beta

predict.py

@@ -32,7 +32,7 @@ def predict_no_ui(inputs, top_p, temperature, history=[]):
             # make a POST request to the API endpoint, stream=False
             response = requests.post(API_URL, headers=headers, proxies=proxies,
                                     json=payload, stream=False, timeout=TIMEOUT_SECONDS*2); break
-        except TimeoutError as e:
+        except requests.exceptions.ReadTimeout as e:
             retry += 1
             traceback.print_exc()
             if MAX_RETRY!=0: print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
@@ -110,7 +110,8 @@ def predict(inputs, top_p, temperature, chatbot=[], history=[], system_prompt=''
                     chunk = get_full_error(chunk, stream_response)
                     error_msg = chunk.decode()
                     if "reduce the length" in error_msg:
-                        chatbot[-1] = (history[-1], "[local] input is too long, reduce input or clear history.")
+                        chatbot[-1] = (history[-1], "[Local Message] Input (or history) is too long, please reduce input or clear history by refleshing this page.")
+                        history = []
                     yield chatbot, history, "Json解析不合常规，很可能是文本过长" + error_msg
                     return