Rerank

bedrockagentruntime_rerank

R Documentation

Reranks the relevance of sources based on queries¶

Description¶

Reranks the relevance of sources based on queries. For more information, see Improve the relevance of query responses with a reranker model.

Usage¶

bedrockagentruntime_rerank(nextToken, queries, rerankingConfiguration,
  sources)

Arguments¶

nextToken: If the total number of results was greater than could fit in a response, a token is returned in the nextToken field. You can enter that token in this field to return the next batch of results.
queries: [required] An array of objects, each of which contains information about a query to submit to the reranker model.
rerankingConfiguration: [required] Contains configurations for reranking.
sources: [required] An array of objects, each of which contains information about the sources to rerank.

Value¶

A list with the following syntax:

list(
  nextToken = "string",
  results = list(
    list(
      document = list(
        jsonDocument = list(),
        textDocument = list(
          text = "string"
        ),
        type = "TEXT"|"JSON"
      ),
      index = 123,
      relevanceScore = 123.0
    )
  )
)

Request syntax¶

svc$rerank(
  nextToken = "string",
  queries = list(
    list(
      textQuery = list(
        text = "string"
      ),
      type = "TEXT"
    )
  ),
  rerankingConfiguration = list(
    bedrockRerankingConfiguration = list(
      modelConfiguration = list(
        additionalModelRequestFields = list(
          list()
        ),
        modelArn = "string"
      ),
      numberOfResults = 123
    ),
    type = "BEDROCK_RERANKING_MODEL"
  ),
  sources = list(
    list(
      inlineDocumentSource = list(
        jsonDocument = list(),
        textDocument = list(
          text = "string"
        ),
        type = "TEXT"|"JSON"
      ),
      type = "INLINE"
    )
  )
)