Upload app.py

app.py

@@ -23,6 +23,14 @@ checker_pipe = pipeline('text-classification', 'ksg-dfci/TrialChecker', tokenize
                         truncation=True, padding='max_length', max_length=512)
 
 
+import gradio as gr
+import pandas as pd
+import torch
+import torch.nn.functional as F
+from sentence_transformers import SentenceTransformer
+from safetensors import safe_open
+from transformers import pipeline, AutoTokenizer
+import tempfile
 
 # We assume the following objects have already been loaded:
 # trial_spaces (DataFrame), embedding_model (SentenceTransformer),
@@ -54,7 +62,11 @@ def match_clinical_trials(patient_summary: str):
         'trial_eligibility_criteria': relevant_eligibility_criteria
     }).reset_index(drop=True)
     
-    analysis['pt_trial_pair'] = analysis['this_space'] + "\nNow here is the patient summary:" + analysis['patient_summary_query']
+    analysis['pt_trial_pair'] = (
+        analysis['this_space'] 
+        + "\nNow here is the patient summary:" 
+        + analysis['patient_summary_query']
+    )
     
     # Run checker pipeline
     classifier_results = checker_pipe(analysis.pt_trial_pair.tolist())
@@ -62,16 +74,7 @@ def match_clinical_trials(patient_summary: str):
     analysis['trial_checker_score'] = [x['score'] for x in classifier_results]
     
     # Return the final subset of columns including patient_summary_query as first column
-    return analysis[[
-        'patient_summary_query',
-        'nct_id', 
-        'trial_title', 
-        'trial_brief_summary', 
-        'trial_eligibility_criteria', 
-        'this_space',
-        'trial_checker_result', 
-        'trial_checker_score'
-    ]], analysis[[
+    out_df = analysis[[
         'patient_summary_query',
         'nct_id', 
         'trial_title', 
@@ -81,6 +84,7 @@ def match_clinical_trials(patient_summary: str):
         'trial_checker_result', 
         'trial_checker_score'
     ]]
+    return out_df, out_df
 
 def export_results(df: pd.DataFrame):
     # Save the dataframe to a temporary CSV file and return its path
@@ -102,9 +106,9 @@ custom_css = """
 
 #output_df table td, #output_df table th {
     min-width: 100px;
-    overflow: hidden;
-    text-overflow: ellipsis;
-    white-space: nowrap;
+    max-width: 300px;
+    overflow-wrap: anywhere; /* or 'word-wrap: break-word;' */
+    white-space: pre-wrap;   /* or 'white-space: normal;' */
     border: 1px solid #ccc;
     padding: 4px;
 }
@@ -142,14 +146,18 @@ with gr.Blocks(css=custom_css) as demo:
     export_btn = gr.Button("Export Results")
 
     # On "Find Matches", show the DataFrame and store it in state
-    submit_btn.click(fn=match_clinical_trials, 
-                     inputs=patient_summary_input, 
-                     outputs=[output_df, results_state])
+    submit_btn.click(
+        fn=match_clinical_trials, 
+        inputs=patient_summary_input, 
+        outputs=[output_df, results_state]
+    )
 
     # On "Export Results", use the state to create and return a CSV file
-    export_btn.click(fn=export_results, 
-                     inputs=results_state, 
-                     outputs=gr.File(label="Download CSV"))
+    export_btn.click(
+        fn=export_results, 
+        inputs=results_state, 
+        outputs=gr.File(label="Download CSV")
+    )
 
 if __name__ == '__main__':
     demo.launch()