68 lines
3.0 KiB
Python
68 lines
3.0 KiB
Python
from fastapi import Body
|
||
from fastapi.responses import StreamingResponse
|
||
from configs import LLM_MODELS, TEMPERATURE
|
||
from server.utils import wrap_done, get_OpenAI
|
||
from langchain.chains import LLMChain
|
||
from langchain.callbacks import AsyncIteratorCallbackHandler
|
||
from typing import AsyncIterable, Optional
|
||
import asyncio
|
||
from langchain.prompts.chat import PromptTemplate
|
||
from server.utils import get_prompt_template
|
||
|
||
|
||
async def completion(query: str = Body(..., description="用户输入", examples=["恼羞成怒"]),
|
||
stream: bool = Body(False, description="流式输出"),
|
||
echo: bool = Body(False, description="除了输出之外，还回显输入"),
|
||
model_name: str = Body(LLM_MODELS[0], description="LLM 模型名称。"),
|
||
temperature: float = Body(TEMPERATURE, description="LLM 采样温度", ge=0.0, le=1.0),
|
||
max_tokens: Optional[int] = Body(1024, description="限制LLM生成Token数量，默认None代表模型最大值"),
|
||
# top_p: float = Body(TOP_P, description="LLM 核采样。勿与temperature同时设置", gt=0.0, lt=1.0),
|
||
prompt_name: str = Body("default",
|
||
description="使用的prompt模板名称(在configs/prompt_config.py中配置)"),
|
||
):
|
||
|
||
#todo 因ApiModelWorker 默认是按chat处理的，会对params["prompt"] 解析为messages，因此ApiModelWorker 使用时需要有相应处理
|
||
async def completion_iterator(query: str,
|
||
model_name: str = LLM_MODELS[0],
|
||
prompt_name: str = prompt_name,
|
||
echo: bool = echo,
|
||
) -> AsyncIterable[str]:
|
||
callback = AsyncIteratorCallbackHandler()
|
||
if isinstance(max_tokens, int) and max_tokens <= 0:
|
||
max_tokens = None
|
||
|
||
model = get_OpenAI(
|
||
model_name=model_name,
|
||
temperature=temperature,
|
||
max_tokens=max_tokens,
|
||
callbacks=[callback],
|
||
echo=echo
|
||
)
|
||
|
||
prompt_template = get_prompt_template("completion", prompt_name)
|
||
prompt = PromptTemplate.from_template(prompt_template)
|
||
chain = LLMChain(prompt=prompt, llm=model)
|
||
|
||
# Begin a task that runs in the background.
|
||
task = asyncio.create_task(wrap_done(
|
||
chain.acall({"input": query}),
|
||
callback.done),
|
||
)
|
||
|
||
if stream:
|
||
async for token in callback.aiter():
|
||
# Use server-sent-events to stream the response
|
||
yield token
|
||
else:
|
||
answer = ""
|
||
async for token in callback.aiter():
|
||
answer += token
|
||
yield answer
|
||
|
||
await task
|
||
|
||
return StreamingResponse(completion_iterator(query=query,
|
||
model_name=model_name,
|
||
prompt_name=prompt_name),
|
||
media_type="text/event-stream")
|