Update app.py

app.py

@@ -1,38 +1,152 @@
 import gradio as gr
-from main2 import search_trials  # Importing from main2.py
+import pandas as pd
+from main2 import search_trials  # Your updated search_trials includes summary generation
+
+PAGE_SIZE = 5
 
 def run_search(age, sex, state, keywords):
-    results = search_trials(
+    # Run search WITHOUT generating summaries initially
+    df = search_trials(
         user_age=age,
         user_sex=sex,
         user_state=state,
-        user_keywords=keywords
+        user_keywords=keywords,
+        generate_summaries=False  # generate summaries page-wise
     )
-    return results
+    if df.empty:
+        return pd.DataFrame(), 0, None
+    total_pages = (len(df) + PAGE_SIZE - 1) // PAGE_SIZE
+    page_df = df.iloc[:PAGE_SIZE].copy()
+    page_df['LaymanSummary'] = ""  # empty summary placeholder
+    return page_df, total_pages, df
+
+def generate_summary_for_row(row):
+    # Use the generate_summary helper inside search_trials function, or reimplement here if needed
+    # Since generate_summary is inside search_trials, just call search_trials with generate_summaries=True on 1 row doesn't work.
+    # So, for simplicity, re-implement the summary logic here or expose generate_summary separately.
+    # But easiest: call search_trials with generate_summaries=True on page data and extract LaymanSummary.
+    # To avoid overhead, let's generate summaries for the page using search_trials with generate_summaries=True
+    pass
+
+def load_page(page_num, full_df):
+    if full_df is None or full_df.empty:
+        return pd.DataFrame()
+    start = page_num * PAGE_SIZE
+    end = start + PAGE_SIZE
+    page_df = full_df.iloc[start:end].copy()
+    # Generate summaries for current page only using your own generate_summary inside search_trials
+    # Since generate_summary is local inside search_trials, call search_trials with this subset and generate_summaries=True
 
-with gr.Blocks(theme=gr.theme.Citrus()) as demo:
-    gr.Markdown("#  Clinical Trials Search Tool")
-    gr.Markdown(
-        "Find **recruiting US clinical trials** that match your **age**, **sex**, "
-        "**state**, and optional **keywords**."
+    # Create minimal subset dataframe similar to full_df slice for summary generation
+    page_df_with_summaries = search_trials(
+        user_age=0,    # dummy values; ignored because filtering is done on df subset
+        user_sex="all",
+        user_state="all",
+        user_keywords=[],
+        generate_summaries=True
     )
+    # The above won't work as is because it re-filters dataset; instead do it manually:
+
+    # Workaround: Re-apply generate_summary function here explicitly for each row
+    # Re-implement generate_summary here from your main2.py for page_df only:
+    import re
+    from sklearn.feature_extraction.text import TfidfVectorizer
+    import numpy as np
+
+    def split_sentences(text):
+        return re.split(r'(?<=[.!?])\s+', text.strip())
+
+    def build_input_text(row):
+        text_parts = [
+            f"Intervention Name: {row.get('InterventionName', '')}",
+            f"Intervention Description: {row.get('InterventionDescription', '')}",
+            f"Brief Summary: {row.get('BriefSummary', '')}",
+            f"Primary Outcome Measure: {row.get('PrimaryOutcomeMeasure', '')}",
+            f"Primary Outcome Description: {row.get('PrimaryOutcomeDescription', '')}",
+            f"Start Date: {row.get('StartDate', '')}",
+            f"Detailed Description: {row.get('DetailedDescription', '')}",
+        ]
+        return " ".join([part for part in text_parts if part.strip()])
+
+    def generate_summary(row, num_sentences=5):
+        text = build_input_text(row)
+        if not text.strip():
+            return ""
+        sentences = split_sentences(text)
+        if len(sentences) <= num_sentences:
+            return " ".join(sentences)
+        vectorizer = TfidfVectorizer(stop_words="english")
+        tfidf_matrix = vectorizer.fit_transform(sentences)
+        scores = np.array(tfidf_matrix.sum(axis=1)).flatten()
+        top_indices = scores.argsort()[-num_sentences:][::-1]
+        top_indices = sorted(top_indices)
+        summary_sentences = [sentences[i] for i in top_indices]
+        return " ".join(summary_sentences)
+
+    page_df['LaymanSummary'] = page_df.apply(generate_summary, axis=1)
+    return page_df
+
+def update_page_controls(page_num, total_pages):
+    prev_visible = gr.update(visible=page_num > 0)
+    next_visible = gr.update(visible=page_num < total_pages - 1)
+    page_text = f"Page {page_num + 1} of {total_pages}" if total_pages > 0 else ""
+    return prev_visible, next_visible, page_text
+
+def on_search(age, sex, state, keywords):
+    df_page, total_pages, full_df = run_search(age, sex, state, keywords)
+    page_num = 0
+    if not df_page.empty:
+        df_page = load_page(page_num, full_df)
+    prev_vis, next_vis, page_text = update_page_controls(page_num, total_pages)
+    return df_page, page_text, prev_vis, next_vis, page_num, total_pages, full_df
+
+def on_page_change(increment, page_num, total_pages, full_df):
+    if full_df is None or full_df.empty:
+        return pd.DataFrame(), "", gr.update(visible=False), gr.update(visible=False), 0
+    new_page = max(0, min(page_num + increment, total_pages - 1))
+    page_df = load_page(new_page, full_df)
+    prev_vis, next_vis, page_text = update_page_controls(new_page, total_pages)
+    return page_df, page_text, prev_vis, next_vis, new_page
+
+with gr.Blocks() as demo:
+    gr.Markdown("# Clinical Trials Search Tool with Pagination")
 
