Class GeminiCorpusChunk

Namespace

Uralstech.UGemini.CorporaAPI.Chunks

A Chunk is a subpart of a Document that is treated as an independent unit for the purposes of vector
representation and storage. A Corpus can have a maximum of 1 million Chunks.

public class GeminiCorpusChunk

Inheritance

object

GeminiCorpusChunk

Extension Methods

GeminiFieldMaskGenerator.GetFieldMask(object)

Fields

CreateTime

The timestamp of when the Chunk was created.

public DateTime CreateTime

Field Value

DateTime

CustomMetadata

User provided custom metadata stored as key-value pairs. The maximum number of CustomMetadata per chunk is 20.

public GeminiCorpusCustomMetadata[] CustomMetadata

Field Value

GeminiCorpusCustomMetadata[]

Data

The content for the Chunk, such as text. The maximum number of tokens per chunk is 2043.

public GeminiCorpusChunkData Data

Field Value

GeminiCorpusChunkData

Resource

The Chunk resource ID.

public GeminiCorpusChunkId Resource

Field Value

GeminiCorpusChunkId

Remarks

The ID (name excluding the "corpora//documents//chunks/" prefix) can contain up to 40 characters
that are lowercase alphanumeric or dashes (-). The ID cannot start or end with a dash. If the name
is empty on create, a random 12-character unique ID will be generated. Example:
corpora/{corpus_id}/documents/{document_id}/chunks/123a456b789c

State

Current state of the Chunk.

public GeminiCorpusChunkState State

Field Value

GeminiCorpusChunkState

UpdateTime

The timestamp of when the Chunk was last updated.

public DateTime UpdateTime

Field Value

DateTime