import gradio as gr import requests #------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ # Step 1 - Semantic Search from sentence_transformers import SentenceTransformer import torch # Step 2 - Semantic Search # Open the water_cycle.txt file in read mode with UTF-8 encoding with open("water_cycle.txt", "r", encoding="utf-8") as file: # Read the entire contents of the file and store it in a variable water_cycle_text = file.read() # Print the text below print(water_cycle_text) # Step 3 - Semantic Search def preprocess_text(text): # Strip extra whitespace from the beginning and the end of the text cleaned_text = text.strip() # Split the cleaned_text by every newline character (\n) chunks = cleaned_text.split("\n") # Create an empty list to store cleaned chunks cleaned_chunks = [] # Write your for-in loop below to clean each chunk and add it to the cleaned_chunks list for chunk in chunks: stripped_chunk = chunk.strip() if len(stripped_chunk) > 0: cleaned_chunks.append(stripped_chunk) # Print cleaned_chunks print(cleaned_chunks) # Print the length of cleaned_chunks print(len(cleaned_chunks)) # Return the cleaned_chunks return cleaned_chunks # Step 4 - Semantic Search # Load the pre-trained embedding model that converts text to vectors model = SentenceTransformer('all-MiniLM-L6-v2') def create_embeddings(text_chunks): # Convert each text chunk into a vector embedding and store as a tensor chunk_embeddings = model.encode(text_chunks, convert_to_tensor=True) # Replace ... with the text_chunks list # Print the chunk embeddings print(chunk_embeddings) # Print the shape of chunk_embeddings print(chunk_embeddings.shape) # Return the chunk_embeddings return chunk_embeddings # Call the create_embeddings function and store the result in a new chunk_embeddings variable chunk_embeddings = create_embeddings(cleaned_chunks) # Complete this line # Call the preprocess_text function and store the result in a cleaned_chunks variable #cleaned_chunks = preprocess_text(water_cycle_text) # Complete this line # Step 5 - Semantic Search def get_top_chunks(query, chunk_embeddings, text_chunks): # Convert the query text into a vector embedding query_embedding = model.encode(query, convert_to_tensor = True) # Complete this line # Normalize the query embedding to unit length for accurate similarity comparison query_embedding_normalized = query_embedding / query_embedding.norm() # Normalize all chunk embeddings to unit length for consistent comparison chunk_embeddings_normalized = chunk_embeddings / chunk_embeddings.norm(dim=1, keepdim=True) # Calculate cosine similarity between query and all chunks using matrix multiplication similarities = torch.matmul(chunk_embeddings_normalized, query_embedding_normalized) # Complete this line # Print the similarities print(similarities) # Find the indices of the 3 chunks with highest similarity scores top_indices = torch.topk(similarities, k=3).indices # Print the top indices print(top_indices) # Create an empty list to store the most relevant chunks top_chunks = [] # Loop through the top indices and retrieve the corresponding text chunks for i in top_indices: chunk = text_chunks[i] top_chunks.append(chunk) # Return the list of most relevant chunks return top_chunks # Step 6 - Semantic Search # Call the get_top_chunks function with the original query top_results = get_top_chunks("How does water get into the sky", chunk_embeddings, cleaned_chunks) # Complete this line # Print the top results print(top_results) #------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ SPOONACULAR_API_KEY = "71259036cfb3405aa5d49c1220a988c5" recipe_id_map = {} # search for recipes def search_recipes(ingredient, cuisine, dietary): global recipe_id_map url = "https://api.spoonacular.com/recipes/complexSearch" params = { "query": ingredient, "cuisine": cuisine, "diet": dietary, "number": 3, "apiKey": SPOONACULAR_API_KEY } res = requests.get(url, params=params) data = res.json() if "results" not in data or not data["results"]: recipe_id_map = {} return gr.update(choices=[], visible=True, label="No recipes found"), gr.update(value="No recipes found.") recipe_id_map = {r["title"]: r["id"] for r in data["results"]} return gr.update(choices=list(recipe_id_map.keys()), visible=True, label="Select a recipe"), gr.update(value="Select a recipe from the dropdown above.") # get recipe details def get_recipe_details(selected_title): if not selected_title or selected_title not in recipe_id_map: return "Please select a valid recipe." recipe_id = recipe_id_map[selected_title] url = f"https://api.spoonacular.com/recipes/{recipe_id}/information" params = {"apiKey": SPOONACULAR_API_KEY} res = requests.get(url, params=params) data = res.json() title = data.get("title", "Unknown Title") time = data.get("readyInMinutes", "N/A") instructions = data.get("instructions") or "No instructions available." return f"### 🍽️ {title}\n**⏱️ Cook Time:** {time} minutes\n\n**📋 Instructions:**\n{instructions}" # UI with gr.Blocks() as demo: gr.Markdown("## 🥗 The BiteBot") with gr.Row(): ingredient = gr.Textbox(label="Preferred Ingredient", placeholder="e.g., chicken") cuisine = gr.Textbox(label="Preferred Cuisine", placeholder="e.g., Indian") diet = gr.Textbox(label="Dietary Restrictions", placeholder="e.g., vegetarian") search_button = gr.Button("Search Recipes") recipe_dropdown = gr.Dropdown(label="Select a recipe", visible=False) recipe_output = gr.Markdown() search_button.click( fn=search_recipes, inputs=[ingredient, cuisine, diet], outputs=[recipe_dropdown, recipe_output] ) recipe_dropdown.change( fn=get_recipe_details, inputs=recipe_dropdown, outputs=recipe_output ) demo.launch()