modified

app.py

@@ -43,53 +43,68 @@ 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")
 
-            # Create a message specifically for image prompts
+            logger.debug("Image uploaded. Processing...")
+            # Create a message specifically for the image
             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}"}}
+                    ]
                 }
             ]
 
-            logger.info("Sending image to Groq API for processing...")
-            # Send the image message to the Groq API
+            # Send image query to Groq API
             response = client.chat.completions.create(
                 model="llama-3.2-11b-vision-preview",
                 messages=messages,
             )
             logger.info("Image processed successfully.")
-        else:
-            # Process text input
-            logger.info("Processing text input...")
+
+            # 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...")
             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 the reply
-        LLM_reply = response.choices[0].message.content.strip()
-        logger.debug(f"LLM reply: {LLM_reply}")
+            # 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}")
 
-        # Append user input and bot reply as a tuple to the chat history
-        chat_history.append((user_input, LLM_reply))
+            return [(q, r) for q, r in chat_history if r], None
 
-        return chat_history
+        return chat_history, None
 
     except Exception as e:
         logger.error(f"Error in customLLMBot function: {e}")
-        return chat_history
+        return chat_history + [(None, f"An error occurred: {e}")], None
+