mirror of https://github.com/THUDM/ChatGLM-6B
36 lines
1.1 KiB
Python
36 lines
1.1 KiB
Python
from fastapi import FastAPI, Request
|
|
from transformers import AutoTokenizer, AutoModel
|
|
import uvicorn, json, datetime
|
|
|
|
app = FastAPI()
|
|
|
|
|
|
@app.post("/")
|
|
async def create_item(request: Request):
|
|
global model, tokenizer
|
|
json_post_raw = await request.json()
|
|
json_post = json.dumps(json_post_raw)
|
|
json_post_list = json.loads(json_post)
|
|
prompt = json_post_list.get('prompt')
|
|
history = json_post_list.get('history')
|
|
response, history = model.chat(tokenizer, prompt, history=history)
|
|
now = datetime.datetime.now()
|
|
time = now.strftime("%Y-%m-%d %H:%M:%S")
|
|
answer = {
|
|
"response": response,
|
|
"history": history,
|
|
"status": 200,
|
|
"time": time
|
|
}
|
|
log = "[" + time + "] " + '", prompt:"' + prompt + '", response:"' + repr(response) + '"'
|
|
print(log)
|
|
return answer
|
|
|
|
|
|
if __name__ == '__main__':
|
|
uvicorn.run('API:app', host='0.0.0.0', port=8000, workers=1)
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
|
|
model = AutoModel.from_pretrained("THUDM/chatglm_6b", trust_remote_code=True).half().cuda()
|
|
model.eval()
|