local-llm-server/llm_server/routes/v1/info.py

import time

from flask import jsonify

from . import bp
from ..helpers.http import cache_control
from ... import opts
from ...llm.info import get_running_model
from ..cache import cache


# cache = Cache(bp, config={'CACHE_TYPE': 'simple'})


# @bp.route('/info', methods=['GET'])
# # @cache.cached(timeout=3600, query_string=True)
# def get_info():
#     # requests.get()
#     return 'yes'


@bp.route('/model', methods=['GET'])
@cache.cached(timeout=60, query_string=True)
def get_model():
    model = get_running_model()
    if not model:
        return jsonify({
            'code': 500,
            'error': 'failed to reach backend'
        }), 500
    else:
        return jsonify({
            'result': model,
            'timestamp': int(time.time())
        }), 200