Update app.py

app.py

@@ -1,109 +1,32 @@
 import streamlit as st
 import pandas as pd
-import chromadb
-from sentence_transformers import SentenceTransformer
-from transformers import pipeline
-from PIL import Image
-from io import BytesIO
 import requests
-import os
-from huggingface_hub import login
-
+from io import BytesIO
+from PIL import Image
+from transformers import pipeline
 
 # --- 1. Load Recipes Dataset ---
 @st.cache_data
-def load_recipes():
-    try:
-        recipes_df = pd.read_csv("recipes.csv")
-        recipes_df = recipes_df.rename(columns={"recipe_name": "title", "directions": "instructions"})
-        recipes_df = recipes_df[['title', 'ingredients', 'instructions', 'img_src']]
-        recipes_df.fillna("", inplace=True)
-        recipes_df["ingredients"] = recipes_df["ingredients"].str.lower().str.replace(r'[^\w\s]', '', regex=True)
-        recipes_df["combined_text"] = recipes_df["title"] + " " + recipes_df["ingredients"]
-        return recipes_df
-    except Exception as e:
-        st.error(f"⚠ Error loading recipes: {e}")
-        return pd.DataFrame()
-
-recipes_df = load_recipes()
-
-# --- 2. Load SentenceTransformer Model ---
-@st.cache_resource
-def load_embedding_model():
-    return SentenceTransformer("all-MiniLM-L6-v2")  # Smaller & optimized model
-
-embedding_model = load_embedding_model()
-
-# --- 3. Initialize ChromaDB ---
-chroma_client = chromadb.PersistentClient(path="./chroma_db")
-collection = chroma_client.get_or_create_collection(name="recipe_collection")
-
-# --- 4. Generate & Store Embeddings ---
-def get_sentence_transformer_embeddings(text):
-    return embedding_model.encode(text).tolist()
+def load_data():
+    return pd.read_csv("recipes.csv")
 
-try:
-    existing_data = collection.get()
-    existing_ids = set(existing_data.get("ids", []))  # Use `.get()` for safety
-except Exception as e:
-    st.error(f"⚠ ChromaDB Error: {e}")
-    existing_ids = set()
+df = load_data()
 
-for index, row in recipes_df.iterrows():
-    recipe_id = str(index)
-    if recipe_id in existing_ids:
-        continue
-    embedding = get_sentence_transformer_embeddings(row["combined_text"])
-    if embedding:
-        collection.add(
-            embeddings=[embedding],
-            documents=[row["combined_text"]],
-            ids=[recipe_id],
-            metadatas=[{"title": row["title"], "ingredients": row["ingredients"], "instructions": row["instructions"], "img_src": row["img_src"]}]
-        )
+# --- 2. Initialize LLM Pipeline ---
+llm = pipeline("text-generation", model="facebook/opt-1.3b")
 
-# --- 5. Retrieve Similar Recipes ---
-def retrieve_recipes(query, top_k=3):
-    query_embedding = get_sentence_transformer_embeddings(query)
-    results = collection.query(query_embeddings=[query_embedding], n_results=top_k)
+# --- 3. Retrieve Recipe Function ---
+def retrieve_recipe(query):
+    matching_recipes = df[df['recipe_name'].str.contains(query, case=False, na=False)]
+    return matching_recipes if not matching_recipes.empty else None
 
-    if results and results.get("ids"):
-        recipe_indices = [int(id) for id in results["ids"][0] if id.isdigit()]
-        return recipes_df.iloc[recipe_indices] if recipe_indices else None
-    return None
-    
-hf_token = st.secrets["key"]
-if hf_token is None:
-    raise ValueError("Hugging Face token is missing. Add it as a secret in your Space.")
-login(token=hf_token)  
+# --- 4. Generate Response for Non-Recipe Queries ---
+def generate_response(query):
+    prompt = f"You are an AI assistant that only provides recipe-related responses. If the user asks something unrelated to recipes, politely decline. Query: {query}"
+    response = llm(prompt, max_length=100, do_sample=True)[0]['generated_text']
+    return response
 
