Update app.py

app.py

@@ -26,6 +26,55 @@ def preprocess_text(text):
 
   return cleaned_chunks
 
+model = SentenceTransformer('all-MiniLM-L6-v2')
+
+def create_embeddings(text_chunks):
+  chunk_embeddings = model.encode(text_chunks, convert_to_tensor=True) # Replace ... with the text_chunks list
+
+  print(chunk_embeddings)
+
+  print(chunk_embeddings.shape)
+
+  return chunk_embeddings
+
+chunk_embeddings = create_embeddings(cleaned_chunks)# Complete this line
+
+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 top_chunks
+
+top_results = get_top_chunks("How does water get into the sky?", chunk_embeddings, cleaned_chunks) # Complete this line
+
+print(top_results)
+
 
 cleaned_chunks = preprocess_text(knowledge_base)