app.py

import gradio as gr
from typing import List, Dict, Any
from config import DATASET_NAME
from arxiv_retrieval_service import ArxivRetrievalService
from dataset_management_service import DatasetManagementService
import logging

logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')

arxiv_service = ArxivRetrievalService()
dataset_service = DatasetManagementService(DATASET_NAME)

def handle_metadata_extraction(query: str, max_results: int) -> str:
    try:
        logging.info(f"Fetching metadata for query: {query}, max_results: {max_results}")
        metadata_list = arxiv_service.fetch_metadata(query, max_results)
        if not metadata_list:
            return "No metadata found for the given query."
        
        result = dataset_service.update_dataset(metadata_list)
        logging.info(f"Dataset update result: {result}")
        return result
    except Exception as e:
        error_msg = f"An error occurred during metadata extraction: {str(e)}"
        logging.error(error_msg)
        return error_msg

def handle_dataset_view(page: int = 1, page_size: int = 10) -> Dict[str, Any]:
    logging.info(f"handle_dataset_view called with page={page}, page_size={page_size}")
    try:
        total_records = dataset_service.get_dataset_size()
        logging.info(f"Total records: {total_records}")
        
        records = dataset_service.get_dataset_records(page, page_size)
        logging.info(f"Records type: {type(records)}")
        logging.info(f"Number of records returned: {len(records)}")
        
        result = {
            "total_records": total_records,
            "current_page": page,
            "page_size": page_size,
            "records": records
        }
        logging.info(f"Returning result: {result}")
        return result
    except Exception as e:
        error_msg = f"Error loading dataset: {str(e)}"
        logging.error(error_msg)
        return {"error": error_msg}

with gr.Blocks() as demo:
    gr.Markdown(
        f"""# ArXiv Metadata Extraction and Dataset Management
        
        This application extracts metadata from ArXiv papers and manages the dataset:
        [{DATASET_NAME}](https://huggingface.co/datasets/{DATASET_NAME}/viewer)
        """
    )
    
    with gr.Tab("Extract Metadata"):
        query_input = gr.Textbox(label="ArXiv Query")
        max_results = gr.Slider(minimum=1, maximum=100, value=10, step=1, label="Max Results")
        submit_button = gr.Button("Extract Metadata")
        output = gr.Textbox(label="Result")
        
        submit_button.click(
            fn=handle_metadata_extraction,
            inputs=[query_input, max_results],
            outputs=output
        )
    
    with gr.Tab("View Dataset"):
        page_number = gr.Number(value=1, label="Page Number", precision=0)
        page_size = gr.Slider(minimum=5, maximum=50, value=10, step=5, label="Page Size")
        refresh_button = gr.Button("Refresh Dataset View")
        dataset_info = gr.JSON(label="Dataset Info")
        
        refresh_button.click(
            fn=handle_dataset_view,
            inputs=[page_number, page_size],
            outputs=dataset_info
        )

if __name__ == "__main__":
    demo.launch()