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 (2).py

@@ -0,0 +1,199 @@
+import gradio as gr
+from datasets import load_dataset
+from sentence_transformers import SentenceTransformer
+import faiss
+import numpy as np
+from transformers import pipeline
+import time
+
+# --- 1. DATA LOADING AND PREPROCESSING (FINAL FIX) ---
+print("===== Application Startup =====")
+start_time = time.time()
+
+# Load dataset and limit to the first 20,000 rows
+dataset = load_dataset("corbt/all-recipes", split="train[:20000]")
+
+# Preprocessing functions to extract features from the raw text
+def extract_title_and_ingredients(sample):
+    extraction = sample['input'][:sample['input'].find("Directions")]
+    return {"text_for_embedding": extraction}
+
+def extract_each_feature(sample):
+    """
+    FIXED: More robustly extracts recipe features and cleans duplicated content.
+    """
+    full_text = sample['input']
+    
+    # Extract Title
+    title = full_text[:full_text.find("\\n")]
+    
+    # Extract Ingredients
+    ingredients = "Not available"
+    if "Ingredients:" in full_text:
+        start_ing = full_text.find("Ingredients:") + len("Ingredients:")
+        end_ing = full_text.find("Directions:")
+        if end_ing > start_ing:
+            ingredients = full_text[start_ing:end_ing].strip()
+
+    # Extract and clean Directions
+    directions = "Not available"
+    if "Directions:" in full_text:
+        start_dir = full_text.find("Directions:") + len("Directions:")
+        # Take the text after the first "Directions:"
+        temp_directions = full_text[start_dir:].strip()
+        # If "Ingredients:" appears again, it's a duplicate. Cut it off.
+        if "Ingredients:" in temp_directions:
+            end_dir = temp_directions.find("Ingredients:")
+            directions = temp_directions[:end_dir].strip()
+        else:
+            directions = temp_directions
+
+    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 ---
+print("Loading embedding model...")
+model_name = "all-MiniLM-L6-v2"
+embedding_model = SentenceTransformer(f"sentence-transformers/{model_name}")
+
+print("Generating embeddings...")
+embeddings = embedding_model.encode(dataset['text_for_embedding'], show_progress_bar=True)
+embeddings = np.array(embeddings, dtype=np.float32)
+
+print("Building 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 (IMPROVED MODEL AND PROMPT) ---
+print("Loading generative model...")
+# Switched back to gpt2 for better instruction following
+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 idx_numpy in indices[0]:
+        idx = int(idx_numpy) 
+        recipe = {
+            "title": dataset[idx]['title'],
+            "ingredients": dataset[idx]['ingredients'],
+            "directions": dataset[idx]['directions']
+        }
+        results.append(recipe)
+        
+    # 2. Generate a new recipe with a better "few-shot" prompt
+    prompt = f"""Given the ingredients: {query_ingredients}, create a complete recipe.
+
+### Title ###
+[A creative recipe title]
+
+### Ingredients ###
+- [List of ingredients]
+
+### Directions ###
+1. [First step]
+2. [Second step]
+3. [And so on...]
+
+### Title ###
+"""
+    # Generate the recipe text
+    generated_outputs = generator(prompt, max_new_tokens=250, num_return_sequences=1, pad_token_id=50256)
+    generated_text = generated_outputs[0]['generated_text'].replace(prompt, "").strip()
+
+    # 3. More robustly parse the generated text
+    try:
+        title = "AI Generated Recipe"
+        ingredients = ""
+        directions = ""
+
+        if "### Ingredients ###" in generated_text:
+            parts = generated_text.split("### Ingredients ###")
+            title = parts[0].strip()
+            rest = parts[1]
+            if "### Directions ###" in rest:
+                dir_parts = rest.split("### Directions ###")
+                ingredients = dir_parts[0].strip()
+                directions = dir_parts[1].strip()
+            else:
+                ingredients = rest.strip()
+        else:
+            directions = generated_text # Fallback
+
+        generated_recipe = {
+            "title": title,
+            "ingredients": ingredients,
+            "directions": directions
+        }
+    except Exception as e:
+        print(f"Error parsing generated text: {e}")
+        generated_recipe = {
+            "title": "AI Generated Recipe (Parsing Error)",
+            "ingredients": "Could not determine ingredients.",
+            "directions": generated_text
+        }
+    
+    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(scale=2):
+            gr.Markdown("### Recommended Recipes")
+            output_rec1 = gr.Markdown()
+            output_rec2 = gr.Markdown()
+            output_rec3 = gr.Markdown()
+        with gr.Column(scale=1):
+            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 (2).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