Update app.py

app.py

@@ -328,21 +328,30 @@ def process_summary_with_openai(summary):
         
 
 def process_and_query(input_language=None,audio_input=None,image_input=None,text_input=None):
+        # Initialize the combined text
+        combined_text = ""
     try:
-        text = ""
-        if text_input is not None :
-            # augment the prompt before feeding it to vectara
-            text = "the user asks the following to his health adviser " + text
-        # process audio
-        if audio_input is not None :
-            text += "\n"+process_speech(input_language,audio_input)
-        # process image
-        if image_input is not None :
-            text += "\n"+process_image(image_input)
-        
-        
+        # Initialize the combined text
+        combined_text = ""
+
+        # Process text input
+        if text_input is not None:
+            # Augment the prompt before feeding it to Vectara
+            combined_text = "the user asks the following to his health adviser: " + text_input
+
+        # Process audio input
+        if audio_input is not None:
+            audio_text = process_speech(input_language, audio_input)
+            combined_text += "\n" + audio_text
+
+        # Process image input
+        if image_input is not None:
+            # Use the current combined text (which includes the processed text input) for image processing
+            image_text = process_image(image_input, combined_text)
+            combined_text += "\n" + image_text
+            
         # Use the text to query Vectara
-        vectara_response_json = query_vectara(text)
+        vectara_response_json = query_vectara(combined_text)
         
         # Convert the Vectara response to Markdown
         markdown_output = convert_to_markdown(vectara_response_json)