src/research_assistant/main.py

import argparse
from pathlib import Path

from dotenv import load_dotenv

from research_assistant.app_logging import app_logger
from research_assistant.config.configuration import ConfigurationManager
from research_assistant.pipeline.articleSearch import ArticleSearchPipeline
from research_assistant.pipeline.articleSummarization import ArticleSummarization
from research_assistant.utils.common import write_summary_to_file


def article_summarization():
    app_logger.info("Starting the Summarization Pipeline")
    load_dotenv(Path(".env"))
    article_config = ConfigurationManager().get_article_details_config()
    filepath = article_config.file_path
    app_logger.info(f"Processing file: {filepath}")
    summary = ArticleSummarization(filepath).get_summary()
    app_logger.info(f"Summary: {summary}")
    app_logger.info("Completed Summarizing the article")
    write_summary_to_file(article_config, summary)
    app_logger.info("Summarization Pipeline completed successfully")


def article_search():
    app_logger.info("Starting the article search pipeline")
    arxiv_search_details = ConfigurationManager().get_article_search_params()
    article_search = ArticleSearchPipeline(arxiv_search_details)
    article_list = article_search.get_article_list()
    app_logger.info(
        f"Completed searching for articles. We found a total of {len(article_list)} articles"
    )


def main():
    parser = argparse.ArgumentParser(description="Research Assistant CLI")
    parser.add_argument(
        "--summarize_article",
        action="store_true",
        help="Runs the article summmarization pipeline",
    )
    parser.add_argument(
        "--search_articles",
        action="store_true",
        help="Run the article search pipeline",
    )
    args = parser.parse_args()
    if args.summarize_article:
        article_summarization()
    elif args.search_articles:
        article_search()
    else:
        app_logger.info("No valid arguments provided. Use --help for options.")


if __name__ == "__main__":
    main()