app.py

import os
import base64
import gradio as gr
from PIL import Image
import io
import json
from groq import Groq
import logging

# Set up logging
logging.basicConfig(level=logging.DEBUG)
logger = logging.getLogger(__name__)

# Load environment variables
GROQ_API_KEY = os.environ.get("GROQ_API_KEY")
if not GROQ_API_KEY:
    logger.error("GROQ_API_KEY is not set in environment variables")
    raise ValueError("GROQ_API_KEY is not set")

# Initialize Groq client
client = Groq(api_key=GROQ_API_KEY)

def encode_image(image):
    try:
        if isinstance(image, str):  # If image is a file path
            with open(image, "rb") as image_file:
                return base64.b64encode(image_file.read()).decode('utf-8')
        elif isinstance(image, Image.Image):  # If image is a PIL Image
            buffered = io.BytesIO()
            image.save(buffered, format="PNG")
            return base64.b64encode(buffered.getvalue()).decode('utf-8')
        else:
            raise ValueError(f"Unsupported image type: {type(image)}")
    except Exception as e:
        logger.error(f"Error encoding image: {str(e)}")
        raise

def analyze_construction_image(image, follow_up_question=""):
    if image is None:
        logger.warning("No image provided")
        return "Error: No image uploaded", "", ""

    try:
        logger.info("Starting image analysis")
        image_data_url = f"data:image/png;base64,{encode_image(image)}"

        messages = [
            {
                "role": "user",
                "content": [
                    {
                        "type": "text",
                        "text": "Analyze this construction site image. Identify any issues or snags, categorize them, provide a detailed description, and suggest steps to resolve them. Format your response as a JSON object with keys 'snag_category', 'snag_description', and 'desnag_steps' (as an array)."
                    },
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": image_data_url
                        }
                    }
                ]
            }
        ]

        if follow_up_question:
            messages.append({
                "role": "user",
                "content": follow_up_question
            })

        logger.info("Sending request to Groq API")
        completion = client.chat.completions.create(
            model="llama-3.2-90b-vision-preview",
            messages=messages,
            temperature=0.7,
            max_tokens=1000,
            top_p=1,
            stream=False,
            response_format={"type": "json_object"},
            stop=None
        )

        logger.info("Received response from Groq API")
        result = completion.choices[0].message.content
        logger.debug(f"Raw API response: {result}")

        # Try to parse the result as JSON
        try:
            parsed_result = json.loads(result)
        except json.JSONDecodeError:
            logger.error("Failed to parse API response as JSON")
            return "Error: Invalid response format", "", ""

        snag_category = parsed_result.get('snag_category', 'N/A')
        snag_description = parsed_result.get('snag_description', 'N/A')
        desnag_steps = '\n'.join(parsed_result.get('desnag_steps', ['N/A']))

        logger.info("Analysis completed successfully")
        return snag_category, snag_description, desnag_steps
    except Exception as e:
        logger.error(f"Error during image analysis: {str(e)}")
        return f"Error: {str(e)}", "", ""

# Create the Gradio interface
iface = gr.Interface(
    fn=analyze_construction_image,
    inputs=[
        gr.Image(type="pil", label="Upload Construction Image"),
        gr.Textbox(label="Follow-up Question (Optional)")
    ],
    outputs=[
        gr.Textbox(label="Snag Category"),
        gr.Textbox(label="Snag Description"),
        gr.Textbox(label="Steps to Desnag")
    ],
    title="Construction Image Analyzer (Llama 3.2 90B Vision via Groq)",
    description="Upload a construction site image to identify issues and get desnag steps using Llama 3.2 90B Vision technology through Groq API. You can also ask follow-up questions about the image.",
    examples=[
        ["example_image1.jpg", "What safety concerns do you see?"],
        ["example_image2.jpg", "Is there any visible structural damage?"]
    ],
    cache_examples=False,
    theme="default"
)

# Launch the app
if __name__ == "__main__":
    iface.launch(debug=True)