Module veryfi.documents

View Source

import os

import base64

from typing import Dict, List, Optional

from veryfi._documents.line_items import LineItems

from veryfi._documents.tags import Tags

from veryfi._documents.pdf_split import PDFSplit

from veryfi.client_base import Client

class Documents(Tags, LineItems, PDFSplit):

    DEFAULT_CATEGORIES = [

        "Advertising & Marketing",

        "Automotive",

        "Bank Charges & Fees",

        "Legal & Professional Services",

        "Insurance",

        "Meals & Entertainment",

        "Office Supplies & Software",

        "Taxes & Licenses",

        "Travel",

        "Rent & Lease",

        "Repairs & Maintenance",

        "Payroll",

        "Utilities",

        "Job Supplies",

        "Grocery",

    ]

    def __init__(self, client: Client):

        self.client = client

        LineItems.__init__(self, self.client)

        Tags.__init__(self, self.client)

        PDFSplit.__init__(self, self.client)

    def get_documents(

        self,

        q: Optional[str] = None,

        external_id: Optional[str] = None,

        tag: Optional[str] = None,

        created_gt: Optional[str] = None,

        created_gte: Optional[str] = None,

        created_lt: Optional[str] = None,

        created_lte: Optional[str] = None,

        **kwargs,

    ) -> Dict:

        """

        Get list of documents.

        https://docs.veryfi.com/api/receipts-invoices/search-documents/

        :param q: Search query

        :param external_id: Search by external ID

        :param tag: Search by tag

        :param created_gt: Search by created date greater than

        :param created_gte: Search by created date greater than or equal to

        :param created_lt: Search by created date less than

        :param created_lte: Search by created date less than or equal to

        :param kwargs: Additional query parameters

        :return: List of previously processed documents

        """

        query_params = {}

        if q:

            query_params["q"] = q

        if external_id:

            query_params["external_id"] = external_id

        if tag:

            query_params["tag"] = tag

        if created_gt:

            query_params["created__gt"] = created_gt

        if created_gte:

            query_params["created__gte"] = created_gte

        if created_lt:

            query_params["created__lt"] = created_lt

        if created_lte:

            query_params["created__lte"] = created_lte

        query_params.update(kwargs)

        endpoint_name = "/documents/"

        return self.client._request("GET", endpoint_name, {}, query_params)

    def get_document(self, document_id: int, **kwargs) -> Dict:

        """

        Retrieve document by ID

        https://docs.veryfi.com/api/receipts-invoices/get-a-document/

        :param document_id: ID of the document you'd like to retrieve

        :param kwargs: Additional query parameters

        :return: Data extracted from the Document

        """

        endpoint_name = f"/documents/{document_id}/"

        return self.client._request("GET", endpoint_name, {}, kwargs)

    def process_document(

        self,

        file_path: str,

        categories: Optional[List] = None,

        delete_after_processing: bool = False,

        **kwargs,

    ) -> Dict:

        """

        Process a document and extract all the fields from it.

        https://docs.veryfi.com/api/receipts-invoices/process-a-document/

        :param file_path: Path on disk to a file to submit for data extraction

        :param categories: List of categories Veryfi can use to categorize the document

        :param delete_after_processing: Delete this document from Veryfi after data has been extracted

        :param kwargs: Additional body parameters

        :return: Data extracted from the document

        """

        if not categories:

            categories = self.DEFAULT_CATEGORIES

        file_name = os.path.basename(file_path)

        with open(file_path, "rb") as image_file:

            base64_encoded_string = base64.b64encode(image_file.read()).decode("utf-8")

        request_arguments = {

            "file_name": file_name,

            "file_data": base64_encoded_string,

            "categories": categories,

            "auto_delete": delete_after_processing,

        }

        request_arguments.update(kwargs)

        return self.client._request("POST", "/documents/", request_arguments)

    def process_document_url(

        self,

        file_url: Optional[str] = None,

        categories: Optional[List[str]] = None,

        delete_after_processing: bool = False,

        boost_mode: bool = False,

        external_id: Optional[str] = None,

        max_pages_to_process: Optional[int] = None,

        file_urls: Optional[List[str]] = None,

        **kwargs,

    ) -> Dict:

        """Process Document from url and extract all the fields from it.

        https://docs.veryfi.com/api/receipts-invoices/process-a-document/

        :param file_url: Required if file_urls isn't specified. Publicly accessible URL to a file, e.g. "https://cdn.example.com/receipt.jpg".

        :param file_urls: Required if file_url isn't specifies. List of publicly accessible URLs to multiple files, e.g. ["https://cdn.example.com/receipt1.jpg", "https://cdn.example.com/receipt2.jpg"]

        :param categories: List of categories to use when categorizing the document

        :param delete_after_processing: Delete this document from Veryfi after data has been extracted

        :param max_pages_to_process: When sending a long document to Veryfi for processing, this parameter controls how many pages of the document will be read and processed, starting from page 1.

        :param boost_mode: Flag that tells Veryfi whether boost mode should be enabled. When set to 1, Veryfi will skip data enrichment steps, but will process the document faster. Default value for this flag is 0

        :param external_id: Optional custom document identifier. Use this if you would like to assign your own ID to documents

        :param kwargs: Additional body parameters

        :return: Data extracted from the document.

