Source code for nv_ingest_api.util.string_processing

# SPDX-FileCopyrightText: Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES.
# All rights reserved.
# SPDX-License-Identifier: Apache-2.0

import logging
import re

logger = logging.getLogger(__name__)

DEPLOT_MAX_TOKENS = 128
DEPLOT_TEMPERATURE = 1.0
DEPLOT_TOP_P = 1.0




def remove_url_endpoints(url) -> str:
    """Some configurations provide the full endpoint in the URL.
    Ex: http://deplot:8000/v1/chat/completions. For hitting the
    health endpoint we need to get just the hostname:port combo
    that we can append the health/ready endpoint to so we attempt
    to parse that information here.

    Args:
        url str: Incoming URL

    Returns:
        str: URL with just the hostname:port portion remaining
    """
    if "/v1" in url:
        url = url.split("/v1")[0]

    return url





def generate_url(url) -> str:
    """Examines the user defined URL for http*://. If that
    pattern is detected the URL is used as provided by the user.
    If that pattern does not exist then the assumption is made that
    the endpoint is simply `http://` and that is prepended
    to the user supplied endpoint.

    Args:
        url str: Endpoint where the Rest service is running

    Returns:
        str: Fully validated URL
    """
    if not re.match(r"^https?://", url):
        # Add the default `http://` if it's not already present in the URL
        url = f"http://{url}"

    return url