Update app.py

app.py

@@ -64,6 +64,13 @@ storage_context = StorageContext.from_defaults(persist_dir="VectorStore")
 # load index
 index_persisted = load_index_from_storage(storage_context, index_id="vector_index")
 
+async def remove_ref(text):
+    split_text = re.split(r'\bReference Papers\b', text, flags=re.IGNORECASE)
+
+    if len(split_text) > 1:
+        return split_text[0].strip()
+    
+    return text.strip()
 
 async def run_function_on_text(top_k,study_obj,study_type,phase,purpose,allocation,intervention_model,Masking,conditions,interventions,location_countries,removed_location_countries):
 
@@ -155,6 +162,59 @@ async def run_function_on_text(top_k,study_obj,study_type,phase,purpose,allocati
       """
     )
 
+  #Extract ref
+  if query_response.response != "Empty Response":
+    pattern = r'Reference Papers:?\s*(.*?)(?:\n\n.*$|$)'
+    match = re.search(pattern, query_response.response, re.DOTALL | re.IGNORECASE)
+    ext_ref = match.group(1) if match and match.group(1) else ''
+    split_ref = re.split(r'\d+\.\s+', ext_ref)[1:]
+
+    formatted_ref = []
+    n=0
+    for ref in split_ref:
+        nct_match = re.search(r'NCT[_ ]ID: (NCT\d+)', ref)
+        if nct_match:
+            nct_id = nct_match.group(1)
+        else:
+            nct_match = re.search(r'(NCT\d+)', ref)
+            if nct_match:
+                nct_id = nct_match.group(1)
+            else:
+                continue
+        n+=1        
+        study_name = re.search(r'Study Name:?\s*(.*?)(?=\n|Condition:|Intervention/Treatment:|$)', ref, re.DOTALL).group(1).strip()
+        condition = re.search(r'Condition:?\s*(.*?)(?=\n|Intervention/Treatment:|$)', ref, re.DOTALL).group(1).strip()
+        intervention = re.search(r'Intervention/Treatment:?\s*(.*?)(?=\n|$)', ref, re.DOTALL).group(1).strip()
+
+        study_name = re.sub(r'\*+', '', study_name).strip()
+        condition = re.sub(r'\*+', '', condition).strip()
+        intervention = re.sub(r'\*+', '', intervention).strip()     
+
+        formatted_trial = [
+            n,
+            f'<a href="https://clinicaltrials.gov/study/{nct_id}">{nct_id}</a>',
+            study_name,
+            condition,
+            intervention
+        ]
+
+        formatted_ref.append(formatted_trial)
+      
+  else:
+    formatted_ref = []
+
+  #Extract criteria
+  if query_response.response == "Empty Response":
+    return query_response,formatted_ref
+  else:
+    removed_ref = await remove_ref(query_response.response)
+    combine_criteira = re.sub(r'##\s*', '', removed_ref).strip()
+    combine_criteira = re.sub(r'#\s*', '', combine_criteira).strip()
+    combine_criteira = re.sub(r'\*\*', '', combine_criteira).strip()
+    combine_criteira = re.sub(r'(Criteria)\n\s*\n(\d+\.)', r'\1\n\2', combine_criteira).strip()
+
+    return combine_criteira,formatted_ref
+
   # # LLM.complete
   # complete_response  = await llm.acomplete(f"""
   #     Based on the provided instructions and clinical trial information, generate the new eligibility criteria by analyzing clinical trial information(### Clinical Trial Information).
@@ -252,7 +312,7 @@ async def run_function_on_text(top_k,study_obj,study_type,phase,purpose,allocati
   #     """
     # )
 
-  return query_response
+  # return query_response
   # return query_response,complete_response,combine_response
 
 # Place holder
@@ -335,6 +395,24 @@ with gr.Blocks() as demo:
           placeholder=prefilled_value,
           # placeholder=objective_place_holder,
           lines=10)
+  # Conditions
+  with gr.Row():
+      gr.Markdown("# Conditions"),
+  with gr.Row():
+      conditions_box = gr.Textbox(
+          label="Conditions / Disease",
+          info="Primary Disease or Condition of Cancer Being Studied in the Trial, or the Focus of the Study",
+          placeholder=conditions_place_holder,
+          )
+  #Interventions
+  with gr.Row():
+      gr.Markdown("# Interventions / Drugs"),
+  with gr.Row():
+      intervention_box = gr.Textbox(
+          label="Intervention type",
+          placeholder=interventions_place_holder,
+          lines=10,
+          )
   # Study Design
   with gr.Row():
       gr.Markdown("# Study Design"),
@@ -363,24 +441,6 @@ with gr.Blocks() as demo:
           ["None (Open Label)", "Single", "Double", "Triple", "Quadruple"],
           label="Masking"
           )
-  # Conditions
-  with gr.Row():
-      gr.Markdown("# Conditions"),
-  with gr.Row():
-      conditions_box = gr.Textbox(
-          label="Conditions / Disease",
-          info="Primary Disease or Condition of Cancer Being Studied in the Trial, or the Focus of the Study",
-          placeholder=conditions_place_holder,
-          )
-  #Interventions
-  with gr.Row():
-      gr.Markdown("# Interventions / Drugs"),
-  with gr.Row():
-      intervention_box = gr.Textbox(
-          label="Intervention type",
-          placeholder=interventions_place_holder,
-          lines=10,
-          )
   #Location
   with gr.Row():
       gr.Markdown("# Location"),
@@ -395,7 +455,7 @@ with gr.Blocks() as demo:
   # Submit & Clear
   with gr.Row():
     submit_button = gr.Button("Submit")
-    # clear_button = gr.Button("Clear")
+    clear_button = gr.Button("Clear")
 
   # Output
   with gr.Row():
@@ -406,6 +466,13 @@ with gr.Blocks() as demo:
               # label="Response 1",
               lines=15,
               interactive=False)
+  with gr.Row():
+          ref_table = gr.Dataframe(
+              label="Reference",
+              headers=["No.",'Link', 'Study name', 'Condition', 'Intervention'],
+              datatype=["markdown","html","markdown", "markdown","markdown"],
+              wrap=True,
+              interactive=False)
       # with gr.Column():
       #     rag_box = gr.Textbox(
       #         label="Response 2",
@@ -416,9 +483,11 @@ with gr.Blocks() as demo:
       #         label="Response 3",
       #         lines=15,
       #         interactive=False)
-          
+  with gr.Row():
+    regenerate_button = gr.Button("Regenerate")
+      
   inputs_information = [top_k_box, study_obj_box, study_type_box, phase_box, purpose_box, allocation_box, intervention_model_box, masking_box, conditions_box, intervention_box, location_box, removed_location_box]
-  outputs_information = [base_box]
+  outputs_information = [base_box,ref_table]
   # outputs_information = [base_box, rag_box,combine_box]
 
   submit_button.click(
@@ -426,8 +495,14 @@ with gr.Blocks() as demo:
       inputs=inputs_information,
       outputs=outputs_information
       )
+    
+  regenerate_button.click(
+      run_function_on_text,
+      inputs=inputs_information,
+      outputs=outputs_information
+      )
 
-  # clear_button.click(lambda : [None] * len(inputs_information), outputs=inputs_information)
+  clear_button.click(lambda : [None] * len(inputs_information), outputs=inputs_information)
 
   # with gr.Row():
   #     selected_response = gr.Radio(