README.md

---
title: Research Paper Ai Agent
emoji: 👁
colorFrom: yellow
colorTo: green
sdk: gradio
sdk_version: 5.31.0
app_file: app.py
pinned: false
short_description: Superlinked powered AI research paper agent
---

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

# Research AI Agent

A Gradio application that provides an AI-powered research assistant for academic papers.
Based on this article: https://superlinked.com/vectorhub/articles/research-agent

## Features

- **Paper Retrieval**: Find relevant research papers based on your query
- **Paper Summarization**: Generate concise summaries of selected papers
- **Question Answering**: Ask questions about research topics and get AI-generated answers

## Setup Instructions

This application uses OpenAI's API. You need to provide an API key as a secret in your Hugging Face Space:

1. Go to your Space settings
2. Add a secret with the key `OPENAI_API_KEY` and your OpenAI API key as the value

## How to Use

### General Query
Enter any research-related query, and the agent will classify it as retrieval, summarization, or question answering automatically.

### Paper Retrieval
Search for papers on specific topics by entering a search query. Results include publication dates and summaries.

### Paper Summarization
1. Enter comma-separated paper IDs
2. Click "View Available Papers" to see a list of paper IDs in the dataset
3. Click "Summarize" to generate a summary of the selected papers

### Question Answering
Ask specific questions about research topics, and the agent will provide answers based on the paper database.

## Technology

- **Superlinked**: For vector-based similarity search and time-aware paper discovery
- **Sentence Transformers**: For text embedding
- **OpenAI**: For LLM-based summarization and question answering
- **Gradio**: For the user interface

## Dataset

The application uses a dataset of AI research papers from arXiv.