app.py

import gradio as gr
from Bio import Entrez
from transformers import pipeline
import os  # For environment variables and file paths

# ---------------------------- Configuration ----------------------------
ENTREZ_EMAIL = os.environ.get("ENTREZ_EMAIL", "[email protected]")  # Use environment variable, default fallback
HUGGINGFACE_API_TOKEN = os.environ.get("HUGGINGFACE_API_TOKEN", "HUGGINGFACE_API_TOKEN") # Use environment variable, default fallback
SUMMARIZATION_MODEL = "facebook/bart-large-cnn"

# ---------------------------- Global Variables ----------------------------
summarizer = None
initialization_status = "Initializing..."  # Track initialization state

# ---------------------------- Helper Functions ----------------------------

def log_error(message: str):
    """Logs an error message to the console and a file (if possible)."""
    print(f"ERROR: {message}")
    try:
        with open("error_log.txt", "a") as f:
            f.write(f"{message}\n")
    except:
        print("Couldn't write to error log file.")  #If logging fails, still print to console

# ---------------------------- Tool Functions ----------------------------

def search_pubmed(query: str) -> list:
    """Searches PubMed and returns a list of article IDs."""
    try:
        Entrez.email = ENTREZ_EMAIL
        handle = Entrez.esearch(db="pubmed", term=query, retmax="5")
        record = Entrez.read(handle)
        handle.close()
        return record["IdList"]
    except Exception as e:
        log_error(f"PubMed search error: {e}")
        return [f"Error during PubMed search: {e}"]

def fetch_abstract(article_id: str) -> str:
    """Fetches the abstract for a given PubMed article ID."""
    try:
        Entrez.email = ENTREZ_EMAIL
        handle = Entrez.efetch(db="pubmed", id=article_id, rettype="abstract", retmode="text")
        abstract = handle.read()
        handle.close()
        return abstract
    except Exception as e:
        log_error(f"Error fetching abstract for {article_id}: {e}")
        return f"Error fetching abstract for {article_id}: {e}"

def summarize_abstract(abstract: str) -> str:
    """Summarizes an abstract using a transformer model."""
    global summarizer
    if summarizer is None:
        log_error("Summarizer not initialized.")
        return "Summarizer not initialized. Check initialization status."

    try:
        # Check if the abstract is empty or too short
        if not abstract or len(abstract.strip()) < 50:
            return "Abstract too short to summarize. A more detailed abstract was not found."

        summary = summarizer(abstract, max_length=130, min_length=30, do_sample=False)[0]['summary_text']
        return summary
    except Exception as e:
        log_error(f"Summarization error: {e}")
        return f"Error during summarization: Failed to generate concise summary with the current model."

# ---------------------------- Agent Function ----------------------------

def medai_agent(query: str) -> str:
    """Orchestrates the medical literature review and summarization."""
    article_ids = search_pubmed(query)

    if isinstance(article_ids, list) and article_ids:
        results = []
        for article_id in article_ids:
            abstract = fetch_abstract(article_id)
            if "Error" not in abstract:
                summary = summarize_abstract(abstract)
                results.append(f"<div class='article'>\n"
                               f"  <h3 class='article-id'>Article ID: {article_id}</h3>\n"
                               f"  <p class='summary'><strong>Summary:</strong> {summary}</p>\n"
                               f"</div>\n")
            else:
                results.append(f"<div class='article error'>\n"
                               f"  <h3 class='article-id'>Article ID: {article_id}</h3>\n"
                               f"  <p class='error-message'>Error processing article: {abstract}</p>\n"
                               f"</div>\n")
        return "\n".join(results)
    else:
        return f"No articles found or error occurred: {article_ids}"

# ---------------------------- Initialization and Setup ----------------------------

def setup():
    """Initializes the summarization model."""
    global summarizer, initialization_status
    initialization_status = "Initializing..."
    try:
        print("Initializing summarization pipeline...")
        initialization_status += "\nInitializing summarization pipeline..."
        summarizer = pipeline("summarization", model=SUMMARIZATION_MODEL, token=HUGGINGFACE_API_TOKEN)
        print("Summarization pipeline initialized.")
        initialization_status += f"\nSummarization pipeline initialized. Model {SUMMARIZATION_MODEL} loaded and ready."
        return initialization_status
    except Exception as e:
        initialization_status = f"Initialization error: {e}"
        log_error(initialization_status)
        return initialization_status

# ---------------------------- Gradio Interface ----------------------------

def launch_gradio():
    """Launches the Gradio interface."""
    global initialization_status

    # CSS to style the article output
    css = """
    .article {
      border: 1px solid #ddd;
      margin-bottom: 10px;
      padding: 10px;
      border-radius: 5px;
    }
    .article.error {
      border-color: #f00;
    }
    .article-id {
      font-size: 1.2em;
      margin-bottom: 5px;
    }
    .summary {
      font-style: italic;
    }
    .error-message {
      color: #f00;
    }
    """

    with gr.Blocks(css=css) as iface:
        gr.Markdown("# MedAI: Medical Literature Review and Summarization")
        status_display = gr.Textbox(value=initialization_status, interactive=False)
        query_input = gr.Textbox(lines=3, placeholder="Enter your medical query (e.g., 'new treatments for diabetes')...")
        submit_button = gr.Button("Submit")
        output_results = gr.HTML()  # Use HTML for formatted output

        submit_button.click(medai_agent, inputs=query_input, outputs=output_results)
        status_display.value = setup()

    iface.launch()

# ---------------------------- Main Execution ----------------------------

if __name__ == "__main__":
    launch_gradio()