        """

        endpoint_name = "/documents/"

        request_arguments = {

            "auto_delete": delete_after_processing,

            "boost_mode": boost_mode,

            "categories": categories,

            "external_id": external_id,

            "file_url": file_url,

            "file_urls": file_urls,

            "max_pages_to_process": max_pages_to_process,

        }

        request_arguments.update(kwargs)

        return self.client._request("POST", endpoint_name, request_arguments)

    def process_documents_bulk(self, file_urls: List[str]) -> List[int]:

        """

        Process multiple documents from urls and extract all the fields from it.

        If you want to use this endpoint, please contact support@veryfi.com first. Veryfi's Bulk upload allows you to process multiple Documents.

        https://docs.veryfi.com/api/receipts-invoices/bulk-process-multiple-documents/

        :param file_urls: List of publicly accessible URLs to multiple files, e.g. ["https://cdn.example.com/receipt1.jpg", "https://cdn.example.com/receipt2.jpg"]

        :return: List of document IDs being processed

        """

        endpoint_name = "/documents/bulk/"

        request_arguments = {"file_urls": file_urls}

        return self.client._request("POST", endpoint_name, request_arguments)

    def delete_document(self, document_id: int):

        """

        Delete Document from Veryfi

        https://docs.veryfi.com/api/receipts-invoices/delete-a-document/

        :param document_id: ID of the document you'd like to delete

        """

        self.client._request("DELETE", f"/documents/{document_id}/", {"id": document_id})

    def update_document(self, document_id: int, **kwargs) -> Dict:

        """

        Update data for a previously processed document, including almost any field like `vendor`, `date`, `notes` and etc.

        https://docs.veryfi.com/api/receipts-invoices/update-a-document/

        ```veryfi_client.update_document(id, date="2021-01-01", notes="look what I did")```

        :param document_id: ID of the document you'd like to update

        :param kwargs: fields to update

        :return: A document json with updated fields, if fields are writable. Otherwise a document with unchanged fields.

        """

        return self.client._request("PUT", f"/documents/{document_id}/", kwargs)

Classes

Documents

class Documents(
    client: veryfi.client_base.Client
)

View Source

class Documents(Tags, LineItems, PDFSplit):

    DEFAULT_CATEGORIES = [

        "Advertising & Marketing",

        "Automotive",

        "Bank Charges & Fees",

        "Legal & Professional Services",

        "Insurance",

        "Meals & Entertainment",

        "Office Supplies & Software",

        "Taxes & Licenses",

        "Travel",

        "Rent & Lease",

        "Repairs & Maintenance",

        "Payroll",

        "Utilities",

        "Job Supplies",

        "Grocery",

    ]

    def __init__(self, client: Client):

        self.client = client

        LineItems.__init__(self, self.client)

        Tags.__init__(self, self.client)

        PDFSplit.__init__(self, self.client)

    def get_documents(

        self,

        q: Optional[str] = None,

        external_id: Optional[str] = None,

        tag: Optional[str] = None,

        created_gt: Optional[str] = None,

        created_gte: Optional[str] = None,

        created_lt: Optional[str] = None,

        created_lte: Optional[str] = None,

        **kwargs,

    ) -> Dict:

        """

        Get list of documents.

        https://docs.veryfi.com/api/receipts-invoices/search-documents/

        :param q: Search query

        :param external_id: Search by external ID

        :param tag: Search by tag

        :param created_gt: Search by created date greater than

        :param created_gte: Search by created date greater than or equal to

        :param created_lt: Search by created date less than

        :param created_lte: Search by created date less than or equal to

        :param kwargs: Additional query parameters

        :return: List of previously processed documents

        """

        query_params = {}

        if q:

            query_params["q"] = q

        if external_id:

            query_params["external_id"] = external_id

        if tag:

            query_params["tag"] = tag

        if created_gt:

            query_params["created__gt"] = created_gt

        if created_gte:

            query_params["created__gte"] = created_gte

        if created_lt:

            query_params["created__lt"] = created_lt

        if created_lte:

            query_params["created__lte"] = created_lte

        query_params.update(kwargs)

        endpoint_name = "/documents/"

        return self.client._request("GET", endpoint_name, {}, query_params)

    def get_document(self, document_id: int, **kwargs) -> Dict:

        """

        Retrieve document by ID

        https://docs.veryfi.com/api/receipts-invoices/get-a-document/

        :param document_id: ID of the document you'd like to retrieve

        :param kwargs: Additional query parameters

        :return: Data extracted from the Document

        """

        endpoint_name = f"/documents/{document_id}/"

        return self.client._request("GET", endpoint_name, {}, kwargs)

    def process_document(

        self,

        file_path: str,

        categories: Optional[List] = None,

        delete_after_processing: bool = False,

        **kwargs,

    ) -> Dict:

        """

        Process a document and extract all the fields from it.

        https://docs.veryfi.com/api/receipts-invoices/process-a-document/

        :param file_path: Path on disk to a file to submit for data extraction

        :param categories: List of categories Veryfi can use to categorize the document

        :param delete_after_processing: Delete this document from Veryfi after data has been extracted

