Update app.py

app.py

@@ -1 +1,94 @@
-import gradio as gr
+from huggingface_hub import InferenceClient
+#step 1 from semantic search
+from sentence_transformers import SentenceTransformer
+import torch
+import gradio as gr
+import random
+client = InferenceClient("Qwen/Qwen2.5-72B-Instruct")
+#step 2 from semantic search read file
+# Open the water_cycle.txt file in read mode with UTF-8 encoding
+with open("books_file.txt", "r", encoding="utf-8") as file:
+  # Read the entire contents of the file and store it in a variable
+  books_file_text = file.read()
+# Print the text below
+print(books_file_text)
+#step 3 from semantix 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:
+    clean_chunk = chunk.strip()
+    if(len(clean_chunk) >= 0):
+      cleaned_chunks.append(clean_chunk)
+  # 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(books_file_text) # Complete this line
+#step 4 from 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
+#step 5 from semantic search
+# 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=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:
+    top_chunks.append(text_chunks[i])
+  # Return the list of most relevant chunks
+  return top_chunks
+def respond(message, history):
+    best_next_read = get_top_chunks(message, chunk_embeddings, cleaned_chunks)
+    print(best_next_red)
+    str_read_chunks = "\n".join(best_next_red)
+    messages = [
+        {"role":"system",
+        "content": "You are a Gen Z and Gen Alpha-friendly chatbot that helps teenagers find their next best book to read. Speak naturally and casually, like someone from Gen Z. Only recommend books, never anything else. Use only the books in our database YOU CAN NEVER USE OUTSIDE DATA ONLY TAKE DATA FROM OUR DATABASE! Match show suggestions to the user's age using. If they don’t share their age, assume they’re Gen Z or Gen Alpha and use those guidelines. If the user is not Gen Z or Gen Alpha, you can recommend any book from the database. If they give you a genre, use it to guide your recommendation. If they don’t, pick something fun or relevant. If they mention a book they liked, match the genre of that book to recommend something similar. If nothing matches all their preferences, suggest the most similar book from the database. You got this! Remember you can ONLY take data from " + str_read_chunks_chunks + " ."
+        }
+    ]
+    if history:
+        messages.extend(history)
+    messages.append(
+        {'role':'user',
+        'content':message}
+    )
+    response = client.chat_completion(
+        messages, max_tokens = 700, temperature=1.3, top_p=0.6
+    )
+    return response['choices'][0]['message']['content'].strip()
+chatbot = gr.ChatInterface(respond, type="messages")
+chatbot.launch()