mirror of
https://github.com/RYDE-WORK/Langchain-Chatchat.git
synced 2026-01-19 13:23:16 +08:00
b51ba11f45
新功能： - 将 LLM_MODEL 配置项改为 LLM_MODELS 列表，同时启动多个模型 - 将 wiki 纳入 samples 知识库 依赖变化： - 指定 streamlit~=1.27.0。1.26.0会报rerun错误，1.28.0会有无限刷新错误 修复优化： - 优化 get_default_llm_model 逻辑 - 适配 Qwen 在线 API 做 Embeddings 时最大 25 行的限制 - 列出知识库磁盘文件时跳过 . 开头的文件
59 lines
1.8 KiB
Python
59 lines
1.8 KiB
Python
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',
|
||
)
|