        :param kwargs: Additional body parameters

        :return: Data extracted from the document

        """

        if not categories:

            categories = self.DEFAULT_CATEGORIES

        file_name = os.path.basename(file_path)

        with open(file_path, "rb") as image_file:

            base64_encoded_string = base64.b64encode(image_file.read()).decode("utf-8")

        request_arguments = {

            "file_name": file_name,

            "file_data": base64_encoded_string,

            "categories": categories,

            "auto_delete": delete_after_processing,

        }

        request_arguments.update(kwargs)

        return self.client._request("POST", "/documents/", request_arguments)

    def process_document_url(

        self,

        file_url: Optional[str] = None,

        categories: Optional[List[str]] = None,

        delete_after_processing: bool = False,

        boost_mode: bool = False,

        external_id: Optional[str] = None,

        max_pages_to_process: Optional[int] = None,

        file_urls: Optional[List[str]] = None,

        **kwargs,

    ) -> Dict:

        """Process Document from url and extract all the fields from it.

        https://docs.veryfi.com/api/receipts-invoices/process-a-document/

        :param file_url: Required if file_urls isn't specified. Publicly accessible URL to a file, e.g. "https://cdn.example.com/receipt.jpg".

        :param file_urls: Required if file_url isn't specifies. List of publicly accessible URLs to multiple files, e.g. ["https://cdn.example.com/receipt1.jpg", "https://cdn.example.com/receipt2.jpg"]

        :param categories: List of categories to use when categorizing the document

        :param delete_after_processing: Delete this document from Veryfi after data has been extracted

        :param max_pages_to_process: When sending a long document to Veryfi for processing, this parameter controls how many pages of the document will be read and processed, starting from page 1.

        :param boost_mode: Flag that tells Veryfi whether boost mode should be enabled. When set to 1, Veryfi will skip data enrichment steps, but will process the document faster. Default value for this flag is 0

        :param external_id: Optional custom document identifier. Use this if you would like to assign your own ID to documents

        :param kwargs: Additional body parameters

        :return: Data extracted from the document.

        """

        endpoint_name = "/documents/"

        request_arguments = {

            "auto_delete": delete_after_processing,

            "boost_mode": boost_mode,

            "categories": categories,

            "external_id": external_id,

            "file_url": file_url,

            "file_urls": file_urls,

            "max_pages_to_process": max_pages_to_process,

        }

        request_arguments.update(kwargs)

        return self.client._request("POST", endpoint_name, request_arguments)

    def process_documents_bulk(self, file_urls: List[str]) -> List[int]:

        """

        Process multiple documents from urls and extract all the fields from it.

        If you want to use this endpoint, please contact support@veryfi.com first. Veryfi's Bulk upload allows you to process multiple Documents.

        https://docs.veryfi.com/api/receipts-invoices/bulk-process-multiple-documents/

        :param file_urls: List of publicly accessible URLs to multiple files, e.g. ["https://cdn.example.com/receipt1.jpg", "https://cdn.example.com/receipt2.jpg"]

        :return: List of document IDs being processed

        """

        endpoint_name = "/documents/bulk/"

        request_arguments = {"file_urls": file_urls}

        return self.client._request("POST", endpoint_name, request_arguments)

    def delete_document(self, document_id: int):

        """

        Delete Document from Veryfi

        https://docs.veryfi.com/api/receipts-invoices/delete-a-document/

        :param document_id: ID of the document you'd like to delete

        """

        self.client._request("DELETE", f"/documents/{document_id}/", {"id": document_id})

    def update_document(self, document_id: int, **kwargs) -> Dict:

        """

        Update data for a previously processed document, including almost any field like `vendor`, `date`, `notes` and etc.

        https://docs.veryfi.com/api/receipts-invoices/update-a-document/

        ```veryfi_client.update_document(id, date="2021-01-01", notes="look what I did")```

        :param document_id: ID of the document you'd like to update

        :param kwargs: fields to update

        :return: A document json with updated fields, if fields are writable. Otherwise a document with unchanged fields.

        """

        return self.client._request("PUT", f"/documents/{document_id}/", kwargs)

---

Ancestors (in MRO)

• veryfi._documents.tags.Tags
• veryfi._documents.line_items.LineItems
• veryfi._documents.pdf_split.PDFSplit

Descendants

• veryfi.client.Client

Class variables

DEFAULT_CATEGORIES

Methods

add_line_item

def add_line_item(
    self,
    document_id: int,
    payload: Dict
) -> Dict

Add a new line item on an existing document.

https://docs.veryfi.com/api/receipts-invoices/create-a-line-item/

Parameters:

Name	Type	Description	Default
document_id	None	ID of the document you'd like to update	None
payload	None	line item object to add	None

Returns:

Type	Description
None	Added line item data

View Source

    def add_line_item(self, document_id: int, payload: Dict) -> Dict:

        """

        Add a new line item on an existing document.

        https://docs.veryfi.com/api/receipts-invoices/create-a-line-item/

        :param document_id: ID of the document you'd like to update

        :param payload: line item object to add

        :return: Added line item data

        """

        return self.client._request("POST", f"/documents/{document_id}/line-items/", payload)

add_tag

def add_tag(
    self,
    document_id,
    tag_name
)

