ExtractorCreateRequest

Properties

Name

Type

Description

Notes

name

str

Human-readable name

description

str

What this extractor does

llm

str

Identifier or version of the language model the extractor uses

var_schema

str

JSONSchema that the extractor outputs, serialized as a string. Must be empty or a JSON object; a string, array or other non-object value is rejected with 400. When schema is not empty, the output is always returned as a JSON object. When schema is empty the extractor is unconstrained and its results are returned as free-form text rather than an object.

prompt

str

Custom prompt text for the extractor. If empty, default prompt will be used. If combined with schema, prompt can customize the output, but cannot change its format as it will always be JSON object.

[optional]

pre_prompt_summary

str

(Optional) Pre-prompt summary text for the extractor

[optional]

keep_intermediate_results

bool

(Optional) Flag indicating whether to keep intermediate results during extraction

[optional]

system_prompt

str

(Optional) System prompt text for the extractor

[optional]

max_num_chunks

int

(Optional) Maximum number of chunks to process

[optional]

vision

str

(Optional) Vision mode setting

[optional]

vision_llm

str

(Optional) Vision LLM model identifier

[optional]

image_batch_image_prompt

str

(Optional) Image batch processing prompt

[optional]

image_batch_final_prompt

str

(Optional) Final prompt for image batch processing

[optional]

guardrails_settings

GuardrailsSettings

[optional]

Example

from h2ogpte.rest_async.models.extractor_create_request import ExtractorCreateRequest

# TODO update the JSON string below
json = "{}"
# create an instance of ExtractorCreateRequest from a JSON string
extractor_create_request_instance = ExtractorCreateRequest.from_json(json)
# print the JSON string representation of the object
print(ExtractorCreateRequest.to_json())

# convert the object into a dict
extractor_create_request_dict = extractor_create_request_instance.to_dict()
# create an instance of ExtractorCreateRequest from a dict
extractor_create_request_from_dict = ExtractorCreateRequest.from_dict(extractor_create_request_dict)