model

Documentation

Index

• type Document
• type ExtractEntity
• type ExtractedEntities
• type Identified
• type TextUnit
  • func FromFile(file string) (*TextUnit, error)

Types

type Document

type Document struct {
	Identified
	Text string `json:"text"`

	// TextUnits is a list of TextUnit IDs that are part of this document.
	TextUnits []*TextUnit `json:"text_units,omitempty"`

	// ExtractedEntities is a list of entities that were extracted from the document.
	ExtractedEntities ExtractedEntities `json:"extracted_entities,omitempty"`
}

type ExtractEntity

type ExtractEntity string

type ExtractedEntities

type ExtractedEntities []ExtractEntity

type Identified

type Identified struct {
	ID      string `json:"id"`
	ShortID string `json:"short_id,omitempty"`
}

Identified represents a base struct with identification fields.

type TextUnit

type TextUnit struct {
	Identified
	Text            string              `json:"text"`
	TextEmbedding   []float64           `json:"text_embedding,omitempty"`
	EntityIDs       []string            `json:"entity_ids,omitempty"`
	RelationshipIDs []string            `json:"relationship_ids,omitempty"`
	CovariateIDs    map[string][]string `json:"covariate_ids,omitempty"`
	NTokens         int                 `json:"n_tokens,omitempty"`
	DocumentIDs     []string            `json:"document_ids,omitempty"`
	Attributes      map[string]any      `json:"attributes,omitempty"`
}

TextUnit represents a protocol for a TextUnit item in a Document database.

func FromFile

func FromFile(file string) (*TextUnit, error)