support GroundingDINO and segment-anything

requirements.txt

@@ -1,7 +1,6 @@
 langchain==0.0.101
 torch==1.13.1
 torchvision==0.14.1
-gradio==3.20.1
 wget==3.2
 accelerate
 addict
@@ -10,6 +9,7 @@ basicsr
 controlnet-aux
 diffusers
 einops
+gradio
 imageio
 imageio-ffmpeg
 invisible-watermark

visual_chatgpt.py

@@ -1306,7 +1306,7 @@ 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.strip()})
         res['output'] = res['output'].replace("\\", "/")
-        response = re.sub('(image/[-\w]*.png)', lambda m: f'![](/file={m.group(0)})*{m.group(0)}*', res['output'])
+        response = re.sub('(image/[-\w]*.png)', lambda m: f'![](file={m.group(0)})*{m.group(0)}*', res['output'])
         state = state + [(text, response)]
         print(f"\nProcessed run_text, Input text: {text}\nCurrent state: {state}\n"
               f"Current Memory: {self.agent.memory.buffer}")
@@ -1333,7 +1333,7 @@ def run_image(self, image, state, txt, lang):
             Human_prompt = f'\nHuman: provide a figure named {image_filename}. The description is: {description}. This information helps you to understand this image, but you should use tools to finish following tasks, rather than directly imagine from my description. If you understand, say \"Received\". \n'
             AI_prompt = "Received.  "
         self.agent.memory.buffer = self.agent.memory.buffer + Human_prompt + 'AI: ' + AI_prompt
-        state = state + [(f"![](/file={image_filename})*{image_filename}*", AI_prompt)]
+        state = state + [(f"![](file={image_filename})*{image_filename}*", AI_prompt)]
         print(f"\nProcessed run_image, Input image: {image_filename}\nCurrent state: {state}\n"
               f"Current Memory: {self.agent.memory.buffer}")
         return state, state, f'{txt} {image_filename} '