app.py

from groq import Groq
import gradio as gr
from gtts import gTTS
import uuid
import base64
from io import BytesIO
import os
import logging

# Set up logger
logger = logging.getLogger(__name__)
logger.setLevel(logging.DEBUG)
console_handler = logging.StreamHandler()
file_handler = logging.FileHandler('chatbot_log.log')
formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
console_handler.setFormatter(formatter)
file_handler.setFormatter(formatter)
logger.addHandler(console_handler)
logger.addHandler(file_handler)

# Initialize Groq Client
client = Groq(api_key=os.getenv("GROQ_API_KEY_2"))

# Function to encode the image
def encode_image(uploaded_image):
    try:
        logger.debug("Encoding image...")
        buffered = BytesIO()
        uploaded_image.save(buffered, format="PNG")  # Ensure the correct format
        logger.debug("Image encoding complete.")
        return base64.b64encode(buffered.getvalue()).decode("utf-8")
    except Exception as e:
        logger.error(f"Error encoding image: {e}")
        raise

# Function to handle text and image inputs
def customLLMBot(user_input, uploaded_image, chat_history):
    try:
        logger.info("Processing input...")

        # Append user input to the chat history
        chat_history.append((user_input, None))

        if uploaded_image is not None:
            # Encode the image to base64
            base64_image = encode_image(uploaded_image)

            # Log the image size and type
            logger.debug(f"Image received, size: {len(base64_image)} bytes")

            # 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}"}}
                    ]
                }
            ]

            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.")
        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 the reply
        LLM_reply = response.choices[0].message.content
        logger.debug(f"LLM reply: {LLM_reply}")

        # Append the bot's response to the chat history
        chat_history[-1] = (user_input, LLM_reply)

        # Generate audio for response
        audio_file = f"response_{uuid.uuid4().hex}.mp3"
        tts = gTTS(LLM_reply, lang='en')
        tts.save(audio_file)
        logger.info(f"Audio response saved as {audio_file}")

        # Return chat history and audio file
        return chat_history, audio_file

    except Exception as e:
        # Handle errors gracefully
        logger.error(f"Error in customLLMBot function: {e}")
        return [(user_input, f"An error occurred: {e}")], None


# Gradio Interface
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=None, elem_id="chatbot").style(
                    align_self_right=True,
                    align_self_left=False,
                    match=False,
                )
                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):
            logger.info("User submitted a query.")
            response, audio = customLLMBot(user_query, image, chat_history)
            return response, audio, ""

        # Submit on pressing Enter key
        user_input.submit(
            handle_submit,
            inputs=[user_input, uploaded_image],
            outputs=[chatbot, audio_output, user_input],
        )

        # Submit on button click
        submit_btn.click(
            handle_submit,
            inputs=[user_input, uploaded_image],
            outputs=[chatbot, audio_output, user_input],
        )

        # Action for clearing all fields
        clear_btn.click(
            lambda: ([], "", None, None),
            inputs=[],
            outputs=[chatbot, user_input, uploaded_image, audio_output],
        )

    return demo


# Launch the interface
chatbot_ui().launch(server_name="0.0.0.0", server_port=7860)