Update app.py

app.py

@@ -87,22 +87,33 @@ if uploaded_files:
         index = VectorStoreIndex(nodes=nodes, storage_context=storage_context)
 
         # Retrieval
-        bm25_retriever = BM25Retriever.from_defaults(nodes=nodes, similarity_top_k=3)
+        bm25_retriever = BM25Retriever.from_defaults(nodes=nodes, similarity_top_k=1)
         vector_retriever = index.as_retriever(similarity_top_k=3)
 
         # Hybrid Retriever class
         class HybridRetriever(BaseRetriever):
             def __init__(self, vector_retriever, bm25_retriever):
-                self.vector_retriever = vector_retriever
+                # self.vector_retriever = vector_retriever
                 self.bm25_retriever = bm25_retriever
                 super().__init__()
 
+            # def _retrieve(self, query, **kwargs):
+            #     bm25_nodes = self.bm25_retriever.retrieve(query, **kwargs)
+            #     vector_nodes = self.vector_retriever.retrieve(query, **kwargs)
+            #     all_nodes = []
+            #     node_ids = set()
+            #     for n in bm25_nodes + vector_nodes:
+            #         if n.node.node_id not in node_ids:
+            #             all_nodes.append(n)
+            #             node_ids.add(n.node.node_id)
+            #     return all_nodes
+
             def _retrieve(self, query, **kwargs):
                 bm25_nodes = self.bm25_retriever.retrieve(query, **kwargs)
-                vector_nodes = self.vector_retriever.retrieve(query, **kwargs)
+                # vector_nodes = self.vector_retriever.retrieve(query, **kwargs)
                 all_nodes = []
                 node_ids = set()
-                for n in bm25_nodes + vector_nodes:
+                for n in bm25_nodes
                     if n.node.node_id not in node_ids:
                         all_nodes.append(n)
                         node_ids.add(n.node.node_id)