Source code for nv_ingest.extraction_workflows.pdf.tika_helper

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


# SPDX-FileCopyrightText: Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import requests

TIKA_URL = "http://tika:9998/tika"



[docs]
def tika(pdf_stream, extract_text, extract_images, extract_tables, **kwargs):
    headers = {"Accept": "text/plain"}
    timeout = 120  # Timeout in seconds
    response = requests.put(TIKA_URL, headers=headers, data=pdf_stream, timeout=timeout)

    return response.text