Extract Key-Value

​

Overview

Using AnyParser, you can extract key-value information from your documents.

​

Setup

Refer to the Quickstart guide to install the AnyParser SDK and get your api key.

First, set up your AnyParser client.

from any_parser import AnyParser

ap = AnyParser(api_key="...")

Next, you’ll need to create your extract_instruction. This is a dictionary of the form {"key": "key description"} where the key is the name of the key to extract and the key description is a description of that key.

extract_instruction = {
                "social_security_number": "the social security number of the employee",
                "ein": "the employer identification number",
            }

Finally, use the extract_key_value method, passing in the following:

• file_path (str): the path to the local file
• extract_instruction (dict): keys to extract and their descriptions

key_value_result, total_time = ap.extract_key_value(file_path="/path/to/your/file", extract_instruction)

This will return two things:

• key_value_result (dict): Dictionary with the keys specified in extract_instruction, and the values extracted from the document
• total_time (str): the time elapsed in seconds

​

Full Code

from any_parser import AnyParser

ap = AnyParser(api_key="...")

local_file_path = "/path/to/your/file"
extract_instruction = {
                "social_security_number": "the social security number of the employee",
                "ein": "the employer identification number",
            }

key_value_result, total_time = ap.extract_key_value(file_path="/path/to/your/file", extract_instruction)

​

Output

A dictionary where the keys are the same as those in the input dictionary, and the values are the corresponding extracted results.

​

Full Notebook Examples

Check out these notebooks for more detailed examples of using both sync and async AnyParser.