动态endpoint

crazy_functions/询问多个大语言模型.py

@@ -16,7 +16,7 @@ def 同时问询(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
     chatbot.append((txt, "正在同时咨询ChatGPT和ChatGLM……"))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
 
-    llm_kwargs['llm_model'] = 'chatglm&gpt-3.5-turbo'
+    llm_kwargs['llm_model'] = 'gpt-3.5-turbo&api2d-gpt-3.5-turbo'
     gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
         inputs=txt, inputs_show_user=txt, 
         llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 

request_llm/bridge_chatgpt.py

@@ -60,7 +60,9 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
     while True:
         try:
             # make a POST request to the API endpoint, stream=False
-            response = requests.post(llm_kwargs['endpoint'], headers=headers, proxies=proxies,
+            from .bridge_all import model_info
+            endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
+            response = requests.post(endpoint, headers=headers, proxies=proxies,
                                     json=payload, stream=True, timeout=TIMEOUT_SECONDS); break
         except requests.exceptions.ReadTimeout as e:
             retry += 1
@@ -148,7 +150,9 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
     while True:
         try:
             # make a POST request to the API endpoint, stream=True
-            response = requests.post(llm_kwargs['endpoint'], headers=headers, proxies=proxies,
+            from .bridge_all import model_info
+            endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
+            response = requests.post(endpoint, headers=headers, proxies=proxies,
                                     json=payload, stream=True, timeout=TIMEOUT_SECONDS);break
         except:
             retry += 1

toolbox.py

@@ -36,7 +36,6 @@ def ArgsGeneralWrapper(f):
         llm_kwargs = {
             'api_key': cookies['api_key'],
             'llm_model': llm_model,
-            'endpoint': model_info[llm_model]['endpoint'],
             'top_p':top_p, 
             'max_length': max_length,
             'temperature':temperature,