Add a new tag on an existing document.

https://docs.veryfi.com/api/receipts-invoices/add-a-tag-to-a-document/

Parameters:

Name	Type	Description	Default
document_id	None	ID of the document you'd like to update	None
tag_name	None	name of the new tag	None

Returns:

Type	Description
None	Added tag data

View Source

    def add_tag(self, document_id, tag_name):

        """

        Add a new tag on an existing document.

        https://docs.veryfi.com/api/receipts-invoices/add-a-tag-to-a-document/

        :param document_id: ID of the document you'd like to update

        :param tag_name: name of the new tag

        :return: Added tag data

        """

        endpoint_name = f"/documents/{document_id}/tags/"

        request_arguments = {"name": tag_name}

        return self.client._request("PUT", endpoint_name, request_arguments)

add_tags

def add_tags(
    self,
    document_id,
    tags
)

Add multiple tags on an existing document.

https://docs.veryfi.com/api/receipts-invoices/add-tags-to-a-document/

Parameters:

Name	Type	Description	Default
document_id	None	ID of the document you'd like to update	None
tags	None	array of strings	None

Returns:

Type	Description
None	Added tags data

View Source

    def add_tags(self, document_id, tags):

        """

        Add multiple tags on an existing document.

        https://docs.veryfi.com/api/receipts-invoices/add-tags-to-a-document/

        :param document_id: ID of the document you'd like to update

        :param tags: array of strings

        :return: Added tags data

        """

        endpoint_name = f"/documents/{document_id}/tags/"

        request_arguments = {"tags": tags}

        return self.client._request("POST", endpoint_name, request_arguments)

delete_document

def delete_document(
    self,
    document_id: int
)

Delete Document from Veryfi

https://docs.veryfi.com/api/receipts-invoices/delete-a-document/

Parameters:

Name	Type	Description	Default
document_id	None	ID of the document you'd like to delete	None

View Source

    def delete_document(self, document_id: int):

        """

        Delete Document from Veryfi

        https://docs.veryfi.com/api/receipts-invoices/delete-a-document/

        :param document_id: ID of the document you'd like to delete

        """

        self.client._request("DELETE", f"/documents/{document_id}/", {"id": document_id})

delete_line_item

def delete_line_item(
    self,
    document_id: int,
    line_item_id: int
)

Delete an existing line item on an existing document.

https://docs.veryfi.com/api/receipts-invoices/delete-a-line-item/

Parameters:

Name	Type	Description	Default
document_id	None	ID of the document you'd like to delete	None
line_item_id	None	ID of the line item you'd like to delete	None

View Source

    def delete_line_item(self, document_id: int, line_item_id: int):

        """

        Delete an existing line item on an existing document.

        https://docs.veryfi.com/api/receipts-invoices/delete-a-line-item/

        :param document_id: ID of the document you'd like to delete

        :param line_item_id: ID of the line item you'd like to delete

        """

        self.client._request("DELETE", f"/documents/{document_id}/line-items/{line_item_id}")

delete_line_items

def delete_line_items(
    self,
    document_id: int
)

Delete all line items on an existing document.

https://docs.veryfi.com/api/receipts-invoices/delete-all-document-line-items/

Parameters:

Name	Type	Description	Default
document_id	None	ID of the document you'd like to delete	None

View Source

    def delete_line_items(self, document_id: int):

        """

        Delete all line items on an existing document.

        https://docs.veryfi.com/api/receipts-invoices/delete-all-document-line-items/

        :param document_id: ID of the document you'd like to delete

        """

        self.client._request("DELETE", f"/documents/{document_id}/line-items/")

delete_tag

def delete_tag(
    self,
    document_id,
    tag_id
)

Unlink a tag from the list of tags assigned to a specific Document.

https://docs.veryfi.com/api/receipts-invoices/unlink-a-tag-from-a-document/

Parameters:

Name	Type	Description	Default
document_id	None	ID of the document	None
tag_id	None	ID of the tag you'd like to unlink	None

View Source

    def delete_tag(self, document_id, tag_id):

        """

        Unlink a tag from the list of tags assigned to a specific Document.

        https://docs.veryfi.com/api/receipts-invoices/unlink-a-tag-from-a-document/

        :param document_id: ID of the document

        :param tag_id: ID of the tag you'd like to unlink

        """

        endpoint_name = f"/documents/{document_id}/tags/{tag_id}"

        self.client._request("DELETE", endpoint_name, {})

delete_tags

def delete_tags(
    self,
    document_id
)

Unlink all tags assigned to a specific Document.

https://docs.veryfi.com/api/receipts-invoices/unlink-all-tags-from-a-document/

Parameters:

Name	Type	Description	Default
document_id	None	ID of the document	None

View Source

    def delete_tags(self, document_id):

        """

        Unlink all tags assigned to a specific Document.

