Send a Reranking Request

Use the /v1/rerank endpoint to submit a query and a list of documents. The service returns the documents sorted by relevance.

curl --location 'https://localhost:9091/v1/rerank' \
  --header 'Content-Type: application/json' \
  --header "Authorization: Bearer $API_KEY" \
  --cacert "$SECRETS_DIR/cert.pem" \
  --data '{
    "model": "mxbai-rerank-base-v2",
    "query": "What is the capital of France?",
    "documents": [
      "The capital of Brazil is Brasilia.",
      "The capital of France is Paris.",
      "Horses and cows are both animals."
    ]
  }'

The request body includes the following parameters:

• model: The name of the reranking model to use.
• query: The query text used to rank the documents.
• documents: An array of document strings to rank against the query.

The response includes the ranked results. Each result includes the original document index, the document text, and a relevance score. For example:

{
  "id": "rerank-b389becfb1070107",
  "model": "mxbai-rerank-base-v2",
  "usage": {
    "prompt_tokens": 56,
    "total_tokens": 56
  },
  "results": [
    {
      "index": 1,
      "document": {
        "text": "The capital of France is Paris.",
        "multi_modal": null
      },
      "relevance_score": 0.9985467791557312
    },
    {
      "index": 0,
      "document": {
        "text": "The capital of Brazil is Brasilia.",
        "multi_modal": null
      },
      "relevance_score": 0.0005859603406861424
    },
    {
      "index": 2,
      "document": {
        "text": "Horses and cows are both animals.",
        "multi_modal": null
      },
      "relevance_score": 3.7307050661183894e-05
    }
  ]
}

The highest-scoring results is the document that the model determined to be most relevant to the query.