LLM API

Rerank caller-supplied document embeddings

Runs a deterministic reranking pass over caller-supplied embedding vectors. This route does not generate embeddings from text; it ranks the provided documents with the selected runtime-backed similarity or distance metric.

post/v1/rerank

Request

  • Base URL: https://api.algenta.ai
  • URL: https://api.algenta.ai/v1/rerank
  • Auth: one of:
    • HTTP bearer
    • API key in header X-API-Key

Request body

modelstring

Reranking model identifier from GET /v1/models.

query_embeddingnumber[] required

Precomputed query embedding vector.

top_ninteger nullable

Optional number of ranked documents to return. Defaults to all documents.

Response

Successful Response

object'list'
modelstring required
similarity_metricstring required
total_documentsinteger required
returned_documentsinteger required

Changes

No recorded changes to this operation across all 1 revision of this API.