        https://docs.veryfi.com/api/receipts-invoices/unlink-all-tags-from-a-document/

        :param document_id: ID of the document

        """

        endpoint_name = f"/documents/{document_id}/tags"

        self.client._request("DELETE", endpoint_name, {})

get_document

def get_document(
    self,
    document_id: int,
    **kwargs
) -> Dict

Retrieve document by ID

https://docs.veryfi.com/api/receipts-invoices/get-a-document/

Parameters:

Name	Type	Description	Default
document_id	None	ID of the document you'd like to retrieve	None
kwargs	None	Additional query parameters	None

Returns:

Type	Description
None	Data extracted from the Document

View Source

    def get_document(self, document_id: int, **kwargs) -> Dict:

        """

        Retrieve document by ID

        https://docs.veryfi.com/api/receipts-invoices/get-a-document/

        :param document_id: ID of the document you'd like to retrieve

        :param kwargs: Additional query parameters

        :return: Data extracted from the Document

        """

        endpoint_name = f"/documents/{document_id}/"

        return self.client._request("GET", endpoint_name, {}, kwargs)

get_documents

def get_documents(
    self,
    q: Optional[str] = None,
    external_id: Optional[str] = None,
    tag: Optional[str] = None,
    created_gt: Optional[str] = None,
    created_gte: Optional[str] = None,
    created_lt: Optional[str] = None,
    created_lte: Optional[str] = None,
    **kwargs
) -> Dict

Get list of documents.

https://docs.veryfi.com/api/receipts-invoices/search-documents/

Parameters:

Name	Type	Description	Default
q	None	Search query	None
external_id	None	Search by external ID	None
tag	None	Search by tag	None
created_gt	None	Search by created date greater than	None
created_gte	None	Search by created date greater than or equal to	None
created_lt	None	Search by created date less than	None
created_lte	None	Search by created date less than or equal to	None
kwargs	None	Additional query parameters	None

Returns:

Type	Description
None	List of previously processed documents

View Source

    def get_documents(

        self,

        q: Optional[str] = None,

        external_id: Optional[str] = None,

        tag: Optional[str] = None,

        created_gt: Optional[str] = None,

        created_gte: Optional[str] = None,

        created_lt: Optional[str] = None,

        created_lte: Optional[str] = None,

        **kwargs,

    ) -> Dict:

        """

        Get list of documents.

        https://docs.veryfi.com/api/receipts-invoices/search-documents/

        :param q: Search query

        :param external_id: Search by external ID

        :param tag: Search by tag

        :param created_gt: Search by created date greater than

        :param created_gte: Search by created date greater than or equal to

        :param created_lt: Search by created date less than

        :param created_lte: Search by created date less than or equal to

        :param kwargs: Additional query parameters

        :return: List of previously processed documents

        """

        query_params = {}

        if q:

            query_params["q"] = q

        if external_id:

            query_params["external_id"] = external_id

        if tag:

            query_params["tag"] = tag

        if created_gt:

            query_params["created__gt"] = created_gt

        if created_gte:

            query_params["created__gte"] = created_gte

        if created_lt:

            query_params["created__lt"] = created_lt

        if created_lte:

            query_params["created__lte"] = created_lte

        query_params.update(kwargs)

        endpoint_name = "/documents/"

        return self.client._request("GET", endpoint_name, {}, query_params)

get_documents_from_pdf

def get_documents_from_pdf(
    self,
    document_id: int
)

Get Documents from PDF endpoint allows you to retrieve a collection of previously processed documents.

https://docs.veryfi.com/api/receipts-invoices/get-documents-from-pdf/

Parameters:

Name	Type	Description	Default
document_id	None	ID of the document you'd like to retrieve	None

Returns:

Type	Description
None	The processed Document response.

View Source

    def get_documents_from_pdf(self, document_id: int):

        """

        Get Documents from PDF endpoint allows you to retrieve a collection of previously processed documents.

        https://docs.veryfi.com/api/receipts-invoices/get-documents-from-pdf/

        :param document_id: ID of the document you'd like to retrieve

        :return: The processed Document response.

        """

        endpoint_name = f"/documents-set/{document_id}"

        return self.client._request("GET", endpoint_name, {})

get_line_item

def get_line_item(
    self,
    document_id: int,
    line_item_id: int
)

Retrieve a line item for existing document by ID.

https://docs.veryfi.com/api/receipts-invoices/get-a-line-item/

Parameters:

Name	Type	Description	Default
document_id	None	ID of the document you'd like to retrieve	None
line_item_id	None	ID of the line item you'd like to retrieve	None

Returns:

Type	Description
None	Line item extracted from the document

View Source

    def get_line_item(self, document_id: int, line_item_id: int):

        """

        Retrieve a line item for existing document by ID.

        https://docs.veryfi.com/api/receipts-invoices/get-a-line-item/

        :param document_id: ID of the document you'd like to retrieve

        :param line_item_id: ID of the line item you'd like to retrieve

        :return: Line item extracted from the document

        """

        return self.client._request("GET", f"/documents/{document_id}/line-items/{line_item_id}")

get_line_items

def get_line_items(
    self,
    document_id: int
)

Retrieve all line items for a document.

https://docs.veryfi.com/api/receipts-invoices/get-document-line-items/

Parameters:

Name	Type	Description	Default
document_id	None	ID of the document you'd like to retrieve	None

Returns:

Type	Description
None	List of line items extracted from the document

View Source

    def get_line_items(self, document_id: int):

        """

        Retrieve all line items for a document.

        https://docs.veryfi.com/api/receipts-invoices/get-document-line-items/

        :param document_id: ID of the document you'd like to retrieve

        :return: List of line items extracted from the document

        """

        return self.client._request("GET", f"/documents/{document_id}/line-items/")

get_pdf

def get_pdf(
    self,
    **kwargs
)

Get a Submitted PDF endpoint allows you to retrieve a collection of previously processed.

https://docs.veryfi.com/api/receipts-invoices/get-submitted-pdf/

Parameters:

Name	Type	Description	Default
kwargs	None	Additional query parameters.	None

Returns:

Type	Description
None	The processed Document response.

