优化autogen的使用

request_llm/bridge_all.py

@@ -182,6 +182,15 @@ model_info = {
         "token_cnt": get_token_num_gpt4,
     },
 
+    "api2d-gpt-3.5-turbo-16k": {
+        "fn_with_ui": chatgpt_ui,
+        "fn_without_ui": chatgpt_noui,
+        "endpoint": api2d_endpoint,
+        "max_token": 1024*16,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
+
     # 将 chatglm 直接对齐到 chatglm2
     "chatglm": {
         "fn_with_ui": chatglm_ui,

request_llm/bridge_chatgpt.py

@@ -314,7 +314,10 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
     what_i_ask_now["role"] = "user"
     what_i_ask_now["content"] = inputs
     messages.append(what_i_ask_now)
-    model = llm_kwargs['llm_model'].strip('api2d-')
+    model = llm_kwargs['llm_model']
+    if llm_kwargs['llm_model'].startswith('api2d-'):
+        model = llm_kwargs['llm_model'][len('api2d-'):]
+
     if model == "gpt-3.5-random": # 随机选择, 绕过openai访问频率限制
         model = random.choice([
             "gpt-3.5-turbo",