modified

app.py

@@ -43,67 +43,54 @@ def customLLMBot(user_input, uploaded_image, chat_history):
     try:
         logger.info("Processing input...")
 
-        # Append user input to the chat history
-        if user_input:
-            chat_history.append((user_input, None))
-
         if uploaded_image is not None:
             # Encode the image to base64
             base64_image = encode_image(uploaded_image)
+            logger.debug(f"Image received, size: {len(base64_image)} bytes")
 
-            logger.debug("Image uploaded. Processing...")
-            # Create a message specifically for the image
+            # Create a message specifically for image prompts
             messages = [
                 {
                     "role": "user",
                     "content": [
                         {"type": "text", "text": "What's in this image?"},
-                        {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{base64_image}"}}
-                    ]
+                        {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{base64_image}"}}]
                 }
             ]
 
-            # Send image query to Groq API
+            logger.info("Sending image to Groq API for processing...")
+            # Send the image message to the Groq API
             response = client.chat.completions.create(
                 model="llama-3.2-11b-vision-preview",
                 messages=messages,
             )
             logger.info("Image processed successfully.")
-
-            # Extract and append the bot's response
-            LLM_reply = response.choices[0].message.content
-            chat_history[-1] = (chat_history[-1][0], LLM_reply)
-            logger.debug(f"LLM reply for image: {LLM_reply}")
-
-            # Return the updated chat history and clear uploaded image after processing
-            return [(q, r) for q, r in chat_history if r], None
-
-        if user_input:
-            # Handle text input
-            logger.debug("Processing text input...")
+        else:
+            # Process text input
+            logger.info("Processing text input...")
             messages = [
                 {"role": "system", "content": "You are Dr. HealthBuddy, a professional virtual doctor chatbot."},
                 {"role": "user", "content": user_input},
             ]
-
             response = client.chat.completions.create(
                 model="llama-3.2-11b-vision-preview",
                 messages=messages,
             )
             logger.info("Text processed successfully.")
 
-            # Extract and append the bot's response
-            LLM_reply = response.choices[0].message.content
-            chat_history[-1] = (chat_history[-1][0], LLM_reply)
-            logger.debug(f"LLM reply for text: {LLM_reply}")
+        # Extract the reply
+        LLM_reply = response.choices[0].message.content.strip()
+        logger.debug(f"LLM reply: {LLM_reply}")
 
-            return [(q, r) for q, r in chat_history if r], None
+        # Append user input and bot reply as a tuple to the chat history
+        chat_history.append((user_input, LLM_reply))
 
-        return chat_history, None
+        return chat_history
 
     except Exception as e:
         logger.error(f"Error in customLLMBot function: {e}")
-        return chat_history + [(None, f"An error occurred: {e}")], None
+        return chat_history
+
 
 
 
@@ -136,8 +123,35 @@ def chatbot_ui():
         def handle_submit(user_query, image):
             logger.info("User submitted a query.")
             updated_chat_history = customLLMBot(user_query, image, chat_history)
-            return updated_chat_history, None, ""  # Audio output is currently not implemented
+            return updated_chat_history, None, ""  # Return the updated chat history
+
+
+def chatbot_ui():
+    chat_history = []  # Initialize empty chat history
+
+    with gr.Blocks() as demo:
+        gr.Markdown("# Healthcare Chatbot Doctor")
 
+        # Layout for chatbot and input box alignment
+        with gr.Row():
+            with gr.Column(scale=3):  # Main column for chatbot
+                chatbot = gr.Chatbot(label="Responses", elem_id="chatbot")
+                user_input = gr.Textbox(
+                    label="Ask a health-related question",
+                    placeholder="Describe your symptoms...",
+                    elem_id="user-input",
+                    lines=1,
+                )
+            with gr.Column(scale=1):  # Side column for image and buttons
+                uploaded_image = gr.Image(label="Upload an Image", type="pil")
+                submit_btn = gr.Button("Submit")
+                clear_btn = gr.Button("Clear")
+                audio_output = gr.Audio(label="Audio Response")
+
+        # Define actions
+        def handle_submit(user_query, image):
+            response = customLLMBot(user_query, image, chat_history)
+            return response, None, ""  # Return chat history and reset input
 
         # Submit on pressing Enter key
         user_input.submit(
@@ -153,11 +167,11 @@ def chatbot_ui():
             outputs=[chatbot, audio_output, user_input],
         )
 
-        # Action for clearing all fields
+        # Clear button action
         clear_btn.click(
-            lambda: ([], "", None, None),
+            lambda: ([], None, ""),
             inputs=[],
-            outputs=[chatbot, user_input, uploaded_image, audio_output],
+            outputs=[chatbot, uploaded_image, user_input],
         )
 
     return demo