View Source

    def get_pdf(self, **kwargs):

        """

        Get a Submitted PDF endpoint allows you to retrieve a collection of previously processed.

        https://docs.veryfi.com/api/receipts-invoices/get-submitted-pdf/

        :param kwargs: Additional query parameters.

        :return: The processed Document response.

        """

        endpoint_name = "/documents-set/"

        return self.client._request("GET", endpoint_name, {}, kwargs)

get_tags

def get_tags(
    self,
    document_id
)

Return all Tag assigned to a specific Document.

https://docs.veryfi.com/api/receipts-invoices/get-document-tags/

Parameters:

Name	Type	Description	Default
document_id	None	ID of the document you'd like to get	None

Returns:

Type	Description
None	Added tags data

View Source

    def get_tags(self, document_id):

        """

        Return all Tag assigned to a specific Document.

        https://docs.veryfi.com/api/receipts-invoices/get-document-tags/

        :param document_id: ID of the document you'd like to get

        :return: Added tags data

        """

        endpoint_name = f"/documents/{document_id}/tags"

        return self.client._request("GET", endpoint_name, {})

process_document

def process_document(
    self,
    file_path: str,
    categories: Optional[List] = None,
    delete_after_processing: bool = False,
    **kwargs
) -> Dict

Process a document and extract all the fields from it.

https://docs.veryfi.com/api/receipts-invoices/process-a-document/

Parameters:

Name	Type	Description	Default
file_path	None	Path on disk to a file to submit for data extraction	None
categories	None	List of categories Veryfi can use to categorize the document	None
delete_after_processing	None	Delete this document from Veryfi after data has been extracted	None
kwargs	None	Additional body parameters	None

Returns:

Type	Description
None	Data extracted from the document

View Source

    def process_document(

        self,

        file_path: str,

        categories: Optional[List] = None,

        delete_after_processing: bool = False,

        **kwargs,

    ) -> Dict:

        """

        Process a document and extract all the fields from it.

        https://docs.veryfi.com/api/receipts-invoices/process-a-document/

        :param file_path: Path on disk to a file to submit for data extraction

        :param categories: List of categories Veryfi can use to categorize the document

        :param delete_after_processing: Delete this document from Veryfi after data has been extracted

        :param kwargs: Additional body parameters

        :return: Data extracted from the document

        """

        if not categories:

            categories = self.DEFAULT_CATEGORIES

        file_name = os.path.basename(file_path)

        with open(file_path, "rb") as image_file:

            base64_encoded_string = base64.b64encode(image_file.read()).decode("utf-8")

        request_arguments = {

            "file_name": file_name,

            "file_data": base64_encoded_string,

            "categories": categories,

            "auto_delete": delete_after_processing,

        }

        request_arguments.update(kwargs)

        return self.client._request("POST", "/documents/", request_arguments)

process_document_url

def process_document_url(
    self,
    file_url: Optional[str] = None,
    categories: Optional[List[str]] = None,
    delete_after_processing: bool = False,
    boost_mode: bool = False,
    external_id: Optional[str] = None,
    max_pages_to_process: Optional[int] = None,
    file_urls: Optional[List[str]] = None,
    **kwargs
) -> Dict

Process Document from url and extract all the fields from it.

https://docs.veryfi.com/api/receipts-invoices/process-a-document/

Parameters:

Name	Type	Description	Default
file_url	None	Required if file_urls isn't specified. Publicly accessible URL to a file, e.g. "https://cdn.example.com/receipt.jpg".	None
file_urls	None	Required if file_url isn't specifies. List of publicly accessible URLs to multiple files, e.g. ["https://cdn.example.com/receipt1.jpg", "https://cdn.example.com/receipt2.jpg"]	None
categories	None	List of categories to use when categorizing the document	None
delete_after_processing	None	Delete this document from Veryfi after data has been extracted	None
max_pages_to_process	None	When sending a long document to Veryfi for processing, this parameter controls how many pages of the document will be read and processed, starting from page 1.	None
boost_mode	None	Flag that tells Veryfi whether boost mode should be enabled. When set to 1, Veryfi will skip data enrichment steps, but will process the document faster. Default value for this flag is 0	None
external_id	None	Optional custom document identifier. Use this if you would like to assign your own ID to documents	None
kwargs	None	Additional body parameters	None

Returns:

Type	Description
None	Data extracted from the document.

