将文档AI与Google的Python一起使用Document AI和Google CodeLabs的代码返回错误或空的结果

Question

我尝试了Codelabs.developers.google.com的以下代码：

import pandas as pd
from google.cloud import documentai_v1 as documentai


def online_process(
    project_id: str,
    location: str,
    processor_id: str,
    file_path: str,
    mime_type: str,
) -> documentai.Document:
    """
    Processes a document using the Document AI Online Processing API.
    """

    opts = {"api_endpoint": f"{location}-documentai.googleapis.com"}

    # Instantiates a client
    documentai_client = documentai.DocumentProcessorServiceClient(client_options=opts)

    # The full resource name of the processor, e.g.:
    # projects/project-id/locations/location/processor/processor-id
    # You must create new processors in the Cloud Console first
    resource_name = documentai_client.processor_path(project_id, location, processor_id)

    # Read the file into memory
    with open(file_path, "rb") as file:
        file_content = file.read()

    # Load Binary Data into Document AI RawDocument Object
    raw_document = documentai.RawDocument(content=file_content, mime_type=mime_type)

    # Configure the process request
    request = documentai.ProcessRequest(name=resource_name, raw_document=raw_document)

    # Use the Document AI client to process the sample form
    result = documentai_client.process_document(request=request)

    return result.document


PROJECT_ID = "YOUR_PROJECT_ID"
LOCATION = "YOUR_PROJECT_LOCATION"  # Format is 'us' or 'eu'
PROCESSOR_ID = "PROCUREMENT_SPLITTER_ID"  # Create processor in Cloud Console

# The local file in your current working directory
FILE_PATH = "procurement_multi_document.pdf"
# Refer to https://cloud.google.com/document-ai/docs/processors-list
# for supported file types
MIME_TYPE = "application/pdf"

document = online_process(
    project_id=PROJECT_ID,
    location=LOCATION,
    processor_id=PROCESSOR_ID,
    file_path=FILE_PATH,
    mime_type=MIME_TYPE,
)

print("Document processing complete.")

types = []
confidence = []
pages = []

# Each Document.entity is a classification
for entity in document.entities:
    classification = entity.type_
    types.append(classification)
    confidence.append(f"{entity.confidence:.0%}")

    # entity.page_ref contains the pages that match the classification
    pages_list = []
    for page_ref in entity.page_anchor.page_refs:
        pages_list.append(page_ref.page)
    pages.append(pages_list)

# Create a Pandas Dataframe to print the values in tabular format.
df = pd.DataFrame({"Classification": types, "Confidence": confidence, "Pages": pages})

print(df)

预期输出（类似）：

$ python3 classification.py
Document processing complete.
         Classification Confidence Pages
0     invoice_statement       100%   [0]
1     receipt_statement        98%   [1]
2                 other        81%   [2]
3     utility_statement       100%   [3]
4  restaurant_statement       100%   [4]

结果输出：

Document processing complete.
Empty DataFrame
Columns: [Classification, Confidence, Pages]
Index: []

我检查了Google Documentai的其他所有输入，其他一切似乎都很好。但是，我可以使用document.text毫无问题地获取文本（OCR）。也许我已经达到了我的DocumentAi配额的结尾？如果可能的话，还有其他原因或如何解决？谢谢。

Answer 1

文档AI是一种文档理解解决方案，它使用机器学习使非结构化数据更易于理解和分析。来自您使用的代码，用于专业处理器将输入作为发票或收据或实用程序语句，这些发票是非结构化文档并采购结构化数据。文档AI中支持的文件类型在此。问题似乎是您正在使用的文件类型。尝试使用文档中列出的文件类型。有关更多信息，您可以检查此 link 。

我尝试了以下代码以获取预期的输出。

代码

import pandas as pd
from google.cloud import documentai_v1 as documentai


def online_process(
   project_id: "project",
   location: "us",
   processor_id: "processor-id",
   file_path: "file_path",
   mime_type: "mime_type",
) -> documentai.Document:
   
   opts = {"api_endpoint": f"{location}-documentai.googleapis.com"}

   # Instantiates a client
   documentai_client = documentai.DocumentProcessorServiceClient(client_options=opts)

   resource_name = documentai_client.processor_path(project_id, location, processor_id)

   # Read the file into memory
   with open(file_path, "rb") as file:
       file_content = file.read()

   # Load Binary Data into Document AI RawDocument Object
   raw_document = documentai.RawDocument(content=file_content, mime_type=mime_type)

   # Configure the process request
   request = documentai.ProcessRequest(name=resource_name, raw_document=raw_document)

   # Use the Document AI client to process the sample form
   result = documentai_client.process_document(request=request)

   return result.document


PROJECT_ID = "project"
LOCATION = "us" 
PROCESSOR_ID = "processor-id"  

# The local file in your current working directory
FILE_PATH = "file_path"
# Refer to https://cloud.google.com/document-ai/docs/processors-list
# for supported file types
MIME_TYPE = "mime_type"

document = online_process(
   project_id=PROJECT_ID,
   location=LOCATION,
   processor_id=PROCESSOR_ID,
   file_path=FILE_PATH,
   mime_type=MIME_TYPE,
)

print("Document processing complete.")

types = []
confidence = []
pages = []

# Each Document.entity is a classification
for entity in document.entities:
   classification = entity.type_
   types.append(classification)
   confidence.append(f"{entity.confidence:.0%}")

   # entity.page_ref contains the pages that match the classification
   pages_list = []
   for page_ref in entity.page_anchor.page_refs:
       pages_list.append(page_ref.page)
   pages.append(pages_list)

# Create a Pandas Dataframe to print the values in tabular format.
df = pd.DataFrame({"Classification": types, "Confidence": confidence, "Pages": pages})

print(df)

不同文件的输出：

1. procurement_multi_document.pdf

   

2. invoice.pdf

   

3. sample.pdf -pdf文件仅包含段落

   

4. kitten.png-包含单个图像