-# --- 6. Load LLM Model for Generation ---
-@st.cache_resource
-def load_llm_model():
-    return pipeline("text-generation", model="mistralai/Mistral-7B-Instruct-v0.3")
-
-llm_model = load_llm_model()
-
-# --- 7. Validate Recipe Query ---
-def is_recipe_query(query):
-    # Check if the query includes any food-related words
-    food_keywords = ["recipe", "cook", "ingredient", "dish", "food", "meal","Prepare","Make"]
-    return any(keyword in query.lower() for keyword in food_keywords)
-
-def generate_recipe(query):
-    related_recipes = retrieve_recipes(query, top_k=2)
-
-    if not related_recipes or related_recipes.empty:
-        return "I couldn't find a matching recipe, but let me create one for you!"
-
-    base_text = "\n".join([f"- {r['title']}: {r['ingredients']}" for _, r in related_recipes.iterrows()])
-    # Construct the full prompt for generating a recipe
-    full_prompt = f"Using these ingredients: {query}, create a unique recipe.\n\nHere are similar recipes:\n{base_text}\n\nNow create a new recipe that uses these ideas."
-
-    response = llm_model(full_prompt, max_length=200, num_return_sequences=1)
-    return response[0]["generated_text"]
-
-# --- 8. Display Image Function ---
+# --- 5. Display Image Function ---
 def display_image(image_url, recipe_name):
     try:
         if not isinstance(image_url, str) or not image_url.startswith("http"):
@@ -112,36 +35,24 @@ def display_image(image_url, recipe_name):
         response.raise_for_status()
         image = Image.open(BytesIO(response.content))
         st.image(image, caption=recipe_name, use_container_width=True)
-    except requests.exceptions.RequestException as e:
-        st.warning(f"⚠ Image fetch error: {e}")
-        placeholder_url = "https://via.placeholder.com/300?text=No+Image"
-        st.image(placeholder_url, caption=recipe_name, use_container_width=True)
-
-# --- 9. Streamlit UI ---
-st.title("🍽️ AI Recipe Assistant")
-
-user_query = st.text_input("Enter your recipe search query:", "", key="main_query_input")
-
-if "retrieved_recipes" not in st.session_state:
-    st.session_state["retrieved_recipes"] = None
-
-if st.button("Ask AI"):
-    if user_query:
-        if is_recipe_query(user_query):  # Check if it's food-related
-            st.subheader("🤖 AI Response:")
-            response = generate_recipe(user_query)
-            st.write(response)
-
-            retrieved_recipes = retrieve_recipes(user_query)
-            if retrieved_recipes is not None and not retrieved_recipes.empty:
-                st.session_state["retrieved_recipes"] = retrieved_recipes
-                st.subheader("🍴 Found Recipes:")
-                for _, recipe in retrieved_recipes.iterrows():
-                    st.markdown(f"### {recipe['title']}")
-                    st.write(f"**Ingredients:** {recipe['ingredients']}")
-                    st.write(f"**Instructions:** {recipe['instructions']}")
-                    display_image(recipe.get('img_src', ''), recipe['title'])
-            else:
-                st.warning("⚠️ No relevant recipes found.")
-        else:
-            st.write("I can't answer that. Please ask me about recipes.")
+    except requests.exceptions.RequestException:
+        st.image("https://via.placeholder.com/300?text=No+Image", caption=recipe_name, use_container_width=True)
+
+# --- 6. Streamlit UI ---
+st.title("🍽 Recipe Finder RAG App")
+query = st.text_input("Ask me for a recipe:")
+
+if query:
+    recipe_result = retrieve_recipe(query)
+    if recipe_result is not None:
+        for _, row in recipe_result.iterrows():
+            st.subheader(row['recipe_name'])
+            st.write(f"**Prep Time:** {row['prep_time']} | **Cook Time:** {row['cook_time']} | **Total Time:** {row['total_time']}")
+            st.write(f"**Servings:** {row['servings']} | **Yield:** {row['yield']}")
+            st.write(f"**Ingredients:** {row['ingredients']}")
+            st.write(f"**Directions:** {row['directions']}")
+            st.write(f"[View Full Recipe]({row['url']})")
+            display_image(row['img_src'], row['recipe_name'])
+    else:
+        st.warning("⚠ No recipe found! Generating a response...")
+        st.write(generate_response(query))