Source code for langchain_community.tools.edenai.ocr_invoiceparser

from __future__ import annotations

import logging
from typing import Optional

from langchain_core.callbacks import CallbackManagerForToolRun

from langchain_community.tools.edenai.edenai_base_tool import EdenaiTool

logger = logging.getLogger(__name__)


class EdenAiParsingInvoiceTool(EdenaiTool):
    """查询Eden AI发票解析API的工具。

要使用，请设置环境变量``EDENAI_API_KEY``，并使用您的API令牌。您可以在此处找到您的令牌：https://app.edenai.run/admin/account/settings"""

    name = "edenai_invoice_parsing"

    description = (
        "A wrapper around edenai Services invoice parsing. "
        """Useful for when you have to extract information from 
        an image it enables to take invoices 
        in a variety of formats and returns the data in contains
        (items, prices, addresses, vendor name, etc.)
        in a structured format to automate the invoice processing """
        "Input should be the string url of the document to parse."
    )

    language: Optional[str] = None
    """传递给模型的图像的语言。"""

    feature = "ocr"
    subfeature = "invoice_parser"

    def _parse_response(self, response: list) -> str:
        formatted_list: list = []

        if len(response) == 1:
            self._parse_json_multilevel(
                response[0]["extracted_data"][0], formatted_list
            )
        else:
            for entry in response:
                if entry.get("provider") == "eden-ai":
                    self._parse_json_multilevel(
                        entry["extracted_data"][0], formatted_list
                    )

        return "\n".join(formatted_list)

    def _run(
        self,
        query: str,
        run_manager: Optional[CallbackManagerForToolRun] = None,
    ) -> str:
        """使用这个工具。"""
        query_params = {
            "file_url": query,
            "language": self.language,
            "attributes_as_list": False,
        }

        return self._call_eden_ai(query_params)