This repository has been archived on 2024-10-27. You can view files and clone it, but cannot push or open issues or pull requests.
local-llm-server/llm_server/llm/info.py

29 lines
868 B
Python

import requests
from llm_server import opts
def get_running_model():
if opts.mode == 'oobabooga':
try:
backend_response = requests.get(f'{opts.backend_url}/api/v1/model', timeout=3, verify=opts.verify_ssl)
except Exception as e:
return False, e
try:
r_json = backend_response.json()
return r_json['result'], None
except Exception as e:
return False, e
elif opts.mode == 'hf-textgen':
try:
backend_response = requests.get(f'{opts.backend_url}/info', verify=opts.verify_ssl)
except Exception as e:
return False, e
try:
r_json = backend_response.json()
return r_json['model_id'].replace('/', '_'), None
except Exception as e:
return False, e
else:
raise Exception