diff --git a/chains/local_doc_qa.py b/chains/local_doc_qa.py
index d4cdcb0..6921ef8 100644
--- a/chains/local_doc_qa.py
+++ b/chains/local_doc_qa.py
@@ -121,7 +121,7 @@ def similarity_search_with_score_by_vector(
             else:
                 _id0 = self.index_to_docstore_id[id]
                 doc0 = self.docstore.search(_id0)
-                doc.page_content += doc0.page_content
+                doc.page_content += " " + doc0.page_content
         if not isinstance(doc, Document):
             raise ValueError(f"Could not find document for id {_id}, got {doc}")
         doc_score = min([scores[0][id] for id in [indices[0].tolist().index(i) for i in id_seq if i in indices[0]]])
diff --git a/models/chatglm_llm.py b/models/chatglm_llm.py
index 49ce97c..a63a3d1 100644
--- a/models/chatglm_llm.py
+++ b/models/chatglm_llm.py
@@ -69,19 +69,17 @@ class ChatGLM(LLM):
               history: List[List[str]] = [],
               streaming: bool = STREAMING):  # -> Tuple[str, List[List[str]]]:
         if streaming:
-            for inum, (stream_resp, _) in enumerate(self.model.stream_chat(
+            history += [[]]
+            for stream_resp, _ in self.model.stream_chat(
                     self.tokenizer,
                     prompt,
                     history=history[-self.history_len:-1] if self.history_len > 0 else [],
                     max_length=self.max_token,
                     temperature=self.temperature,
                     top_p=self.top_p,
-            )):
+            ):
                 torch_gc()
-                if inum == 0:
-                    history += [[prompt, stream_resp]]
-                else:
-                    history[-1] = [prompt, stream_resp]
+                history[-1] = [prompt, stream_resp]
                 yield stream_resp, history
                 torch_gc()
         else: