app.py

import streamlit as st
from datasets import load_dataset
from sentence_transformers import SentenceTransformer
import chromadb

# Load dataset
# Load dataset
def load_recipes():
    try:
        dataset = load_dataset("mbien/recipe_nlg", split="train", trust_remote_code=True)
        print("✅ Dataset loaded successfully!")
        return dataset
    except Exception as e:
        print(f"❌ Error loading dataset: {e}")
        return None

recipes_df = load_recipes()

if recipes_df is None:
    st.error("❌ Failed to load dataset! Check internet or dataset availability.")
    st.stop()  # Stops Streamlit from running further if the dataset isn't loaded

# Load embedding model
@st.cache_resource
def load_embedding_model():
    return SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")

embed_model = load_embedding_model()

# Initialize ChromaDB
chroma_client = chromadb.PersistentClient(path="./chroma_db")  # Saves vectors
recipe_collection = chroma_client.get_or_create_collection(name="recipes")

# Ensure recipes_df is iterable
if isinstance(recipes_df, list) or isinstance(recipes_df, dict):
    if recipe_collection.count() == 0:
        st.info("Indexing recipes... This will take a few minutes.")
        for i, recipe in enumerate(recipes_df):
            title = recipe.get("title", "Unknown Title")  # Handle missing keys
            ingredients = ", ".join(recipe.get("ingredients", []))
            instructions = recipe.get("instructions", "No instructions available")
            
            embedding = embed_model.encode(title).tolist()
            recipe_collection.add(
                ids=[str(i)],
                embeddings=[embedding],
                metadatas=[{"title": title, "ingredients": ingredients, "index": i}],
            )
else:
    st.error("❌ Dataset is not in the correct format!")

# UI
st.title("🍽️ AI Recipe Finder with ChromaDB RAG")
query = st.text_input("🔍 Search for a recipe (e.g., pasta, cake)")

if query:
    query_embedding = embed_model.encode(query).tolist()
    results = recipe_collection.query(
        query_embeddings=[query_embedding], n_results=5
    )

    st.subheader("🔎 Most relevant recipes:")
    for result in results["metadatas"][0]:
        index = result["index"]
        recipe = recipes_df[index]
        st.write(f"**🍴 {recipe.get('title', 'No title available')}**")
        st.write(f"**Ingredients:** {', '.join(recipe.get('ingredients', []))}")
        st.write(f"**Instructions:** {recipe.get('instructions', 'No instructions available')}")
        st.write("---")
else:
    st.info("Type a recipe name to find similar recipes.")