Upload 3 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+recipe_index.faiss filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,131 @@
+import gradio as gr
+from datasets import load_dataset
+from sentence_transformers import SentenceTransformer
+import faiss
+import numpy as np
+import os
+from transformers import pipeline
+import time
+
+# --- 1. DATA LOADING AND PREPROCESSING ---
+print("===== Application Startup =====")
+start_time = time.time()
+
+# Load dataset
+dataset = load_dataset("corbt/all-recipes", split="train[:20000]")
+
+# Preprocessing functions
+def extract_title_and_ingredients(sample):
+    extraction = sample['input'][:sample['input'].find("Directions")]
+    return {"text_for_embedding": extraction}
+
+def extract_each_feature(sample):
+    title = sample['input'][:sample['input'].find("\\n")]
+    ingredients = sample['input'][sample['input'].find("Ingredients")+len("Ingredients:\\n"):sample['input'].find("Directions")].strip()
+    directions = sample['input'][sample['input'].find("Directions")+len("Directions:\\n"):].strip()
+    return {"title": title, "ingredients": ingredients, "directions": directions}
+
+# Apply preprocessing
+dataset = dataset.map(extract_title_and_ingredients)
+dataset = dataset.map(extract_each_feature)
+
+# --- 2. EMBEDDING AND RECOMMENDATION ENGINE ---
+model_name = "all-MiniLM-L6-v2"
+embedding_model = SentenceTransformer(f"sentence-transformers/{model_name}")
+
+# Compute embeddings
+print("Loading dataset and embedding model...")
+embeddings = embedding_model.encode(dataset['text_for_embedding'], show_progress_bar=True)
+embeddings = np.array(embeddings, dtype=np.float32)
+
+# Build FAISS index
+dimension = embeddings.shape[1]
+index = faiss.IndexFlatL2(dimension)
+index.add(embeddings)
+print(f"Index is ready. Total vectors in index: {index.ntotal}")
+
+# --- 3. SYNTHETIC GENERATION ---
+generator = pipeline('text-generation', model='gpt2')
+
+def get_recommendations_and_generate(query_ingredients, k=3):
+    # 1. Get Recommendations
+    query_vector = embedding_model.encode([query_ingredients])
+    query_vector = np.array(query_vector, dtype=np.float32)
+    distances, indices = index.search(query_vector, k)
+    
+    results = []
+    for i, idx_numpy in enumerate(indices[0]):
+        idx = int(idx_numpy) # FIX: Convert numpy.int64 to standard Python int
+        recipe = {
+            "title": dataset[idx]['title'],
+            "ingredients": dataset[idx]['ingredients'],
+            "directions": dataset[idx]['directions']
+        }
+        results.append(recipe)
+        
+    # 2. Generate a new recipe idea
+    prompt = f"Create a short, simple recipe title and a list of ingredients using: {query_ingredients}."
+    generated_text = generator(prompt, max_length=100, num_return_sequences=1)[0]['generated_text']
+    
+    # Clean up generated text to be more readable
+    # (This is a basic cleanup, can be improved)
+    generated_recipe_parts = generated_text.split("Ingredients:")
+    generated_title = generated_recipe_parts[0].replace(prompt.replace(f"using: {query_ingredients}",""), "").strip()
+    generated_ingredients = generated_recipe_parts[1].strip() if len(generated_recipe_parts) > 1 else "Could not determine ingredients."
+    
+    generated_recipe = {
+        "title": generated_title,
+        "ingredients": generated_ingredients,
+        "directions": "This is an AI-generated idea. Directions are not provided."
+    }
+    
+    return results[0], results[1], results[2], generated_recipe
+
+# --- 4. GRADIO USER INTERFACE ---
+def format_recipe(recipe):
+    if not recipe or not recipe['title']:
+        return "### No recipe found."
+    return f"### {recipe['title']}\n**Ingredients:**\n{recipe['ingredients']}\n\n**Directions:**\n{recipe['directions']}"
+
+def recipe_wizard(ingredients):
+    rec1, rec2, rec3, gen_rec = get_recommendations_and_generate(ingredients)
+    return format_recipe(rec1), format_recipe(rec2), format_recipe(rec3), format_recipe(gen_rec)
+
+end_time = time.time()
+print(f"Models and data loaded in {end_time - start_time:.2f} seconds.")
+
+# Gradio Interface
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# 🍳 RecipeWizard AI")
+    gr.Markdown("Enter the ingredients you have, and get recipe recommendations plus a new AI-generated idea!")
+    
+    with gr.Row():
+        ingredient_input = gr.Textbox(label="Your Ingredients", placeholder="e.g., chicken, rice, tomatoes, garlic")
+        submit_btn = gr.Button("Get Recipes")
+
+    with gr.Row():
+        with gr.Column():
+            gr.Markdown("### Recommended Recipes")
+            output_rec1 = gr.Markdown()
+            output_rec2 = gr.Markdown()
+            output_rec3 = gr.Markdown()
+        with gr.Column():
+            gr.Markdown("### ✨ AI-Generated Idea")
+            output_gen = gr.Markdown()
+
+    submit_btn.click(
+        fn=recipe_wizard,
+        inputs=ingredient_input,
+        outputs=[output_rec1, output_rec2, output_rec3, output_gen]
+    )
+    
+    gr.Examples(
+        examples=[
+            ["chicken, broccoli, cheese"],
+            ["ground beef, potatoes, onions"],
+            ["flour, sugar, eggs, butter"]
+        ],
+        inputs=ingredient_input
+    )
+
+demo.launch()

recipe_index.faiss

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90b9a5c8797e28a0fe4130d9af7ccdb897d0849110ea43765aee3b7b670b14ef
+size 30720045

requirements.txt

@@ -0,0 +1,8 @@
+torch==2.1.0
+faiss-cpu==1.7.4
+gradio==4.8.0
+pyarrow==14.0.1
+datasets==2.15.0
+transformers==4.35.2
+sentence-transformers==2.3.1
+huggingface-hub==0.19.4