Update app.py

app.py

@@ -117,9 +117,9 @@ Use the provided context to generate a result based on the following JSON format
   "n_steps": 0,
   "description": "A GENERAL description of the recipe goes here.",
   "ingredients": [
-    "ingredient1",
-    "ingredient2",
-    "ingredient3"
+    "0 tablespoons ingredient1",
+    "0 cups ingredient2",
+    "0 teaspoons ingredient3"
   ],
   "n_ingredients": 0,
   "formatted_nutrition": [
@@ -145,6 +145,7 @@ Instructions:
 4. Base the response on simple, healthy, and accessible ingredients and techniques.
 5. Rewrite the description in third person
 6. If context does not match {question} at all, return []
+7. Include the ingredient amounts and say them in the steps.
 
 When choosing a recipe from the context, FOLLOW these instructions:
 0. If context does not match {question} at all, return []
@@ -176,8 +177,10 @@ rag_chain = (
 )
 
 def get_response(query):
-    print("get_response query: ", query)
-    return rag_chain.invoke(query)
+    if query:
+        print("get_response query: ", query)
+        return rag_chain.invoke(query)
+    return ""
 
 
 ##############################################
@@ -292,8 +295,9 @@ selected_dish = st.sidebar.selectbox(
     options=class_names,
     index=0  
 )
+st.sidebar.write("Upload an image and/or enter a query to get started! Explore our trained dish types listed below for guidance.")
 
-# Right title
+# Main title
 st.title("Welcome to FOOD CHAIN!")
 with st.expander("**What is FOOD CHAIN?**"):
     st.markdown(
@@ -313,38 +317,39 @@ with st.expander("**What is FOOD CHAIN?**"):
     )
 #################
 
-if not uploaded_image: 
-    placeholder = Image.open("dish-placeholder.jpg")
-    st.image(placeholder, caption="Placeholder Image.", use_container_width=True)
-    st.write("Top Predictions:")
-    st.markdown(f"*Donuts*: 98.11%")
+col1, col2 = st.columns(2)
+with col1:
+    if not uploaded_image: 
+        placeholder = Image.open("dish-placeholder.jpg")
+        st.image(placeholder, caption="Placeholder Image.", use_container_width=True)
+        st.write("Top Predictions:")
+        st.markdown(f"*Donuts*: 98.11%")
     
-st.sidebar.write("Upload an image and/or enter a query to get started! Explore our trained dish types listed below for guidance.")
-
 # Image Classification Section
 if uploaded_image and recipe_submit:
     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)
-        print("Predictions: ", predictions)
-        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}%,"
-            if int(confidence) > 5:
-                class_name = class_name.replace("_", " ")
-                class_name = class_name.title()
-                st.markdown(f"*{class_name}*: {confidence:.2f}%")
-        print(fpredictions)
+
+        with col1:
+            # Display the image
+            st.image(input_image, caption="Uploaded Image.", use_container_width=True)
+                
+            predictions = classifyImage(input_image)
+            print("Predictions: ", predictions)
+            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}%,"
+                if int(confidence) > 5:
+                    class_name = class_name.replace("_", " ")
+                    class_name = class_name.title()
+                    st.markdown(f"*{class_name}*: {confidence:.2f}%")
+            print(fpredictions)
 
     # call openai to pick the best classification result based on query
     openAICall = [
@@ -379,50 +384,52 @@ if uploaded_image and recipe_submit:
             """
         ),
     ]
-
-    if query:
-        # Call the OpenAI API
-        openAIresponse = llm.invoke(openAICall)
-        print("AI CALL RESPONSE: ", openAIresponse.content, "END AI CALL RESONSE")
-    
-        RAGresponse = get_response(openAIresponse.content + " " + query)
-    else:
-        RAGresponse = get_response(predictions[0][0])
-    print("RAGresponse: ", RAGresponse)
-    
-    with st.expander("Recipe Generation", expanded=True, icon=':material/menu_book:'):
-        st.title('Results: RAG')
-        display_response(RAGresponse)
+    with col2:
+        if query:
+            # Call the OpenAI API
+            openAIresponse = llm.invoke(openAICall)
+            print("AI CALL RESPONSE: ", openAIresponse.content, "END AI CALL RESONSE")
+        
+            RAGresponse = get_response(openAIresponse.content + " " + query)
+        else:
+            RAGresponse = get_response(predictions[0][0])
+        print("RAGresponse: ", RAGresponse)
+        
+        with st.expander("Recipe Generation", expanded=True, icon=':material/menu_book:'):
+            st.title('Results: RAG')
+            display_response(RAGresponse)
 elif uploaded_image is not None:
-    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)
-    
-        # 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}%,"
-            if int(confidence) > 5:
-                class_name = class_name.replace("_", " ")
-                class_name = class_name.title()
-                st.markdown(f"*{class_name}*: {confidence:.2f}%")
-        print(fpredictions)
+    with col1:
+        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)
+        
+            # 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}%,"
+                if int(confidence) > 5:
+                    class_name = class_name.replace("_", " ")
+                    class_name = class_name.title()
+                    st.markdown(f"*{class_name}*: {confidence:.2f}%")
+            print(fpredictions)
 
 elif recipe_submit:
-    response = get_response(query)
-    print(response)
-    with st.expander("**Recipe Generation**", expanded=True, icon=':material/menu_book:'):
-        st.title("Results: RAG")
-        display_response(response)
+    with col2:
+        response = get_response(query)
+        print(response)
+        with st.expander("**Recipe Generation**", expanded=True, icon=':material/menu_book:'):
+            st.title("Results: RAG")
+            display_response(response)
 else:
     st.warning("Please input an image and/or a prompt.", icon=':material/no_meals:')