step 6

app.py

@@ -32,13 +32,14 @@ def generate_output_html(top_3_products):
     return output_html
 
 def encode_text(text):
-    inputs = processor(text, return_tensors="pt", padding=True, truncation=True)
+    inputs = processor(text=[text], return_tensors="pt", padding=True, truncation=True)
     return inputs
 
 def encode_image(image):
-    inputs = processor(images=image, return_tensors="pt", padding=True, truncation=True)
+    inputs = processor(images=[image], return_tensors="pt", padding=True, truncation=True)
     return inputs
 
+
 def initial_query(image, text):
     text_inputs = encode_text(text)
     image_inputs = encode_image(image)
@@ -76,15 +77,17 @@ with gr.Blocks() as demo:
     chatbot = gr.Chatbot([], elem_id="chatbot").style(height=750)
 
     with gr.Row():
-        with gr.Column(scale=0.85):
+        with gr.Column(scale=0.70):
             txt = gr.Textbox(
                 show_label=False,
                 placeholder="Enter text and press enter, or upload an image",
             ).style(container=False)
         with gr.Column(scale=0.15, min_width=0):
             btn = gr.UploadButton("📁", file_types=["image", "video", "audio"])
+        with gr.Column(scale=0.15, min_width=0):
+            send_btn = gr.Button("Send")
 
-    txt.submit(bot, [chatbot, txt], chatbot)
+    # Set the on_click action for the send_btn
+    send_btn.on_click(bot, [chatbot, txt], chatbot)
     btn.upload(bot, [chatbot, btn], chatbot)
-
 demo.launch()