📄 Extract In Json Format¶

templates.key_value_extraction.extract_in_json_format

InputOutputTemplate(
    instruction="Extract the key value pairs from the input. Return a valid json object with the following keys: {keys}. Return only the json representation, no additional text or explanations.",
    input_format="{input}",
    output_format="{key_value_pairs_answer}",
    postprocessors=[
        PostProcess(
            operator=JsonStrToDict(),
        ),
    ],
    serializer=MultiTypeSerializer(
        serializers=[
            ImageSerializer(),
            DictAsJsonSerializer(),
            ListSerializer(),
        ],
    ),
)

[source]

from unitxt.processors import PostProcess
from unitxt.serializers import DictAsJsonSerializer, ImageSerializer, ListSerializer, MultiTypeSerializer
from unitxt.struct_data_operators import JsonStrToDict

Explanation about InputOutputTemplate¶

Generate field ‘source’ from fields designated as input, and fields ‘target’ and ‘references’ from fields designated as output, of the processed instance.

Args specify the formatting strings with which to glue together the input and reference fields of the processed instance into one string (‘source’ and ‘target’), and into a list of strings (‘references’).

Explanation about JsonStrToDict¶

Convert a Json string of representing key value as dictionary.

Ensure keys and values are strings, and there are no None values.