nemoguardrails.library.gliner.models

Pydantic models for GLiNER requests and responses.

Module Contents

Name	Description
`EntitySpan`	Represents a detected entity with its position and metadata.
`GLiNERRequest`	Request model for GLiNER entity extraction.
`GLiNERResponse`	Response model for GLiNER entity extraction.

class nemoguardrails.library.gliner.models.EntitySpan()

Bases: BaseModel

Represents a detected entity with its position and metadata.

end_position

int

score

float = Field(description='Confidence score.')

start_position

int

suggested_label

str = Field(description='The entity label/type.')

value

str = Field(description='The detected entity text.')

class nemoguardrails.library.gliner.models.GLiNERRequest()

Bases: BaseModel

Request model for GLiNER entity extraction.

This model defines the parameters for making requests to a GLiNER server. Default values are centralized here to avoid duplication.

chunk_length

int

flat_ner

bool

labels

Optional[List[str]]

overlap

int

text

str

threshold

float

class nemoguardrails.library.gliner.models.GLiNERResponse()

Bases: BaseModel

Response model for GLiNER entity extraction.

entities

List[EntitySpan] = Field(description='List of detected entities.')

tagged_text

str

total_entities

int