[SSL: CERTIFICATE_VERIFY_FAILED]

[d-evm]

I am trying to run the following program which uses unstructured to extract text from a pdf.

def extract_text_to_json(self):
        dotenv.load_dotenv() 

        api_key = os.getenv("UNSTRUCTURED_API_KEY")
        api_url = os.getenv("UNSTRUCTURED_API_URL")

        if not api_key or not api_url:
            self.logging.error("API key or URL is missing.")
            return

        client = unstructured_client.UnstructuredClient(
            api_key_auth=api_key,
            server_url=api_url,
        )

        print("the api key and url are : ", api_key, api_url)
        if not os.path.exists(self.pdf_file_location):
            print(f"PDF file does not exist at location: {self.pdf_file_location}")
            return

        print(f"PDF file exists at location: {self.pdf_file_location}")
        print(f"PDF file size: {os.path.getsize(self.pdf_file_location)} bytes")

        req = {
            "partition_parameters": {
                "files": {
                    "content": open(self.pdf_file_location, "rb"),
                    "file_name": self.pdf_file_location,
                },
                "strategy": shared.Strategy.HI_RES,
                "languages": ['eng'],
                "split_pdf_page": True,            # If True, splits the PDF file into smaller chunks of pages.
                "split_pdf_allow_failed": True,    # If True, the partitioning continues even if some pages fail.
                "split_pdf_concurrency_level": 15  # Set the number of concurrent request to the maximum value: 15.
            }
        }

        try:
            print("debug: inside try")
            res = client.general.partition(request=req)
            print("debug: ~~~~~~~~~~~~~~~~~~~~~~~~~~~`below element_dicts")
            element_dicts = [element for element in res.elements]

            # Print the processed data's first element only.
            if element_dicts:
                print(element_dicts[0])
            else:
                self.logging.error("No elements found in the response.")

            # Write the processed data to a local file.
            json_elements = json.dumps(element_dicts, indent=2)

            # Ensure the directory exists before writing the file
            output_dir = os.path.dirname(self.json_file_location)
            if not os.path.exists(output_dir):
                os.makedirs(output_dir)

            with open(self.json_file_location, "w") as file:
                file.write(json_elements)

            self.logging.info(f"Extracted text saved to: {self.json_file_location}")
            self.logging.info(f"Extracted text content: {json_elements}")
        except Exception as e:
            self.logging.error(f"Error extracting text to JSON: {e}")

On calling the above method, I keep getting the following error message:

PDF file exists at location: tmp\working-pdf.pdf
PDF file size: 1515917 bytes
debug: inside try
INFO: Failed to process a request due to connection error - [SSL: CERTIFICATE_VERIFY_FAILED]
certificate verify failed: unable to get local issuer certificate (_ssl.c:1000). Attempting r
etry number 1 after sleep.
ERROR: Failed to partition the document.
ERROR: Following error occurred - [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed:
 unable to get local issuer certificate (_ssl.c:1000)
INFO: Failed to process a request due to connection error - [SSL: CERTIFICATE_VERIFY_FAILED]
certificate verify failed: unable to get local issuer certificate (_ssl.c:1000). Attempting r
etry number 2 after sleep.
ERROR: Failed to partition the document.
ERROR: Following error occurred - [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed:
 unable to get local issuer certificate (_ssl.c:1000)

According to the official documentation, you can disable certificate verification for testing purposes, but that too didn't work for me.

However when I am running the program individually (not as a function) in a different py file, it works perfect. I checked the api key and URL, but am not able to figure out whether this is some environment specific problem.

[d-evm]

The program was running in a virtual env but not in global env. Hence I updated the dependency 'unstructured-client' and it worked!