Update app.py

app.py

@@ -1,93 +1,122 @@
 from huggingface_hub import InferenceClient
+
 #STEP1FROMSEMANTICSEARCH (import libraries)
 from sentence_transformers import SentenceTransformer
 import torch
 import gradio as gr
 import random
+
 client=InferenceClient("Qwen/Qwen2.5-72B-Instruct")
 #deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
+
 # Open the water_cycle.txt file in read mode with UTF-8 encoding - step 2 from semantic search
 with open("recipes.txt", "r", encoding="utf-8") as file:
-  # Read the entire contents of the file and store it in a variable
-  recipes_text = file.read()
+    # Read the entire contents of the file and store it in a variable
+    recipes_text = file.read()
+
 # Print the text below
 print(recipes_text)
+
+#Step 3
 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(".")
-  # 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:
-    clean = chunk.strip()
-    if len(chunk)>0:
-      cleaned_chunks.append(clean)
-  # Print cleaned_chunks
-  print(cleaned_chunks)
-  # Print the length of cleaned_chunks
-  print(len(cleaned_chunks))
-  # Return the cleaned_chunks
-  return cleaned_chunks
+    # 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(".")
+    
+    # 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:
+        clean = chunk.strip()
+        
+        if len(chunk)>0:
+            cleaned_chunks.append(clean)
+            
+    # Print cleaned_chunks
+    print(cleaned_chunks)
+    
+    # Print the length of cleaned_chunks
+    print(len(cleaned_chunks))
+    
+    # Return the cleaned_chunks
+    return cleaned_chunks
+    
 # Call the preprocess_text function and store the result in a cleaned_chunks variable
 cleaned_chunks = preprocess_text(recipes_text) # Complete this line
+
+#Step 4
 # 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
+    # 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
+
 #Step 5
 # Define a function to find the most relevant text chunks for a given query, chunk_embeddings, and text_chunks
 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=1).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:
-    top_chunks.append(i)
-    print(top_chunks)
-  # Return the list of most relevant chunks
-  return top_chunks
-best_recipes_chunk = get_top_chunks(message, chunk_embeddings, cleaned_chunks)
-print(best_recipes_chunk)
+    # 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=1).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:
+        top_chunks.append(i)
+        print(top_chunks)
+        
+    # Return the list of most relevant chunks
+    return top_chunks
+
 def respond(message, history):
-    #responses = ["Yes", "No"]
-    #return random.choice(responses)
-    messages = [
-        {"role":"system",
-         "content": "You are a chatbot that is a nutrition expert and helps people with their nutritional goals. You help them plan meals."
-        }
-    ]
+    best_recipes_chunk = get_top_chunks(message, chunk_embeddings, cleaned_chunks)
+    print(best_recipes_chunk)
+    
+    messages = [{"role":"system","content": "You are a chatbot that is a nutrition expert and helps people with their nutritional goals. You help them plan meals based on" + best_recipes_chunk + "."}]
+    
     if history:
         messages.extend(history)
-    messages.append(
-        {"role":"user",
-        "content": "message"}
-    )
-    response = client.chat_completion(messages, max_tokens=100, temperature=1.3, top_p=.2)
+    
+    messages.append({"role":"user","content": "message"})
+    
+    response = client.chat_completion(messages, max_tokens = 100, temperature = 1.3, top_p = 0.3)
+    
     #temperature and top_p control randomness
     return response['choices'][0]['message']['content'].strip()
+
 chatbot = gr.ChatInterface(respond, type="messages")
 chatbot.launch()