# This is an automatically generated code sample.
# To make this code sample work in your Oracle Cloud tenancy,
# please replace the values for any parameters whose current values do not fit
# your use case (such as resource IDs, strings containing ‘EXAMPLE’ or ‘unique_id’, and
# boolean, number, and enum parameters with values not fitting your use case).
import oci
# Create a default config using DEFAULT profile in default location
# Refer to
# https://docs.cloud.oracle.com/en-us/iaas/Content/API/Concepts/sdkconfig.htm#SDK_and_CLI_Configuration_File
# for more info
config = oci.config.from_file()
# Initialize service client with default config file
ai_document_client = oci.ai_document.AIServiceDocumentClient(config)
# Send the request to service, some parameters are not required, see API
# doc for more info
analyze_document_response = ai_document_client.analyze_document(
analyze_document_details=oci.ai_document.models.AnalyzeDocumentDetails(
features=[
oci.ai_document.models.DocumentTextExtractionFeature(
feature_type="TEXT_EXTRACTION",
generate_searchable_pdf=False,
model_id="ocid1.test.oc1..<unique_ID>EXAMPLE-modelId-Value",
selection_mark_detection=False)],
document=oci.ai_document.models.ObjectStorageDocumentDetails(
source="OBJECT_STORAGE",
namespace_name="EXAMPLE-namespaceName-Value",
bucket_name="EXAMPLE-bucketName-Value",
object_name="EXAMPLE-objectName-Value",
page_range=["EXAMPLE--Value"]),
compartment_id="ocid1.test.oc1..<unique_ID>EXAMPLE-compartmentId-Value",
output_location=oci.ai_document.models.OutputLocation(
namespace_name="EXAMPLE-namespaceName-Value",
bucket_name="EXAMPLE-bucketName-Value",
prefix="EXAMPLE-prefix-Value"),
language="EXAMPLE-language-Value",
document_type="HEALTH_INSURANCE_ID",
ocr_data=oci.ai_document.models.AnalyzeDocumentResult(
document_metadata=oci.ai_document.models.DocumentMetadata(
page_count=655,
mime_type="EXAMPLE-mimeType-Value"),
pages=[
oci.ai_document.models.Page(
page_number=942,
dimensions=oci.ai_document.models.Dimensions(
width=7658.252,
height=9447.96,
unit="PIXEL"),
detected_document_types=[
oci.ai_document.models.DetectedDocumentType(
document_type="EXAMPLE-documentType-Value",
confidence=0.45726037,
document_id="ocid1.test.oc1..<unique_ID>EXAMPLE-documentId-Value")],
detected_languages=[
oci.ai_document.models.DetectedLanguage(
language="EXAMPLE-language-Value",
confidence=0.38078272)],
words=[
oci.ai_document.models.Word(
text="EXAMPLE-text-Value",
confidence=0.8342287,
bounding_polygon=oci.ai_document.models.BoundingPolygon(
normalized_vertices=[
oci.ai_document.models.NormalizedVertex(
x=0.25969464,
y=0.46758157)]))],
lines=[
oci.ai_document.models.Line(
text="EXAMPLE-text-Value",
confidence=0.010752916,
bounding_polygon=oci.ai_document.models.BoundingPolygon(
normalized_vertices=[
oci.ai_document.models.NormalizedVertex(
x=0.105644405,
y=0.36052614)]),
word_indexes=[39])],
tables=[
oci.ai_document.models.Table(
row_count=971,
column_count=744,
header_rows=[
oci.ai_document.models.TableRow(
cells=[
oci.ai_document.models.Cell(
text="EXAMPLE-text-Value",
row_index=61,
column_index=869,
confidence=0.678442,
bounding_polygon=oci.ai_document.models.BoundingPolygon(
normalized_vertices=[
oci.ai_document.models.NormalizedVertex(
x=0.79856807,
y=0.82585025)]),
word_indexes=[800])])],
confidence=0.25737917,
bounding_polygon=oci.ai_document.models.BoundingPolygon(
normalized_vertices=[
oci.ai_document.models.NormalizedVertex(
x=0.7323424,
y=0.018351376)]))],
document_fields=[
oci.ai_document.models.DocumentField(
field_type="KEY_VALUE",
field_value=oci.ai_document.models.ValueArray(
value_type="ARRAY",
confidence=0.12567782,
bounding_polygon=oci.ai_document.models.BoundingPolygon(
normalized_vertices=[
oci.ai_document.models.NormalizedVertex(
x=0.8541965,
y=0.14713478)]),
word_indexes=[380],
text="EXAMPLE-text-Value",
normalized_value="EXAMPLE-normalizedValue-Value",
normalized_confidence=0.9049306),
field_label=oci.ai_document.models.FieldLabel(
name="EXAMPLE-name-Value",
confidence=0.23141193),
field_name=oci.ai_document.models.FieldName(
name="EXAMPLE-name-Value",
confidence=0.53373486,
bounding_polygon=oci.ai_document.models.BoundingPolygon(
normalized_vertices=[
oci.ai_document.models.NormalizedVertex(
x=0.15109724,
y=0.02838248)]),
word_indexes=[702]))],
signatures=[
oci.ai_document.models.Signature(
confidence=0.19143075,
bounding_polygon=oci.ai_document.models.BoundingPolygon(
normalized_vertices=[
oci.ai_document.models.NormalizedVertex(
x=0.33537287,
y=0.66658884)]))],
bar_codes=[
oci.ai_document.models.BarCode(
confidence=0.9056299,
value="EXAMPLE-value-Value",
bounding_polygon=oci.ai_document.models.BoundingPolygon(
normalized_vertices=[
oci.ai_document.models.NormalizedVertex(
x=0.33312047,
y=0.43781954)]),
code_type="EXAMPLE-codeType-Value")],
selection_marks=[
oci.ai_document.models.SelectionMark(
state="SELECTED",
confidence=0.8500111,
bounding_polygon=oci.ai_document.models.BoundingPolygon(
normalized_vertices=[
oci.ai_document.models.NormalizedVertex(
x=0.8238592,
y=0.9825451)]))])],
detected_document_types=[
oci.ai_document.models.DetectedDocumentType(
document_type="EXAMPLE-documentType-Value",
confidence=0.73039603,
document_id="ocid1.test.oc1..<unique_ID>EXAMPLE-documentId-Value")],
detected_languages=[
oci.ai_document.models.DetectedLanguage(
language="EXAMPLE-language-Value",
confidence=0.8732025)],
document_classification_model_version="EXAMPLE-documentClassificationModelVersion-Value",
language_classification_model_version="EXAMPLE-languageClassificationModelVersion-Value",
text_extraction_model_version="EXAMPLE-textExtractionModelVersion-Value",
key_value_extraction_model_version="EXAMPLE-keyValueExtractionModelVersion-Value",
table_extraction_model_version="EXAMPLE-tableExtractionModelVersion-Value",
signature_extraction_model_version="EXAMPLE-signatureExtractionModelVersion-Value",
bar_code_extraction_model_version="EXAMPLE-barCodeExtractionModelVersion-Value",
errors=[
oci.ai_document.models.ProcessingError(
code="EXAMPLE-code-Value",
message="EXAMPLE-message-Value")],
searchable_pdf="O0GEO6c7KPdimpz7uXmI")),
if_match="EXAMPLE-ifMatch-Value",
opc_request_id="5PGMWEXVTF3EFDHKF7FV<unique_ID>")
# Get the data from response
print(analyze_document_response.data)