remove /chat/fastchat API endpoint (#2506)

server/api.py

@@ -13,7 +13,6 @@ from fastapi import Body
 from fastapi.middleware.cors import CORSMiddleware
 from starlette.responses import RedirectResponse
 from server.chat.chat import chat
-from server.chat.openai_chat import openai_chat
 from server.chat.search_engine_chat import search_engine_chat
 from server.chat.completion import completion
 from server.chat.feedback import chat_feedback
@@ -59,11 +58,6 @@ def mount_app_routes(app: FastAPI, run_mode: str = None):
             summary="swagger 文档")(document)
 
     # Tag: Chat
-    app.post("/chat/fastchat",
-             tags=["Chat"],
-             summary="与llm模型对话(直接与fastchat api对话)",
-             )(openai_chat)
-
     app.post("/chat/chat",
              tags=["Chat"],
              summary="与llm模型对话(通过LLMChain)",

server/chat/openai_chat.py

@@ -1,58 +0,0 @@
-from fastapi.responses import StreamingResponse
-from typing import List, Optional
-import openai
-from configs import LLM_MODELS, logger, log_verbose
-from server.utils import get_model_worker_config, fschat_openai_api_address
-from pydantic import BaseModel
-
-
-class OpenAiMessage(BaseModel):
-    role: str = "user"
-    content: str = "hello"
-
-
-class OpenAiChatMsgIn(BaseModel):
-    model: str = LLM_MODELS[0]
-    messages: List[OpenAiMessage]
-    temperature: float = 0.7
-    n: int = 1
-    max_tokens: Optional[int] = None
-    stop: List[str] = []
-    stream: bool = False
-    presence_penalty: int = 0
-    frequency_penalty: int = 0
-
-
-async def openai_chat(msg: OpenAiChatMsgIn):
-    config = get_model_worker_config(msg.model)
-    openai.api_key = config.get("api_key", "EMPTY")
-    print(f"{openai.api_key=}")
-    openai.api_base = config.get("api_base_url", fschat_openai_api_address())
-    print(f"{openai.api_base=}")
-    print(msg)
-
-    async def get_response(msg):
-        data = msg.dict()
-
-        try:
-            response = await openai.ChatCompletion.acreate(**data)
-            if msg.stream:
-                async for data in response:
-                    if choices := data.choices:
-                        if chunk := choices[0].get("delta", {}).get("content"):
-                            print(chunk, end="", flush=True)
-                            yield chunk
-            else:
-                if response.choices:
-                    answer = response.choices[0].message.content
-                    print(answer)
-                    yield(answer)
-        except Exception as e:
-            msg = f"获取ChatCompletion时出错：{e}"
-            logger.error(f'{e.__class__.__name__}: {msg}',
-                         exc_info=e if log_verbose else None)
-
-    return StreamingResponse(
-        get_response(msg),
-        media_type='text/event-stream',
-    )

tests/api/test_stream_chat_api.py

@@ -48,18 +48,6 @@ data = {
 }
 
 
-def test_chat_fastchat(api="/chat/fastchat"):
-    url = f"{api_base_url}{api}"
-    data2 = {
-        "stream": True,
-        "messages": data["history"] + [{"role": "user", "content": "推荐一部科幻电影"}]
-    }
-    dump_input(data2, api)
-    response = requests.post(url, headers=headers, json=data2, stream=True)
-    dump_output(response, api)
-    assert response.status_code == 200
-
-
 def test_chat_chat(api="/chat/chat"):
     url = f"{api_base_url}{api}"
     dump_input(data, api)

webui_pages/utils.py

@@ -259,38 +259,6 @@ class ApiRequest:
         return self._get_response_value(response, value_func=lambda r: r.text)
 
     # 对话相关操作
-
-    def chat_fastchat(
-        self,
-        messages: List[Dict],
-        stream: bool = True,
-        model: str = LLM_MODELS[0],
-        temperature: float = TEMPERATURE,
-        max_tokens: int = None,
-        **kwargs: Any,
-    ):
-        '''
-        对应api.py/chat/fastchat接口
-        '''
-        data = {
-            "messages": messages,
-            "stream": stream,
-            "model": model,
-            "temperature": temperature,
-            "max_tokens": max_tokens,
-        }
-
-        # print(f"received input message:")
-        # pprint(data)
-
-        response = self.post(
-            "/chat/fastchat",
-            json=data,
-            stream=True,
-            **kwargs,
-        )
-        return self._httpx_stream2generator(response)
-
     def chat_chat(
             self,
             query: str,
@@ -1058,10 +1026,6 @@ if __name__ == "__main__":
     api = ApiRequest()
     aapi = AsyncApiRequest()
 
-    # print(api.chat_fastchat(
-    #     messages=[{"role": "user", "content": "hello"}]
-    # ))
-
     # with api.chat_chat("你好") as r:
     #     for t in r.iter_text(None):
     #         print(t)