def start(args): assert_api_version() storage = S3(bucket=os.environ["CORTEX_BUCKET"], region=os.environ["AWS_REGION"]) try: raw_api_spec = get_spec(args.cache_dir, args.spec) api = API(storage=storage, cache_dir=args.cache_dir, **raw_api_spec) client = api.predictor.initialize_client(args) cx_logger().info("loading the predictor from {}".format(api.predictor.path)) predictor_impl = api.predictor.initialize_impl(args.project_dir, client) local_cache["api"] = api local_cache["client"] = client local_cache["predictor_impl"] = predictor_impl except: cx_logger().exception("failed to start api") sys.exit(1) if api.tracker is not None and api.tracker.model_type == "classification": try: local_cache["class_set"] = api.get_cached_classes() except Exception as e: cx_logger().warn("an error occurred while attempting to load classes", exc_info=True) waitress_kwargs = extract_waitress_params(api.predictor.config) waitress_kwargs["listen"] = "*:{}".format(args.port) open("/health_check.txt", "a").close() cx_logger().info("{} api is live".format(api.name)) serve(app, **waitress_kwargs)
def start(): cache_dir = os.environ["CORTEX_CACHE_DIR"] spec = os.environ["CORTEX_API_SPEC"] project_dir = os.environ["CORTEX_PROJECT_DIR"] model_dir = os.getenv("CORTEX_MODEL_DIR", None) tf_serving_port = os.getenv("CORTEX_TF_SERVING_PORT", None) storage = S3(bucket=os.environ["CORTEX_BUCKET"], region=os.environ["AWS_REGION"]) try: raw_api_spec = get_spec(storage, cache_dir, spec) api = API(storage=storage, cache_dir=cache_dir, **raw_api_spec) client = api.predictor.initialize_client(model_dir, tf_serving_port) cx_logger().info("loading the predictor from {}".format( api.predictor.path)) predictor_impl = api.predictor.initialize_impl(project_dir, client) local_cache["api"] = api local_cache["client"] = client local_cache["predictor_impl"] = predictor_impl except: cx_logger().exception("failed to start api") sys.exit(1) if api.tracker is not None and api.tracker.model_type == "classification": try: local_cache["class_set"] = api.get_cached_classes() except Exception as e: cx_logger().warn( "an error occurred while attempting to load classes", exc_info=True) cx_logger().info("{} api is live".format(api.name)) return app
def start(): cache_dir = os.environ["CORTEX_CACHE_DIR"] provider = os.environ["CORTEX_PROVIDER"] spec_path = os.environ["CORTEX_API_SPEC"] project_dir = os.environ["CORTEX_PROJECT_DIR"] model_dir = os.getenv("CORTEX_MODEL_DIR", None) tf_serving_port = os.getenv("CORTEX_TF_SERVING_PORT", "9000") tf_serving_host = os.getenv("CORTEX_TF_SERVING_HOST", "localhost") if provider == "local": storage = LocalStorage(os.getenv("CORTEX_CACHE_DIR")) else: storage = S3(bucket=os.environ["CORTEX_BUCKET"], region=os.environ["AWS_REGION"]) try: raw_api_spec = get_spec(provider, storage, cache_dir, spec_path) api = API(provider=provider, storage=storage, cache_dir=cache_dir, **raw_api_spec) client = api.predictor.initialize_client( model_dir, tf_serving_host=tf_serving_host, tf_serving_port=tf_serving_port) cx_logger().info("loading the predictor from {}".format( api.predictor.path)) predictor_impl = api.predictor.initialize_impl(project_dir, client) local_cache["api"] = api local_cache["provider"] = provider local_cache["client"] = client local_cache["predictor_impl"] = predictor_impl local_cache["predict_fn_args"] = inspect.getfullargspec( predictor_impl.predict).args predict_route = "/" if provider != "local": predict_route = "/predict" local_cache["predict_route"] = predict_route except: cx_logger().exception("failed to start api") sys.exit(1) if (provider != "local" and api.monitoring is not None and api.monitoring.model_type == "classification"): try: local_cache["class_set"] = api.get_cached_classes() except: cx_logger().warn( "an error occurred while attempting to load classes", exc_info=True) app.add_api_route(local_cache["predict_route"], predict, methods=["POST"]) app.add_api_route(local_cache["predict_route"], get_summary, methods=["GET"]) return app
def start_fn(): cache_dir = os.environ["CORTEX_CACHE_DIR"] provider = os.environ["CORTEX_PROVIDER"] spec_path = os.environ["CORTEX_API_SPEC"] project_dir = os.environ["CORTEX_PROJECT_DIR"] model_dir = os.getenv("CORTEX_MODEL_DIR") tf_serving_port = os.getenv("CORTEX_TF_BASE_SERVING_PORT", "9000") tf_serving_host = os.getenv("CORTEX_TF_SERVING_HOST", "localhost") if provider == "local": storage = LocalStorage(os.getenv("CORTEX_CACHE_DIR")) else: storage = S3(bucket=os.environ["CORTEX_BUCKET"], region=os.environ["AWS_REGION"]) has_multiple_servers = os.getenv("CORTEX_MULTIPLE_TF_SERVERS") if has_multiple_servers: with FileLock("/run/used_ports.json.lock"): with open("/run/used_ports.json", "r+") as f: used_ports = json.load(f) for port in used_ports.keys(): if not used_ports[port]: tf_serving_port = port used_ports[port] = True break f.seek(0) json.dump(used_ports, f) f.truncate() try: raw_api_spec = get_spec(provider, storage, cache_dir, spec_path) api = API( provider=provider, storage=storage, model_dir=model_dir, cache_dir=cache_dir, **raw_api_spec, ) client = api.predictor.initialize_client( tf_serving_host=tf_serving_host, tf_serving_port=tf_serving_port) cx_logger().info("loading the predictor from {}".format( api.predictor.path)) predictor_impl = api.predictor.initialize_impl(project_dir, client) local_cache["api"] = api local_cache["provider"] = provider local_cache["client"] = client local_cache["predictor_impl"] = predictor_impl local_cache["predict_fn_args"] = inspect.getfullargspec( predictor_impl.predict).args predict_route = "/" if provider != "local": predict_route = "/predict" local_cache["predict_route"] = predict_route except: cx_logger().exception("failed to start api") sys.exit(1) if (provider != "local" and api.monitoring is not None and api.monitoring.model_type == "classification"): try: local_cache["class_set"] = api.get_cached_classes() except: cx_logger().warn( "an error occurred while attempting to load classes", exc_info=True) app.add_api_route(local_cache["predict_route"], predict, methods=["POST"]) app.add_api_route(local_cache["predict_route"], get_summary, methods=["GET"]) return app