Extractor

Properties

Name

Type

Description

Notes

name

str

Human-readable name

description

str

What this extractor does

llm

str

(Optional) Identifier or version of the language model the extractor uses

[optional]

var_schema

str

(Optional) JSONSchema (or other spec) that the extractor outputs

[optional]

prompt

str

(Optional) Prompt text for the extractor

[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]

id

str

Unique identifier of the extractor

is_public

bool

Flag indicating if the extractor is public

created_at

datetime

When the extractor definition was created

Example

from h2ogpte.rest_async.models.extractor import Extractor

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

# convert the object into a dict
extractor_dict = extractor_instance.to_dict()
# create an instance of Extractor from a dict
extractor_from_dict = Extractor.from_dict(extractor_dict)