Update app.py

app.py

@@ -45,6 +45,29 @@ def llm_response(history,text,img):
         history += [(None,response.text)]
         return history
 
+# Function that takes User Inputs and displays it on ChatUI
+def output_query_message(txt,img):
+    if not img:
+        return txt
+    base64 = image_to_base64(img)
+    data_url = f"data:image/jpeg;base64,{base64}"
+    outputText = [(f"{txt} ![]({data_url})", None)]
+    return outputText
+
+# Function that takes User Inputs, generates Response and displays on Chat UI
+def output_llm_response(text,img):
+    if not img:
+        response = txt_model.generate_content(text)
+        history = [(None,response.text)]
+        return history
+
+    else:
+        img = PIL.Image.open(img)
+        response = vis_model.generate_content([text,img])
+        history = [(None,response.text)]
+        return history
+
+        
 # Interface Code- Selector method
 
 def sentence_builder(animal, place):
@@ -59,7 +82,7 @@ with gr.Blocks(theme='snehilsanyal/scikit-learn') as app1:
         image_box = gr.Image(type="filepath")
     
         outputbox = gr.Textbox(label="Output")
-    text_box = gr.Dropdown(
+        text_box = gr.Dropdown(
                 ["what is in the image", 
                  "provide alternative title for the image", 
                  "how many birds can be seen in the picture?"], 
@@ -67,11 +90,11 @@ with gr.Blocks(theme='snehilsanyal/scikit-learn') as app1:
             )
 
     btn = gr.Button("Submit")
-    clicked = btn.click(query_message,
-                        [outputbox,text_box,image_box],
+    clicked = btn.click(output_query_message,
+                        [text_box,image_box],
                         outputbox
-                        ).then(llm_response,
-                                [outputbox,text_box,image_box],
+                        ).then(output_llm_response,
+                                [text_box,image_box],
                                 outputbox
                                 )
     gr.Markdown("""