Update app.py

app.py

@@ -16,6 +16,29 @@ for chunk in chunks:
     cleaned_chunks.append(stripped_chunk)
 print(cleaned_chunks)
 
+model = SentenceTransformer('all-MiniLM-L6-v2')
+chunk_embeddings = model.encode(cleaned_chunks, convert_to_tensor=True)
+print(chunk_embeddings)
+
+def get_top_chunks(query):
+  query_embedding = model.encode(query, convert_to_tensor=True)
+  query_embedding_normalized = query_embedding / query_embedding.norm()
+  chunk_embeddings_normalized = chunk_embeddings / chunk_embeddings.norm(dim=1, keepdim=True)
+
+  similarities = torch.matmul(chunk_embeddings_normalized, query_embedding_normalized)
+  print(similarities)
+
+  top_indices = torch.topk(similarities, k=3).indices
+  print(top_indices)
+
+  top_chunks = []
+
+  for i in top_indices:
+    chunk = chunks[i]
+    top_chunks.append(chunk)
+
+  return top_chunks
+
 client = InferenceClient("google/gemma-3-27b-it")
 
 def respond(message,history):