Spaces:
Runtime error
Runtime error
修改chatglm不记忆上下文的bug
Browse files
request_llm/bridge_chatglm.py
CHANGED
|
@@ -92,8 +92,8 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
|
|
| 92 |
|
| 93 |
# chatglm 没有 sys_prompt 接口,因此把prompt加入 history
|
| 94 |
history_feedin = []
|
|
|
|
| 95 |
for i in range(len(history)//2):
|
| 96 |
-
history_feedin.append(["What can I do?", sys_prompt] )
|
| 97 |
history_feedin.append([history[2*i], history[2*i+1]] )
|
| 98 |
|
| 99 |
watch_dog_patience = 5 # 看门狗 (watchdog) 的耐心, 设置5秒即可
|
|
@@ -131,10 +131,13 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
|
| 131 |
inputs = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"]
|
| 132 |
|
| 133 |
history_feedin = []
|
|
|
|
| 134 |
for i in range(len(history)//2):
|
| 135 |
-
history_feedin.append(["What can I do?", system_prompt] )
|
| 136 |
history_feedin.append([history[2*i], history[2*i+1]] )
|
| 137 |
|
| 138 |
for response in glm_handle.stream_chat(query=inputs, history=history_feedin, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
|
| 139 |
chatbot[-1] = (inputs, response)
|
| 140 |
-
yield from update_ui(chatbot=chatbot, history=history)
|
|
|
|
|
|
|
|
|
|
|
|
| 92 |
|
| 93 |
# chatglm 没有 sys_prompt 接口,因此把prompt加入 history
|
| 94 |
history_feedin = []
|
| 95 |
+
history_feedin.append(["What can I do?", sys_prompt])
|
| 96 |
for i in range(len(history)//2):
|
|
|
|
| 97 |
history_feedin.append([history[2*i], history[2*i+1]] )
|
| 98 |
|
| 99 |
watch_dog_patience = 5 # 看门狗 (watchdog) 的耐心, 设置5秒即可
|
|
|
|
| 131 |
inputs = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"]
|
| 132 |
|
| 133 |
history_feedin = []
|
| 134 |
+
history_feedin.append(["What can I do?", system_prompt] )
|
| 135 |
for i in range(len(history)//2):
|
|
|
|
| 136 |
history_feedin.append([history[2*i], history[2*i+1]] )
|
| 137 |
|
| 138 |
for response in glm_handle.stream_chat(query=inputs, history=history_feedin, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
|
| 139 |
chatbot[-1] = (inputs, response)
|
| 140 |
+
yield from update_ui(chatbot=chatbot, history=history)
|
| 141 |
+
|
| 142 |
+
history.extend([inputs, response])
|
| 143 |
+
yield from update_ui(chatbot=chatbot, history=history)
|