Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Sd2 134 base 64 ocr data extraction #227

Merged
merged 2 commits into from
Jul 15, 2024
Merged

Sd2 134 base 64 ocr data extraction #227

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
084700f
[fix] ValidationError when key is None
KyrianC Jul 15, 2024
0e44d8f
format
KyrianC Jul 15, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
64 changes: 31 additions & 33 deletions edenai_apis/apis/base64/base64_api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,16 +3,23 @@
import mimetypes
import uuid
from enum import Enum
from typing import Any, Dict, Sequence, Type, TypeVar, Union
from io import BytesIO
from typing import Any, Dict, Sequence, Type, TypeVar, Union

import requests
from apis.amazon.helpers import check_webhook_result

from edenai_apis.features import ProviderInterface, OcrInterface
from edenai_apis.apis.base64.base64_helpers import (
extract_item_lignes,
format_financial_document_data,
format_invoice_document_data,
format_receipt_document_data,
)
from edenai_apis.features import OcrInterface, ProviderInterface
from edenai_apis.features.image.face_compare import (
FaceCompareBoundingBox,
FaceCompareDataClass,
FaceMatch,
FaceCompareBoundingBox,
)
from edenai_apis.features.ocr.anonymization_async.anonymization_async_dataclass import (
AnonymizationAsyncDataClass,
Expand All @@ -28,13 +35,15 @@
DataExtractionDataClass,
ItemDataExtraction,
)
from edenai_apis.features.ocr.financial_parser.financial_parser_dataclass import FinancialParserDataClass
from edenai_apis.features.ocr.financial_parser.financial_parser_dataclass import (
FinancialParserDataClass,
)
from edenai_apis.features.ocr.identity_parser import (
IdentityParserDataClass,
InfoCountry,
InfosIdentityParserDataClass,
ItemIdentityParserDataClass,
get_info_country,
InfosIdentityParserDataClass,
)
from edenai_apis.features.ocr.identity_parser.identity_parser_dataclass import (
Country,
Expand All @@ -46,22 +55,16 @@
from edenai_apis.loaders.data_loader import ProviderDataEnum
from edenai_apis.loaders.loaders import load_provider
from edenai_apis.utils.bounding_box import BoundingBox
from apis.amazon.helpers import check_webhook_result
from edenai_apis.utils.exception import ProviderException
from edenai_apis.utils.types import (
AsyncBaseResponseType,
AsyncLaunchJobResponseType,
ResponseType,
AsyncPendingResponseType,
AsyncResponseType,
ResponseType,
)
from edenai_apis.utils.upload_s3 import upload_file_bytes_to_s3, USER_PROCESS
from edenai_apis.apis.base64.base64_helpers import (
extract_item_lignes,
format_invoice_document_data,
format_receipt_document_data,
format_financial_document_data
)
from edenai_apis.utils.upload_s3 import USER_PROCESS, upload_file_bytes_to_s3


class SubfeatureParser(Enum):
RECEIPT = "receipt"
Expand Down Expand Up @@ -128,13 +131,9 @@ def _ocr_finance_document(
ocr_file, "finance/" + document_type.value
)
if document_type == SubfeatureParser.RECEIPT:
standardized_response = format_receipt_document_data(
original_response
)
standardized_response = format_receipt_document_data(original_response)
elif document_type == SubfeatureParser.INVOICE:
standardized_response = format_invoice_document_data(
original_response
)
standardized_response = format_invoice_document_data(original_response)

result = ResponseType[T](
original_response=original_response,
Expand Down Expand Up @@ -164,18 +163,16 @@ def ocr__receipt_parser(
return self._ocr_finance_document(file, SubfeatureParser.RECEIPT)

def ocr__financial_parser(
self, file: str, language: str, document_type: str = "", file_url: str = ""
) -> ResponseType[FinancialParserDataClass]:
original_response = self._send_ocr_document(
file, "finance/" + document_type
)
self, file: str, language: str, document_type: str = "", file_url: str = ""
) -> ResponseType[FinancialParserDataClass]:
original_response = self._send_ocr_document(file, "finance/" + document_type)

standardized_response = format_financial_document_data(original_response)
return ResponseType[FinancialParserDataClass](
original_response=original_response,
standardized_response=standardized_response,
)

def ocr__identity_parser(
self, file: str, file_url: str = ""
) -> ResponseType[IdentityParserDataClass]:
Expand Down Expand Up @@ -408,14 +405,15 @@ def ocr__data_extraction(
except ValueError:
bbox = BoundingBox.unknown()

items.append(
ItemDataExtraction(
key=value.get("key"),
value=value.get("value"),
confidence_score=value.get("confidence"),
bounding_box=bbox,
if key := value.get(key):
items.append(
ItemDataExtraction(
key=key,
value=value.get("value"),
confidence_score=value.get("confidence"),
bounding_box=bbox,
)
)
)

standardized_response = DataExtractionDataClass(fields=items)

Expand Down
Loading