     with gr.Row():
         age_input = gr.Number(label="Your Age", value=30)
-        sex_input = gr.Dropdown(["Male", "Female"], label="Sex", value="Male")
+        sex_input = gr.Dropdown(["Male", "Female", "All"], label="Sex", value="All")
 
     with gr.Row():
-        state_input = gr.Dropdown(["Alabama", "Alaska", "Arizona", "Arkansas", "California", "Colorado", "Connecticut", "Delaware", "Florida", "Georgia", "Hawaii", "Idaho", "Illinois", "Indiana", "Iowa", "Kansas", "Kentucky", "Louisiana", "Maine", "Massachusetts", "Michigan", "Minnesota", "Mississippi", "Missouri", "Montana", "Nebraska", "Nevada", "New Hampshire", "New Jersey", "New York", "North Carolina", "North Dakota", "Ohio", "Oklahoma", "Oregon", "Pennsylvania", "Rhode Island", "South Carolina", "South Dakota", "Tennessee", "Texas", "Utah", "Vermont", "Virginia", "Washington", "West Virginia", "Wisconsin", "Wyoming"], label="State (full name or abbreviation)", value="California")
-        keywords_input = gr.Textbox(label="Keywords (comma separated)", placeholder="e.g., cancer, diabetes")
+        state_input = gr.Textbox(label="State (full name or abbreviation)", placeholder="e.g., California")
+        keywords_input = gr.Textbox(label="Keywords (comma separated)", placeholder="e.g., Cancer, Diabetes")
 
     search_btn = gr.Button("Search Trials")
 
     output_table = gr.Dataframe(label="Matching Trials", interactive=False)
 
+    total_pages_text = gr.Textbox(value="", interactive=False)
+    prev_btn = gr.Button("Previous Page")
+    next_btn = gr.Button("Next Page")
+
+    page_num_state = gr.State(0)
+    total_pages_state = gr.State(0)
+    full_results_state = gr.State(None)
+
     search_btn.click(
-        fn=run_search,
+        fn=on_search,
         inputs=[age_input, sex_input, state_input, keywords_input],
-        outputs=output_table
+        outputs=[output_table, total_pages_text, prev_btn, next_btn, page_num_state, total_pages_state, full_results_state]
+    )
+
+    next_btn.click(
+        fn=on_page_change,
+        inputs=[gr.State(1), page_num_state, total_pages_state, full_results_state],
+        outputs=[output_table, total_pages_text, prev_btn, next_btn, page_num_state]
+    )
+
+    prev_btn.click(
+        fn=on_page_change,
+        inputs=[gr.State(-1), page_num_state, total_pages_state, full_results_state],
+        outputs=[output_table, total_pages_text, prev_btn, next_btn, page_num_state]
     )
 
 if __name__ == "__main__":