Azure Document Intelligence (FormRecognizer) - «InvalidContent» при прохождении PDF ⇐ Python

[Anonymous]

Я загружаю файл PDF в свое приложение Streatlit, как это: < /p>
import streamlit as st

uploaded_file = st.file_uploader("Upload pdf file", type="pdf")
result = analyze_general_document(uploaded_file)

Я хочу проанализировать этот PDF с помощью пакета Azure Document Python, как это:
from io import BytesIO
from azure.core.credentials import AzureKeyCredential
from azure.ai.formrecognizer import DocumentAnalysisClient

def set_client(secrets: dict):
endpoint = secrets["AI_DOCS_BASE"]
key = secrets["AI_DOCS_KEY"]
document_analysis_client = DocumentAnalysisClient(endpoint=endpoint, credential=AzureKeyCredential(key))
return document_analysis_client

def analyze_general_document(uploaded_file, secrets: dict):
print(f"File type: {uploaded_file.type}")
print(f"File size: {uploaded_file.size} bytes")
client = set_client(secrets)
# poller = client.begin_analyze_document_from_url("prebuilt-document", formUrl)
poller = client.begin_analyze_document("prebuilt-document", document=uploaded_file)
< /code>
Я могу успешно распечатать тип файла и размер файла, как вы можете увидеть в выходе терминала: < /p>
File type: application/pdf
File size: 6928426 bytes

также открытие файла с Pymupdf также работает хорошо. < /p>
Traceback (most recent call last):
File "C:\Users\myuser\AppData\Local\miniconda3\envs\projectai\Lib\site-packages\streamlit\runtime\scriptrunner\exec_code.py", line 88, in exec_func_with_error_handling
result = func()
^^^^^^
File "C:\Users\myuser\AppData\Local\miniconda3\envs\projectai\Lib\site-packages\streamlit\runtime\scriptrunner\script_runner.py", line 579, in code_to_exec
exec(code, module.__dict__)
File "C:\Users\myuser\Documents\visual-studio-code\project\project-ai-docs\webapp\app.py", line 79, in
main()
File "C:\Users\myuser\Documents\visual-studio-code\project\project-ai-docs\webapp\app.py", line 61, in main
zip_content = process_pdf(uploaded_file, secrets)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\myuser\Documents\visual-studio-code\project\project-ai-docs\webapp\app_backend.py", line 40, in process_pdf
analyze_general_document(uploaded_file, secrets)
File "C:\Users\myuser\Documents\visual-studio-code\project\project-ai-docs\webapp\az_document_intelligence.py", line 18, in analyze_general_document
poller = client.begin_analyze_document("prebuilt-document", document=uploaded_file)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\myuser\AppData\Local\miniconda3\envs\projectai\Lib\site-packages\azure\core\tracing\decorator.py", line 105, in wrapper_use_tracer
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\myuser\AppData\Local\miniconda3\envs\projectai\Lib\site-packages\azure\ai\formrecognizer\_document_analysis_client.py", line 129, in begin_analyze_document
return _client_op_path.begin_analyze_document( # type: ignore
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\myuser\AppData\Local\miniconda3\envs\projectai\Lib\site-packages\azure\core\tracing\decorator.py", line 105, in wrapper_use_tracer
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\myuser\AppData\Local\miniconda3\envs\projectai\Lib\site-packages\azure\ai\formrecognizer\_generated\v2023_07_31\operations\_document_models_operations.py", line 518, in begin_analyze_document
raw_result = self._analyze_document_initial( # type: ignore
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\myuser\AppData\Local\miniconda3\envs\projectai\Lib\site-packages\azure\ai\formrecognizer\_generated\v2023_07_31\operations\_document_models_operations.py", line 443, in _analyze_document_initial
raise HttpResponseError(response=response)
azure.core.exceptions.HttpResponseError: (InvalidRequest) Invalid request.
Code: InvalidRequest
Message: Invalid request.
Inner error: {
"code": "InvalidContent",
"message": "The file is corrupted or format is unsupported. Refer to documentation for the list of supported formats."
}
< /code>
Почему PDF считается недопустимым?def analyze_general_document(uploaded_file, secrets: dict):
print(f"File type: {uploaded_file.type}")
print(f"File size: {uploaded_file.size} bytes")
# Read the file as bytes
file_bytes = uploaded_file.read()
client = set_client(secrets)
# poller = client.begin_analyze_document_from_url("prebuilt-document", formUrl)
poller = client.begin_analyze_document("prebuilt-document", document=BytesIO(file_bytes))


Подробнее здесь: https://stackoverflow.com/questions/792 ... assing-pdf