Create app.py

app.py

@@ -0,0 +1,127 @@
+import gradio as gr
+import pandas as pd
+from Bio import Entrez
+import requests
+
+import os 
+
+HF_API = os.getenv('HF_API')
+# Function to search PubMed for articles
+def search_pubmed(query, retmax):
+    Entrez.email = '[email protected]'
+    handle = Entrez.esearch(db="pubmed", term=query, retmax=retmax)
+    record = Entrez.read(handle)
+    handle.close()
+    idlist = record['IdList']
+    handle = Entrez.efetch(db="pubmed", id=idlist, retmode="xml")
+    articles = Entrez.read(handle)['PubmedArticle']
+    handle.close()
+    article_list = []
+    for article in articles:
+        article_dict = {
+            'PMID': str(article['MedlineCitation']['PMID']),
+            'Authors': ' '.join([author['LastName'] + ' ' + author.get('Initials', '')
+                                 for author in article['MedlineCitation']['Article']['AuthorList']]),
+            'Title': article['MedlineCitation']['Article']['ArticleTitle'],
+            'Abstract': article['MedlineCitation']['Article'].get('Abstract', {}).get('AbstractText', [None])[0]
+        }
+        article_list.append(article_dict)
+    return pd.DataFrame(article_list)
+
+# Function to summarize articles using Hugging Face's API
+def summarize_with_huggingface(model, selected_articles):
+    API_URL = f"https://api-inference.huggingface.co/models/{model}"
+    # Your Hugging Face API key
+    API_KEY = HF_API 
+    headers = {"Authorization": f"Bearer {API_KEY}"}
+    # Prepare the text to summarize: concatenate all abstracts
+    print(type(selected_articles))
+    print(selected_articles.to_dict(orient='records'))
+    text_to_summarize = " ".join(
+        [f"PMID: {article['PMID']}. Authors: {article['Authors']}. Title: {article['Title']}. Abstract: {article['Abstract']}." 
+         for article in selected_articles.to_dict(orient='records')]
+    )
+    # Define the payload
+    payload = {
+        "inputs": text_to_summarize,
+        "parameters": {"max_length": 300}  # Adjust as needed
+    }
+    # Make the POST request to the Hugging Face API
+    response = requests.post(API_URL, headers=headers, json=payload)
+    response.raise_for_status()  # Raise an HTTPError if the HTTP request returned an unsuccessful status code
+    # The API returns a list of dictionaries. We extract the summary from the first one.
+    return response.json()[0]['generated_text']
+
+
+    
+
+import gradio as gr
+from Bio import Entrez
+
+# Always tell NCBI who you are
+Entrez.email = "[email protected]"
+
+
+def process_query(keywords, top_k):
+    articles = search_pubmed(keywords, top_k)
+    # Convert each article from a dictionary to a list of values in the correct order
+    articles_for_display = [[article['pmid'], article['authors'], article['title'], article['abstract']] for article in articles]
+    return articles_for_display
+
+
+def summarize_articles(indices, articles_for_display):
+    # Convert indices to a list of integers
+    selected_indices = [int(index.strip()) for index in indices.split(',') if index.strip().isdigit()]
+    # Convert the DataFrame to a list of dictionaries
+    articles_list = articles_for_display.to_dict(orient='records')
+    # Select articles based on the provided indices
+    selected_articles = [articles_list[index] for index in selected_indices]
+    # Generate the summary
+    summary = summarize_with_huggingface(selected_articles)
+    return summary
+
+# Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("### PubMed Article Summarizer")
+    model_input = gr.Textbox(label="Enter the model to use", value="h2oai/h2ogpt-4096-llama2-7b-chat")
+    query_input = gr.Textbox(label="Query Keywords")
+    retmax_input = gr.Slider(minimum=1, maximum=20, value=5, step=1, label="Number of articles")
+    search_button = gr.Button("Search")
+    output_table = gr.Dataframe(headers=["PMID", "Authors", "Title","Abstract" ])
+    summarize_button = gr.Button("Summarize")
+    summary_output = gr.Textbox()
+
+    def update_output_table(query, retmax):
+        df = search_pubmed(query, retmax)
+#        output_table.update(value=df)
+        return df
+    search_button.click(update_output_table, inputs=[query_input, retmax_input], outputs=output_table)
+    summarize_button.click(fn=summarize_with_huggingface, inputs=[model_input, output_table], outputs=summary_output)
+
+demo.launch(debug=True)
+
+if False:
+    with gr.Blocks() as demo:
+        gr.Markdown("### PubMed Article Summarizer")
+        with gr.Row():
+            query_input = gr.Textbox(label="Query Keywords")
+            top_k_input = gr.Slider(minimum=1, maximum=20, value=5,  step=1, label="Top K Results")
+        search_button = gr.Button("Search")
+        output_table = gr.Dataframe(headers=["Title", "Authors", "Abstract", "PMID"])
+        indices_input = gr.Textbox(label="Enter indices of articles to summarize (comma-separated)")
+        summarize_button = gr.Button("Summarize Selected Articles")
+        summary_output = gr.Textbox(label="Summary")
+    
+        search_button.click(
+            fn=process_query,
+            inputs=[query_input, top_k_input],
+            outputs=output_table
+        )
+    
+        summarize_button.click(
+            fn=summarize_articles,
+            inputs=[indices_input, output_table],
+            outputs=summary_output
+        )
+    
+    demo.launch(debug=True)