Class GeminiSemanticRetrieverConfig

Namespace

Uralstech.UGemini.Models.Generation.QuestionAnswering.SemanticRetriever

Configuration for retrieving grounding content from a Corpus or Document created using the Semantic Retriever API.

public class GeminiSemanticRetrieverConfig

Inheritance

object

GeminiSemanticRetrieverConfig

Extension Methods

GeminiFieldMaskGenerator.GetFieldMask<T>(T)

Fields

MaxChunksCount

Maximum number of relevant Chunks to retrieve.

public int MaxChunksCount

Field Value

int

MetadataFilters

Filters for selecting Documents and/or Chunks from the resource.

public GeminiMetadataFilter[] MetadataFilters

Field Value

GeminiMetadataFilter[]

MinimumRelevanceScore

Minimum relevance score for retrieved relevant Chunks.

public float MinimumRelevanceScore

Field Value

float

Query

Query to use for similarity matching Chunks in the given resource.

public GeminiContent Query

Field Value

GeminiContent

Source

Name of the resource for retrieval, e.g. corpora/123 or corpora/123/documents/abc.

public string Source

Field Value

string