visual changes (#1)

- visual changes (c5072c980c7e585ec01ac5c7f1bd0b782c397116)


Co-authored-by: David Rodriguez <drod75@users.noreply.huggingface.co>

app.py

@@ -282,27 +282,45 @@ selected_dish = st.sidebar.selectbox(
 )
 
 # Right title
-st.title("Results")
+st.title("Welcome to FOOD CHAIN!")
+with st.expander("**What is FOOD CHAIN?**"):
+    st.markdown(
+        """
+        The project aims to use machine learning and computer vision techniques to analyze food images 
+        and identify them. By using diverse datasets, the model will learn to recognize dishes based on 
+        visual features. Our project aims to inform users about what it is they are eating, including 
+        potential nutritional value and an AI generated response on how their dish might have been prepared. 
+        We want users to have an easy way to figure out what their favorite foods contain, to know any 
+        allergens in the food and to better connect to the food around them. This tool can also tell users 
+        the calories of their dish, they can figure out the nutrients with only a few steps!
+
+        Thank you for using our project!
+
+        Made by the Classify Crew: [Contact List](https://linktr.ee/classifycrew)
+        """
+    )
 #################
 
 # Image Classification Section
 if uploaded_image and query:
-    # Open the image
-    input_image = Image.open(uploaded_image)
-
-    # Display the image
-    st.image(input_image, caption="Uploaded Image.", use_container_width=True)
-        
-    predictions = classifyImage(input_image)
-    fpredictions = ""
-
-    # Show the top predictions with percentages
-    st.write("Top Predictions:")
-    for class_name, confidence in predictions:
-        if int(confidence) > 0.05:
-            fpredictions += f"{class_name}: {confidence:.2f}%,"
-        st.write(f"{class_name}: {confidence:.2f}%")
-    print(fpredictions)
+    with st.expander("**Food Classification**", expanded=True, icon=':material/search_insights:'):
+        st.title("Results: Image Classification")
+        # Open the image
+        input_image = Image.open(uploaded_image)
+    
+        # Display the image
+        st.image(input_image, caption="Uploaded Image.", use_container_width=True)
+            
+        predictions = classifyImage(input_image)
+        fpredictions = ""
+    
+        # Show the top predictions with percentages
+        st.write("Top Predictions:")
+        for class_name, confidence in predictions:
+            if int(confidence) > 0.05:
+                fpredictions += f"{class_name}: {confidence:.2f}%,"
+            st.write(f"{class_name}: {confidence:.2f}%")
+        print(fpredictions)
 
     # call openai to pick the best classification result based on query
     openAICall = [
@@ -325,31 +343,38 @@ if uploaded_image and query:
     openAIresponse = llm.invoke(openAICall)
     print("AI CALL RESPONSE: ", openAIresponse.content)
 
-    # RAG the openai response and display
-    print("RAG INPUT", openAIresponse.content + " " + query)
-    RAGresponse = get_response(openAIresponse.content + " " + query)
-    display_response(RAGresponse)
+    with st.expander("Recipe Generation", expanded=True, icon=':material/menu_book:'):
+         st.title('Results: RAG')
+        # RAG the openai response and display
+        print("RAG INPUT", openAIresponse.content + " " + query)
+        RAGresponse = get_response(openAIresponse.content + " " + query)
+        display_response(RAGresponse)
 elif uploaded_image is not None:
-    # Open the image
-    input_image = Image.open(uploaded_image)
-
-    # Display the image
-    st.image(input_image, caption="Uploaded Image.", use_column_width=True)
-
-    # Classify the image and display the result
-    predictions = classifyImage(input_image)
-    fpredictions = ""
-
-    # Show the top predictions with percentages
-    st.write("Top Predictions:")
-    for class_name, confidence in predictions:
-        if int(confidence) > 0.05:
-            fpredictions += f"{class_name}: {confidence:.2f}%,"
-        st.write(f"{class_name}: {confidence:.2f}%")
-    print(fpredictions)
+    with st.expander("**Food Classification**", expanded=True, icon=':material/search_insights:'):
+        st.title("Results: Image Classification")
+        # Open the image
+        input_image = Image.open(uploaded_image)
+    
+        # Display the image
+        st.image(input_image, caption="Uploaded Image.", use_column_width=True)
+    
+        # Classify the image and display the result
+        predictions = classifyImage(input_image)
+        fpredictions = ""
+    
+        # Show the top predictions with percentages
+        st.write("Top Predictions:")
+        for class_name, confidence in predictions:
+            if int(confidence) > 0.05:
+                fpredictions += f"{class_name}: {confidence:.2f}%,"
+            st.write(f"{class_name}: {confidence:.2f}%")
+        print(fpredictions)
 
 elif query:
-    response = get_response(query)
-    display_response(response)
+     with st.expander("**Recipe Generation**", expanded=True, icon=':material/menu_book:'):
+        st.title("Results: RAG")
+        response = get_response(query)
+        display_response(response)
 else:
-    st.write("Please input an image and/or a prompt.")
+    st.warning("Please input an image and/or a prompt.", icon=':material/no_meals:')
+