support gpt-4o

check_proxy.py

@@ -161,6 +161,8 @@ def warm_up_modules():
         enc.encode("模块预热", disallowed_special=())
         enc = model_info["gpt-4"]['tokenizer']
         enc.encode("模块预热", disallowed_special=())
+        enc = model_info["gpt-4o"]['tokenizer']
+        enc.encode("模块预热", disallowed_special=())
 
 def warm_up_vectordb():
     print('正在执行一些模块的预热 ...')

config.py

@@ -33,6 +33,7 @@
 # [step 3]>> 模型选择是 (注意: LLM_MODEL是默认选中的模型, 它*必须*被包含在AVAIL_LLM_MODELS列表中 )
 LLM_MODEL = "gpt-3.5-turbo-16k" # 可选 ↓↓↓
 AVAIL_LLM_MODELS = ["gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
+                    "gpt-4o", "gpt-4o-2024-05-13",
                     "gpt-3.5-turbo-1106", "gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5",
                     "gpt-4", "gpt-4-32k", "azure-gpt-4", "glm-4", "glm-4v", "glm-3-turbo",
                     "gemini-pro", "chatglm3"

request_llms/bridge_all.py

@@ -47,9 +47,9 @@ def __init__(self, model):
     @staticmethod
     @lru_cache(maxsize=128)
     def get_encoder(model):
-        print('正在加载tokenizer，如果是第一次运行，可能需要一点时间下载参数')
+        print(f'正在加载 {model} 模型的tokenizer，如果是第一次运行，可能需要一点时间下载参数')
         tmp = tiktoken.encoding_for_model(model)
-        print('加载tokenizer完毕')
+        print(f'加载 {model} 模型的tokenizer完毕')
         return tmp
 
     def encode(self, *args, **kwargs):
@@ -94,9 +94,10 @@ def decode(self, *args, **kwargs):
 # 获取tokenizer
 tokenizer_gpt35 = LazyloadTiktoken("gpt-3.5-turbo")
 tokenizer_gpt4 = LazyloadTiktoken("gpt-4")
+tokenizer_gpt4o = LazyloadTiktoken("gpt-4o")
 get_token_num_gpt35 = lambda txt: len(tokenizer_gpt35.encode(txt, disallowed_special=()))
 get_token_num_gpt4 = lambda txt: len(tokenizer_gpt4.encode(txt, disallowed_special=()))
-
+get_token_num_gpt4o = lambda txt: len(tokenizer_gpt4o.encode(txt, disallowed_special=()))
 
 # 开始初始化模型
 AVAIL_LLM_MODELS, LLM_MODEL = get_conf("AVAIL_LLM_MODELS", "LLM_MODEL")
@@ -295,6 +296,23 @@ def decode(self, *args, **kwargs):
         "token_cnt": get_token_num_gpt4,
     },
 
+    "gpt-4o": {
+        "fn_with_ui": chatgpt_ui,
+        "fn_without_ui": chatgpt_noui,
+        "endpoint": openai_endpoint,
+        "max_token": 128000,
+        "tokenizer": tokenizer_gpt4o,
+        "token_cnt": get_token_num_gpt4o,
+    },
+
+    "gpt-4o-2024-05-13": {
+        "fn_with_ui": chatgpt_ui,
+        "fn_without_ui": chatgpt_noui,
+        "endpoint": openai_endpoint,
+        "max_token": 128000,
+        "tokenizer": tokenizer_gpt4o,
+        "token_cnt": get_token_num_gpt4o,
+    },
 
     "gpt-3.5-random": {
         "fn_with_ui": chatgpt_ui,

requirements.txt

@@ -3,7 +3,7 @@ fastapi==0.110
 gradio-client==0.8
 pypdf2==2.12.1
 zhipuai==2.0.1
-tiktoken>=0.3.3
+tiktoken>=0.7.0
 requests[socks]
 pydantic==2.5.2
 protobuf==3.18