Merge pull request chenfei-wu#298 from Magnetic2014/main

Add CoT prompt to improve nlp+vision task.

visual_chatgpt.py

@@ -67,7 +67,8 @@
 New input: {input}
 Since Visual ChatGPT is a text language model, Visual ChatGPT must use tools to observe images rather than imagination.
 The thoughts and observations are only visible for Visual ChatGPT, Visual ChatGPT should remember to repeat important information in the final response for Human. 
-Thought: Do I need to use a tool? {agent_scratchpad}"""
+Thought: Do I need to use a tool? {agent_scratchpad} Let's think step by step.
+"""
 
 os.makedirs('image', exist_ok=True)
 
@@ -1011,7 +1012,7 @@ def __init__(self, load_dict):
 
     def run_text(self, text, state):
         self.agent.memory.buffer = cut_dialogue_history(self.agent.memory.buffer, keep_last_n_words=500)
-        res = self.agent({"input": text})
+        res = self.agent({"input": text.strip()})
         res['output'] = res['output'].replace("\\", "/")
         response = re.sub('(image/\S*png)', lambda m: f'![](/file={m.group(0)})*{m.group(0)}*', res['output'])
         state = state + [(text, response)]