weiweiw
/
Langchain-Chatchat
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

reformat and add version to startup.py

This commit is contained in:
imClumsyPanda 2023-08-17 22:22:28 +08:00
parent 52837429d2
commit 67839daad3
1 changed files with 16 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
startup.py
View File

@ -5,14 +5,16 @@ import sys
import os import os
from pprint import pprint from pprint import pprint
sys.path.append(os.path.dirname(os.path.dirname(__file__))) sys.path.append(os.path.dirname(os.path.dirname(__file__)))
from configs.model_config import EMBEDDING_DEVICE, EMBEDDING_MODEL, llm_model_dict, LLM_MODEL, LLM_DEVICE, LOG_PATH, logger from configs.model_config import EMBEDDING_DEVICE, EMBEDDING_MODEL, llm_model_dict, LLM_MODEL, LLM_DEVICE, LOG_PATH, \
logger
from configs.server_config import (WEBUI_SERVER, API_SERVER, OPEN_CROSS_DOMAIN, FSCHAT_CONTROLLER, FSCHAT_MODEL_WORKERS, from configs.server_config import (WEBUI_SERVER, API_SERVER, OPEN_CROSS_DOMAIN, FSCHAT_CONTROLLER, FSCHAT_MODEL_WORKERS,
FSCHAT_OPENAI_API, fschat_controller_address, fschat_model_worker_address, fschat_openai_api_address,) FSCHAT_OPENAI_API, fschat_controller_address, fschat_model_worker_address,
fschat_openai_api_address, )
from server.utils import MakeFastAPIOffline, FastAPI from server.utils import MakeFastAPIOffline, FastAPI
import argparse import argparse
from typing import Tuple, List from typing import Tuple, List
from configs import VERSION
def set_httpx_timeout(timeout=60.0): def set_httpx_timeout(timeout=60.0):
@ -53,6 +55,7 @@ def create_model_worker_app(**kwargs) -> Tuple[argparse.ArgumentParser, FastAPI]
target=fastchat.serve.model_worker.heart_beat_worker, args=(self,), daemon=True, target=fastchat.serve.model_worker.heart_beat_worker, args=(self,), daemon=True,
) )
self.heart_beat_thread.start() self.heart_beat_thread.start()
ModelWorker.init_heart_beat = _new_init_heart_beat ModelWorker.init_heart_beat = _new_init_heart_beat
parser = argparse.ArgumentParser() parser = argparse.ArgumentParser()
@ -88,7 +91,6 @@ def create_model_worker_app(**kwargs) -> Tuple[argparse.ArgumentParser, FastAPI]
) )
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpus os.environ["CUDA_VISIBLE_DEVICES"] = args.gpus
gptq_config = GptqConfig( gptq_config = GptqConfig(
ckpt=args.gptq_ckpt or args.model_path, ckpt=args.gptq_ckpt or args.model_path,
wbits=args.gptq_wbits, wbits=args.gptq_wbits,
@ -123,7 +125,7 @@ def create_model_worker_app(**kwargs) -> Tuple[argparse.ArgumentParser, FastAPI]
sys.modules["fastchat.serve.model_worker"].worker = worker sys.modules["fastchat.serve.model_worker"].worker = worker
sys.modules["fastchat.serve.model_worker"].args = args sys.modules["fastchat.serve.model_worker"].args = args
sys.modules["fastchat.serve.model_worker"].gptq_config = gptq_config sys.modules["fastchat.serve.model_worker"].gptq_config = gptq_config
MakeFastAPIOffline(app) MakeFastAPIOffline(app)
app.title = f"FastChat LLM Server ({LLM_MODEL})" app.title = f"FastChat LLM Server ({LLM_MODEL})"
return app return app
@ -184,10 +186,10 @@ def run_controller(q: Queue, run_seq: int = 1):
def run_model_worker( def run_model_worker(
model_name: str = LLM_MODEL, model_name: str = LLM_MODEL,
controller_address: str = "", controller_address: str = "",
q: Queue = None, q: Queue = None,
run_seq: int = 2, run_seq: int = 2,
): ):
import uvicorn import uvicorn
@ -210,7 +212,7 @@ def run_openai_api(q: Queue, run_seq: int = 3):
import uvicorn import uvicorn
controller_addr = fschat_controller_address() controller_addr = fschat_controller_address()
app = create_openai_api_app(controller_addr) # todo: not support keys yet. app = create_openai_api_app(controller_addr) # todo: not support keys yet.
_set_app_seq(app, q, run_seq) _set_app_seq(app, q, run_seq)
host = FSCHAT_OPENAI_API["host"] host = FSCHAT_OPENAI_API["host"]
@ -242,8 +244,8 @@ def run_webui(q: Queue, run_seq: int = 5):
break break
q.put(run_seq) q.put(run_seq)
p = subprocess.Popen(["streamlit", "run", "webui.py", p = subprocess.Popen(["streamlit", "run", "webui.py",
"--server.address", host, "--server.address", host,
"--server.port", str(port)]) "--server.port", str(port)])
p.wait() p.wait()
@ -334,13 +336,12 @@ if __name__ == "__main__":
args.model_worker = True args.model_worker = True
args.api = True args.api = True
args.webui = False args.webui = False
elif args.llm_api: elif args.llm_api:
args.openai_api = True args.openai_api = True
args.model_worker = True args.model_worker = True
args.api = False args.api = False
args.webui = False args.webui = False
logger.info(f"正在启动服务：") logger.info(f"正在启动服务：")
logger.info(f"如需查看 llm_api 日志，请前往 {LOG_PATH}") logger.info(f"如需查看 llm_api 日志，请前往 {LOG_PATH}")
@ -406,7 +407,7 @@ if __name__ == "__main__":
print("=" * 30 + "Langchain-Chatchat Configuration" + "=" * 30) print("=" * 30 + "Langchain-Chatchat Configuration" + "=" * 30)
print(f"操作系统：{platform.platform()}.") print(f"操作系统：{platform.platform()}.")
print(f"python版本：{sys.version}") print(f"python版本：{sys.version}")
print(f"项目版本：") # todo print(f"项目版本：{VERSION}")
print(f"langchain版本：{langchain.__version__}. fastchat版本：{fastchat.__version__}") print(f"langchain版本：{langchain.__version__}. fastchat版本：{fastchat.__version__}")
print("\n") print("\n")
print(f"当前LLM模型：{LLM_MODEL} @ {LLM_DEVICE}") print(f"当前LLM模型：{LLM_MODEL} @ {LLM_DEVICE}")