graphs.
This application uses Natural Language Processing (NLP) models to extract summaries and core claims from arXiv papers and visualizes the connections between research papers based on semantic similarity.
For recent updates, refer UPDATE_LOG.
.
├── app.py # FastAPI backend application
├── requirements.txt # Python dependencies
├── backend/ # Backend core logic
│ ├── fetch_papers.py # arXiv data retrieval
│ ├── summarize.py # Abstract summarization
│ ├── claim_extractor.py # Core claim extraction
│ ├── embeddings.py # Similarity matrix computation
│ ├── graph_builder.py # Knowledge graph generation
│ └── graph_visualizer.py # Graph HTML visualization
├── frontend/ # Frontend UI
│ └── streamlit_app.py # Streamlit dashboard application
├── lib/ # Additional utilities/modules
└── data/ # Directory for generated outputs (e.g., graph.html)
Selected from shared topics, language and repository description—not editorial ratings.
lipikapanda443 /
AI-powered research automation system that streamlines literature reviews by refining research topics, retrieving relevant papers from arXiv, generating AI-based summaries with Google Gemini, identifying research gaps, and creating structured PDF reports. Built using Python, Google Colab, Gemini API, and arXiv API.
65/100 healthEnsure you have Python 3.8+ installed. It is recommended to use a virtual environment.
pip install -r requirements.txt
The application consists of a backend API and a frontend dashboard. You need to run both concurrently.
Run the FastAPI server using uvicorn (from the root directory):
uvicorn app:app --reload --host 0.0.0.0 --port 8000
The backend API will be available at http://localhost:8000. You can view the API documentation at http://localhost:8000/docs.
In a new terminal window, run the Streamlit application:
streamlit run frontend/streamlit_app.py
The frontend dashboard will automatically open in your default browser at http://localhost:8501.
This project is licensed under the MIT License, see the LICENSE for more details.