View Source

    def process_document_url(

        self,

        file_url: Optional[str] = None,

        categories: Optional[List[str]] = None,

        delete_after_processing: bool = False,

        boost_mode: bool = False,

        external_id: Optional[str] = None,

        max_pages_to_process: Optional[int] = None,

        file_urls: Optional[List[str]] = None,

        **kwargs,

    ) -> Dict:

        """Process Document from url and extract all the fields from it.

        https://docs.veryfi.com/api/receipts-invoices/process-a-document/

        :param file_url: Required if file_urls isn't specified. Publicly accessible URL to a file, e.g. "https://cdn.example.com/receipt.jpg".

        :param file_urls: Required if file_url isn't specifies. List of publicly accessible URLs to multiple files, e.g. ["https://cdn.example.com/receipt1.jpg", "https://cdn.example.com/receipt2.jpg"]

        :param categories: List of categories to use when categorizing the document

        :param delete_after_processing: Delete this document from Veryfi after data has been extracted

        :param max_pages_to_process: When sending a long document to Veryfi for processing, this parameter controls how many pages of the document will be read and processed, starting from page 1.

        :param boost_mode: Flag that tells Veryfi whether boost mode should be enabled. When set to 1, Veryfi will skip data enrichment steps, but will process the document faster. Default value for this flag is 0

        :param external_id: Optional custom document identifier. Use this if you would like to assign your own ID to documents

        :param kwargs: Additional body parameters

        :return: Data extracted from the document.

        """

        endpoint_name = "/documents/"

        request_arguments = {

            "auto_delete": delete_after_processing,

            "boost_mode": boost_mode,

            "categories": categories,

            "external_id": external_id,

            "file_url": file_url,

            "file_urls": file_urls,

            "max_pages_to_process": max_pages_to_process,

        }

        request_arguments.update(kwargs)

        return self.client._request("POST", endpoint_name, request_arguments)

process_documents_bulk

def process_documents_bulk(
    self,
    file_urls: List[str]
) -> List[int]

Process multiple documents from urls and extract all the fields from it.

If you want to use this endpoint, please contact support@veryfi.com first. Veryfi's Bulk upload allows you to process multiple Documents. https://docs.veryfi.com/api/receipts-invoices/bulk-process-multiple-documents/

Parameters:

Name	Type	Description	Default
file_urls	None	List of publicly accessible URLs to multiple files, e.g. ["https://cdn.example.com/receipt1.jpg", "https://cdn.example.com/receipt2.jpg"]	None

Returns:

Type	Description
None	List of document IDs being processed

View Source

    def process_documents_bulk(self, file_urls: List[str]) -> List[int]:

        """

        Process multiple documents from urls and extract all the fields from it.

        If you want to use this endpoint, please contact support@veryfi.com first. Veryfi's Bulk upload allows you to process multiple Documents.

        https://docs.veryfi.com/api/receipts-invoices/bulk-process-multiple-documents/

        :param file_urls: List of publicly accessible URLs to multiple files, e.g. ["https://cdn.example.com/receipt1.jpg", "https://cdn.example.com/receipt2.jpg"]

        :return: List of document IDs being processed

        """

        endpoint_name = "/documents/bulk/"

        request_arguments = {"file_urls": file_urls}

        return self.client._request("POST", endpoint_name, request_arguments)

replace_tags

def replace_tags(
    self,
    document_id,
    tags
)

Replace multiple tags on an existing document.

https://docs.veryfi.com/api/receipts-invoices/update-a-document/

Parameters:

Name	Type	Description	Default
document_id	None	ID of the document you'd like to update	None
tags	None	array of strings	None

Returns:

Type	Description
None	Added tags data

View Source

    def replace_tags(self, document_id, tags):

        """

        Replace multiple tags on an existing document.

        https://docs.veryfi.com/api/receipts-invoices/update-a-document/

        :param document_id: ID of the document you'd like to update

        :param tags: array of strings

        :return: Added tags data

        """

        endpoint_name = f"/documents/{document_id}/"

        request_arguments = {"tags": tags}

        return self.client._request("PUT", endpoint_name, request_arguments)

split_and_process_pdf

def split_and_process_pdf(
    self,
    file_path: str,
    categories: Optional[List] = None,
    **kwargs
) -> Dict

Process a document and extract all the fields from it

https://docs.veryfi.com/api/receipts-invoices/split-and-process-a-pdf/

Parameters:

Name	Type	Description	Default
file_path	None	Path on disk to a file to submit for data extraction	None
categories	None	List of categories Veryfi can use to categorize the document	None
kwargs	None	Additional body parameters	None

Returns:

Type	Description
None	Data extracted from the document

View Source

    def split_and_process_pdf(

        self,

        file_path: str,

        categories: Optional[List] = None,

        **kwargs,

    ) -> Dict:

        """

