Update app.py

app.py

@@ -108,48 +108,33 @@ def _launch_demo(args, model, tokenizer):
         if not _chatbot:
             return _chatbot 
         chat_query = _chatbot[-1][0]
-        query = task_history[-1][0]
-        print("User: " + _parse_text(query))
-        history_cp = copy.deepcopy(task_history)
-        full_response = ""
-
-        history_filter = []
-        pic_idx = 1
-        pre = ""
-        for i, (q, a) in enumerate(history_cp):
-            if isinstance(q, (tuple, list)):
-                q = f'Picture {pic_idx}: <img>{q[0]}</img>'
-                pre += q + '\n'
-                pic_idx += 1
+        print("User: " + _parse_text(chat_query))
+
+        history = process_history_for_model(task_history)
+
+        if isinstance(chat_query, tuple):  # Image input
+            message = {'image': chat_query[0]}
+        else:  # Text input
+            message = {'text': chat_query}
+
+        response, updated_history = model.chat(tokenizer, query=message, history=history)
+
+        if "<box>" in response:
+            image = tokenizer.draw_bbox_on_latest_picture(response, updated_history)
+            if image is not None:
+                image_path = save_image(image)  
+                _chatbot[-1] = (_parse_text(chat_query), (image_path,))
+                response = process_response(response)
             else:
-                pre += q
-                history_filter.append((pre, a))
-                pre = ""
-        history, message = history_filter[:-1], history_filter[-1][0]
-        response, history = model.chat(tokenizer, message, history=history)
-        image = tokenizer.draw_bbox_on_latest_picture(response, history)
-        if image is not None:
-            temp_dir = secrets.token_hex(20)
-            temp_dir = Path(uploaded_file_dir) / temp_dir
-            temp_dir.mkdir(exist_ok=True, parents=True)
-            name = f"tmp{secrets.token_hex(5)}.jpg"
-            filename = temp_dir / name
-            image.save(str(filename))
-            _chatbot[-1] = (_parse_text(chat_query), (str(filename),))
-            chat_response = response.replace("<ref>", "")
-            chat_response = chat_response.replace(r"</ref>", "")
-            chat_response = re.sub(BOX_TAG_PATTERN, "", chat_response)
-            if chat_response != "":
-                _chatbot.append((None, chat_response))
+                _chatbot[-1] = (_parse_text(chat_query), response)
         else:
             _chatbot[-1] = (_parse_text(chat_query), response)
-        full_response = _parse_text(response)
 
-        task_history[-1] = (query, full_response)
-        print("Qwen-VL-Chat: " + _parse_text(full_response))
-        task_history = task_history[-10:]
+        task_history = update_task_history(task_history, updated_history, response)
+
         return _chatbot
 
+
     def regenerate(_chatbot, task_history):
         if not task_history:
             return _chatbot
@@ -182,16 +167,41 @@ def _launch_demo(args, model, tokenizer):
 
     def reset_user_input():
         return gr.update(value="")
+    
+    def process_response(response):
+        response = response.replace("<ref>", "").replace(r"</ref>", "")
+        response = re.sub(BOX_TAG_PATTERN, "", response)
+        return response
+    def process_history_for_model(task_history):
+        processed_history = []
+        for query, response in task_history:
+            if isinstance(query, tuple): 
+                processed_history.append({'image': query[0]})
+            else:
+                processed_history.append({'text': query})
+            if response:
+                processed_history.append({'text': response})
+        return processed_history
 
     def reset_state(task_history):
         task_history.clear()
         return []
+        
+    def save_image(image):
+        temp_dir = secrets.token_hex(20)
+        temp_dir = Path(uploaded_file_dir) / temp_dir
+        temp_dir.mkdir(exist_ok=True, parents=True)
+        name = f"tmp{secrets.token_hex(5)}.jpg"
+        filename = temp_dir / name
+        image.save(str(filename))
+        return str(filename)
+
 
     with gr.Blocks() as demo:
         gr.Markdown("""# Welcome to Tonic's Qwen-VL-Chat Bot""")
         gr.Markdown(
-            """ This WebUI is based on Qwen-VL-Chat, developed by Alibaba Cloud.
-(本WebUI基于Qwen-VL-Chat打造，实现聊天机器人功能。)""")
+            """ Qwen-VL-Chat is a multimodal input model. 
+(本WebUI基于Qwen-VL-Chat打造，实现聊天机器人功能 但我必须修复它这么多也许我也得到一些荣誉？)""")
         with gr.Row():
             with gr.Column(scale=1):
                 chatbot = gr.Chatbot(label='Qwen-VL-Chat')