Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| from transformers import pipeline | |
| from PIL import Image | |
| from huggingface_hub import InferenceClient | |
| import os | |
| import openai # Added import | |
| from openai.error import OpenAIError # For specific exception handling | |
| # Set page configuration | |
| st.set_page_config( | |
| page_title="Plate Mate - Your Culinary Assistant", | |
| page_icon="🍽️", | |
| layout="centered", | |
| initial_sidebar_state="expanded", | |
| ) | |
| def local_css(): | |
| st.markdown( | |
| """ | |
| <style> | |
| /* Your existing CSS styles here */ | |
| </style> | |
| """, unsafe_allow_html=True | |
| ) | |
| local_css() # Apply the CSS | |
| # Hugging Face API key | |
| API_KEY = st.secrets["HF_API_KEY"] | |
| # Initialize the Hugging Face Inference Client | |
| client = InferenceClient(api_key=API_KEY) | |
| # Load the image classification pipeline | |
| def load_image_classification_pipeline(): | |
| """ Load the image classification pipeline using a pretrained model. """ | |
| return pipeline("image-classification", model="Shresthadev403/food-image-classification") | |
| pipe_classification = load_image_classification_pipeline() | |
| # Function to generate ingredients using Hugging Face Inference Client | |
| def get_ingredients_qwen(food_name): | |
| """ Generate a list of ingredients for the given food item using Qwen NLP model. Returns a clean, comma-separated list of ingredients. """ | |
| messages = [ | |
| { | |
| "role": "user", | |
| "content": f"List only the main ingredients for {food_name}. " | |
| f"Respond in a concise, comma-separated list without any extra text or explanations." | |
| } | |
| ] | |
| try: | |
| completion = client.chat.completions.create( | |
| model="Qwen/Qwen2.5-Coder-32B-Instruct", messages=messages, max_tokens=50 | |
| ) | |
| generated_text = completion.choices[0]['message']['content'].strip() | |
| return generated_text | |
| except Exception as e: | |
| return f"Error generating ingredients: {e}" | |
| # **Set OpenAI API Key** | |
| openai.api_key = st.secrets["openai"] # Ensure you have this in your secrets | |
| # Main content | |
| st.markdown('<div class="title"><h1>PlateMate - Your Culinary Assistant</h1></div>', unsafe_allow_html=True) | |
| # Add banner image with existence check | |
| banner_image_path = "IR_IMAGE.png" | |
| if os.path.exists(banner_image_path): | |
| st.image(banner_image_path, use_container_width=True) | |
| else: | |
| st.warning(f"Banner image '{banner_image_path}' not found.") | |
| # Sidebar for model information (hidden on small screens) | |
| with st.sidebar: | |
| st.title("Model Information") | |
| st.write("**Image Classification Model**") | |
| st.write("Shresthadev403/food-image-classification") | |
| st.write("**LLM for Ingredients**") | |
| st.write("Qwen/Qwen2.5-Coder-32B-Instruct") | |
| st.markdown("---") | |
| st.markdown("<p style='text-align: center;'>Developed by Muhammad Hassan Butt.</p>", unsafe_allow_html=True) | |
| # File uploader | |
| st.subheader("Upload a food image:") | |
| uploaded_file = st.file_uploader("", type=["jpg", "png", "jpeg"]) | |
| if uploaded_file is not None: | |
| # Display the uploaded image | |
| if isinstance(uploaded_file, str): # Sample image selected | |
| if os.path.exists(uploaded_file): | |
| image = Image.open(uploaded_file) | |
| else: | |
| st.error(f"Sample image '{uploaded_file}' not found.") | |
| image = None | |
| else: # User uploaded image | |
| image = Image.open(uploaded_file) | |
| if image: | |
| st.image(image, caption="Uploaded Image", use_container_width=True) | |
| # Classification button | |
| if st.button("Classify"): | |
| with st.spinner("Classifying..."): | |
| try: | |
| # Make predictions | |
| predictions = pipe_classification(image) | |
| if predictions: | |
| # Display only the top prediction | |
| top_food = predictions[0]['label'] | |
| confidence = predictions[0]['score'] | |
| st.header(f"🍽️ Food: {top_food} ({confidence*100:.2f}% confidence)") | |
| # Generate and display ingredients for the top prediction | |
| st.subheader("📝 Ingredients") | |
| try: | |
| ingredients = get_ingredients_qwen(top_food) | |
| st.write(ingredients) | |
| except Exception as e: | |
| st.error(f"Error generating ingredients: {e}") | |
| # **Healthier Alternatives using OpenAI API** | |
| st.subheader("💡 Healthier Alternatives") | |
| try: | |
| response = openai.ChatCompletion.create( | |
| model="gpt-4", # You can choose the model you prefer | |
| messages=[ | |
| { | |
| "role": "system", | |
| "content": "You are a helpful assistant specializing in providing healthy alternatives to various dishes." | |
| }, | |
| { | |
| "role": "user", | |
| "content": f"What's a healthy {top_food} recipe, and why is it healthy?" | |
| } | |
| ], | |
| max_tokens=200, # Adjust as needed | |
| temperature=0.7, # Adjust creativity level as needed | |
| ) | |
| # Corrected access to 'content' | |
| result = response['choices'][0]['message']['content'].strip() | |
| st.write(result) | |
| except OpenAIError as e: | |
| st.error(f"OpenAI API error: {e}") | |
| except Exception as e: | |
| st.error(f"Unable to generate healthier alternatives: {e}") | |
| else: | |
| st.error("No predictions returned from the classification model.") | |
| except Exception as e: | |
| st.error(f"Error during classification: {e}") | |
| else: | |
| st.info("Please select or upload an image to get started.") | |