        Process a document and extract all the fields from it

        https://docs.veryfi.com/api/receipts-invoices/split-and-process-a-pdf/

        :param file_path: Path on disk to a file to submit for data extraction

        :param categories: List of categories Veryfi can use to categorize the document

        :param kwargs: Additional body parameters

        :return: Data extracted from the document

        """

        endpoint_name = "/documents-set/"

        categories = categories or []

        file_name = os.path.basename(file_path)

        with open(file_path, "rb") as image_file:

            base64_encoded_string = base64.b64encode(image_file.read()).decode("utf-8")

        request_arguments = {

            "file_name": file_name,

            "file_data": base64_encoded_string,

            "categories": categories,

        }

        request_arguments.update(kwargs)

        return self.client._request("POST", endpoint_name, request_arguments)

split_and_process_pdf_url

def split_and_process_pdf_url(
    self,
    file_url: Optional[str] = None,
    categories: Optional[List[str]] = None,
    max_pages_to_process: Optional[int] = None,
    file_urls: Optional[List[str]] = None,
    **kwargs
) -> Dict

Process Document from url and extract all the fields from it.

https://docs.veryfi.com/api/receipts-invoices/split-and-process-a-pdf/

Parameters:

Name	Type	Description	Default
file_url	None	Required if file_urls isn't specified. Publicly accessible URL to a file, e.g. "https://cdn.example.com/receipt.jpg".	None
file_urls	None	Required if file_url isn't specifies. List of publicly accessible URLs to multiple files, e.g. ["https://cdn.example.com/receipt1.jpg", "https://cdn.example.com/receipt2.jpg"]	None
categories	None	List of categories to use when categorizing the document	None
max_pages_to_process	None	When sending a long document to Veryfi for processing, this parameter controls how many pages of the document will be read and processed, starting from page 1.	None
kwargs	None	Additional body parameters	None

Returns:

Type	Description
None	Data extracted from the document.

View Source

    def split_and_process_pdf_url(

        self,

        file_url: Optional[str] = None,

        categories: Optional[List[str]] = None,

        max_pages_to_process: Optional[int] = None,

        file_urls: Optional[List[str]] = None,

        **kwargs,

    ) -> Dict:

        """Process Document from url and extract all the fields from it.

        https://docs.veryfi.com/api/receipts-invoices/split-and-process-a-pdf/

        :param file_url: Required if file_urls isn't specified. Publicly accessible URL to a file, e.g. "https://cdn.example.com/receipt.jpg".

        :param file_urls: Required if file_url isn't specifies. List of publicly accessible URLs to multiple files, e.g. ["https://cdn.example.com/receipt1.jpg", "https://cdn.example.com/receipt2.jpg"]

        :param categories: List of categories to use when categorizing the document

        :param max_pages_to_process: When sending a long document to Veryfi for processing, this parameter controls how many pages of the document will be read and processed, starting from page 1.

        :param kwargs: Additional body parameters

        :return: Data extracted from the document.

        """

        endpoint_name = "/documents-set/"

        categories = categories or []

        request_arguments = {

            "categories": categories,

            "file_url": file_url,

            "file_urls": file_urls,

            "max_pages_to_process": max_pages_to_process,

        }

        request_arguments.update(kwargs)

        return self.client._request("POST", endpoint_name, request_arguments)

update_document

def update_document(
    self,
    document_id: int,
    **kwargs
) -> Dict

Update data for a previously processed document, including almost any field like vendor, date, notes and etc.

https://docs.veryfi.com/api/receipts-invoices/update-a-document/

veryfi_client.update_document(id, date="2021-01-01", notes="look what I did")

Parameters:

Name	Type	Description	Default
document_id	None	ID of the document you'd like to update	None
kwargs	None	fields to update	None

Returns:

Type	Description
None	A document json with updated fields, if fields are writable. Otherwise a document with unchanged fields.

View Source

    def update_document(self, document_id: int, **kwargs) -> Dict:

        """

        Update data for a previously processed document, including almost any field like `vendor`, `date`, `notes` and etc.

        https://docs.veryfi.com/api/receipts-invoices/update-a-document/

        ```veryfi_client.update_document(id, date="2021-01-01", notes="look what I did")```

        :param document_id: ID of the document you'd like to update

        :param kwargs: fields to update

        :return: A document json with updated fields, if fields are writable. Otherwise a document with unchanged fields.

        """

        return self.client._request("PUT", f"/documents/{document_id}/", kwargs)

update_line_item

def update_line_item(
    self,
    document_id: int,
    line_item_id: int,
    payload: Dict
) -> Dict

Update an existing line item on an existing document.

https://docs.veryfi.com/api/receipts-invoices/update-a-line-item/

Parameters:

Name	Type	Description	Default
document_id	None	ID of the document you'd like to update	None
line_item_id	None	ID of the line item you'd like to update	None
payload	None	line item object to update	None

Returns:

Type	Description
None	Line item data with updated fields, if fields are writable. Otherwise line item data with unchanged fields.

View Source

    def update_line_item(self, document_id: int, line_item_id: int, payload: Dict) -> Dict:

        """

        Update an existing line item on an existing document.

        https://docs.veryfi.com/api/receipts-invoices/update-a-line-item/

        :param document_id: ID of the document you'd like to update

        :param line_item_id: ID of the line item you'd like to update

        :param payload: line item object to update

        :return: Line item data with updated fields, if fields are writable. Otherwise line item data with unchanged fields.

        """

        return self.client._request(

            "PUT", f"/documents/{document_id}/line-items/{line_item_id}", payload

        )