DocumentProcessorServiceAsyncClient.process_document 方法出错，并显示以下错误消息：
400 Document pages exceed the limit: "PAGE_LIMIT_EXCEEDED"我正在测试的示例代码：
api_path = f'projects/{project_id}/locations/{gcloud_region}/processors/{processor_id}'
documentai_client = documentai.DocumentProcessorServiceAsyncClient() # maybe pass some client_options here?
async def invoke_invoice_processor(self, filebytes):
raw_document = documentai.RawDocument(
content=filebytes,
mime_type="application/pdf",
)
request = documentai.ProcessRequest(
name=api_path,
raw_document=raw_document,
)
response = await documentai_client.process_document(request=request)
return response.document
上述代码块适用于 10 页及以下的 PDF。它仅在 PDF 大于 10 页时失败。
我的问题：我需要对上述代码进行哪些更改才能成功处理超过 10 页的较大 PDF？
迟到的答案，但正如我猜想的那样，200 的限制是针对批量请求的，根据定义，这些请求是异步的。造成混乱的原因是客户端库中还有一个异步客户端。使用任一客户端中的要添加更多详细信息，请按照
batch_process_documents浏览 10 页以上。
发送处理请求中提供的代码示例进行批量处理，以一次发送多个文档并发送比在线处理更多的页面。异步客户端不会影响处理器或平台的页面限制。
https://cloud.google.com/document-ai/quotas#content_limits
import re
from google.api_core.client_options import ClientOptions
from google.api_core.exceptions import InternalServerError
from google.api_core.exceptions import RetryError
from google.cloud import documentai
from google.cloud import storage
# TODO(developer): Uncomment these variables before running the sample.
# project_id = 'YOUR_PROJECT_ID'
# location = 'YOUR_PROCESSOR_LOCATION' # Format is 'us' or 'eu'
# processor_id = 'YOUR_PROCESSOR_ID' # Create processor before running sample
# gcs_input_uri = "YOUR_INPUT_URI" # Format: gs://bucket/directory/file.pdf
# input_mime_type = "application/pdf"
# gcs_output_bucket = "YOUR_OUTPUT_BUCKET_NAME" # Format: gs://bucket
# gcs_output_uri_prefix = "YOUR_OUTPUT_URI_PREFIX" # Format: directory/subdirectory/
# field_mask = "text,entities,pages.pageNumber" # Optional. The fields to return in the Document object.
def batch_process_documents(
project_id: str,
location: str,
processor_id: str,
gcs_input_uri: str,
input_mime_type: str,
gcs_output_bucket: str,
gcs_output_uri_prefix: str,
field_mask: str = None,
timeout: int = 400,
):
# You must set the api_endpoint if you use a location other than 'us'.
opts = ClientOptions(api_endpoint=f"{location}-documentai.googleapis.com")
client = documentai.DocumentProcessorServiceClient(client_options=opts)
gcs_document = documentai.GcsDocument(
gcs_uri=gcs_input_uri, mime_type=input_mime_type
)
# Load GCS Input URI into a List of document files
gcs_documents = documentai.GcsDocuments(documents=[gcs_document])
input_config = documentai.BatchDocumentsInputConfig(gcs_documents=gcs_documents)
# NOTE: Alternatively, specify a GCS URI Prefix to process an entire directory
#
# gcs_input_uri = "gs://bucket/directory/"
# gcs_prefix = documentai.GcsPrefix(gcs_uri_prefix=gcs_input_uri)
# input_config = documentai.BatchDocumentsInputConfig(gcs_prefix=gcs_prefix)
#
# Cloud Storage URI for the Output Directory
# This must end with a trailing forward slash `/`
destination_uri = f"{gcs_output_bucket}/{gcs_output_uri_prefix}"
gcs_output_config = documentai.DocumentOutputConfig.GcsOutputConfig(
gcs_uri=destination_uri, field_mask=field_mask
)
# Where to write results
output_config = documentai.DocumentOutputConfig(gcs_output_config=gcs_output_config)
# The full resource name of the processor, e.g.:
# projects/project_id/locations/location/processor/processor_id
name = client.processor_path(project_id, location, processor_id)
request = documentai.BatchProcessRequest(
name=name,
input_documents=input_config,
document_output_config=output_config,
)
# BatchProcess returns a Long Running Operation (LRO)
operation = client.batch_process_documents(request)
# Continually polls the operation until it is complete.
# This could take some time for larger files
# Format: projects/PROJECT_NUMBER/locations/LOCATION/operations/OPERATION_ID
try:
print(f"Waiting for operation {operation.operation.name} to complete...")
operation.result(timeout=timeout)
# Catch exception when operation doesn't finish before timeout
except (RetryError, InternalServerError) as e:
print(e.message)
# NOTE: Can also use callbacks for asynchronous processing
#
# def my_callback(future):
# result = future.result()
#
# operation.add_done_callback(my_callback)
# Once the operation is complete,
# get output document information from operation metadata
metadata = documentai.BatchProcessMetadata(operation.metadata)
if metadata.state != documentai.BatchProcessMetadata.State.SUCCEEDED:
raise ValueError(f"Batch Process Failed: {metadata.state_message}")
storage_client = storage.Client()
print("Output files:")
# One process per Input Document
for process in metadata.individual_process_statuses:
# output_gcs_destination format: gs://BUCKET/PREFIX/OPERATION_NUMBER/INPUT_FILE_NUMBER/
# The Cloud Storage API requires the bucket name and URI prefix separately
matches = re.match(r"gs://(.*?)/(.*)", process.output_gcs_destination)
if not matches:
print(
"Could not parse output GCS destination:",
process.output_gcs_destination,
)
continue
output_bucket, output_prefix = matches.groups()
# Get List of Document Objects from the Output Bucket
output_blobs = storage_client.list_blobs(output_bucket, prefix=output_prefix)
# Document AI may output multiple JSON files per source file
for blob in output_blobs:
# Document AI should only output JSON files to GCS
if ".json" not in blob.name:
print(
f"Skipping non-supported file: {blob.name} - Mimetype: {blob.content_type}"
)
continue
# Download JSON File as bytes object and convert to Document Object
print(f"Fetching {blob.name}")
document = documentai.Document.from_json(
blob.download_as_bytes(), ignore_unknown_fields=True
)
# For a full list of Document object attributes, please reference this page:
# https://cloud.google.com/python/docs/reference/documentai/latest/google.cloud.documentai_v1.types.Document
# Read the text recognition output from the processor
print("The document contains the following text:")
print(document.text)
其中有以下选项：
individualPageSelector对象（IndividualPageSelector） 要处理哪些页面（1-索引）。
从起始整数 从一开始就只处理某些页面。如果文档页数较少，则处理全部。
fromEnd 整数 只从最后处理某些页面，与上面相同。因此，可以将 fromStart 设置为当前的最大值（例如 10），它将仅根据第一页处理请求，从而消除 PAGE_LIMIT_EXCEEDED 错误。
示例代码如下所示：
$filename = 'your-filename-here';
$object = new StdClass();
$object->skipHumanReview = true;
$object->rawDocument = new StdClass();
$object->rawDocument->mimeType = mime_content_type($filename);
$object->rawDocument->content = base64_encode(trim(file_get_contents($filename)));
$object->processOptions = new StdClass();
$object->processOptions->fromStart = 10;
$json = json_encode($object, JSON_UNESCAPED_SLASHES);
请参阅 https://cloud.google.com/document-ai/docs/reference/rest/v1/ProcessOptions 了解更多信息。