> ## Documentation Index
> Fetch the complete documentation index at: https://docs.trieve.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Get Ranks

> Runs Reranker. Returns a 424 status code if the model is not a Reranker model.

<RequestExample>
  ```json Raw Json theme={null}
  {
    "query": "What are some good electric cars",
    "texts": [
        "Here’s the information about the Mercedes CLR GTR: The Mercedes CLR GTR is a remarkable racing car ...",
        "The Tesla Cybertruck is an all-electric, battery-powered light-duty truck unveiled by Tesla, Inc. ..."
    ],
    "raw_scores": false,
    "return_text": false,
    "truncate": false,
    "truncation_direction": "right"
  }
  ```

  ```sh curl theme={null}
  curl -X POST \
       -H "Content-Type: application/json" \
       -d '{
        "query": "What are some good electric cars",
        "texts": [
            "Here’s the information about the Mercedes CLR GTR: The Mercedes CLR GTR is a remarkable racing car ...",
            "The Tesla Cybertruck is an all-electric, battery-powered light-duty truck unveiled by Tesla, Inc. ..."
        ],
        "raw_scores": false,
        "return_text": false,
        "truncate": false,
        "truncation_direction": "right"
      }' \
       --url http://$ENDPOINT/rerank
  ```

  ```py python theme={null}
  import requests

  endpoint = "<your-custom-endpoint>"

  requests.post(f"{endpoint}/rerank", json={
      "query": "What are some good electric cars",
      "texts": [
        "Here’s the information about the Mercedes CLR GTR: The Mercedes CLR GTR is a remarkable racing car ...",
        "The Tesla Cybertruck is an all-electric, battery-powered light-duty truck unveiled by Tesla, Inc. ..."
      ],
      "raw_scores": False,
      "return_text": False,
      "truncate": False,
      "truncation_direction": "right"
  });

  ## or 

  requests.post(f"{endpoint}/rerank", json={
      "inputs": "test single input"
  });


  ```
</RequestExample>

<ResponseExample>
  ```json 200 Ranks theme={null}
  [
      {
          "index":1,
          "score":0.15253653,
          // if return_text = true
          "text": "The Tesla Cybertruck is an all-electric, battery-powered light-duty truck unveiled by Tesla, Inc. ..."
      },
      {
          "index":0,
          "score":0.00498227
          // if return_text = true
          "text": "Here’s the information about the Mercedes CLR GTR: The Mercedes CLR GTR is a remarkable racing car ..."
      }
  ]
  ```

  ```json 413 theme={null}
  {
      "error": "Batch size error",
      "error_type": "validation"
  }
  ```

  ```json 422 theme={null}
  {
      "error": "Tokenization error",
      "error_type": "validation"
  }
  ```

  ```json 424 theme={null}
  {
      "error": "Inference failed",
      "error_type": "backend"
  }
  ```

  ```json 429 theme={null}
  {
      "error": "Model is overloaded",
      "error_type": "overloaded"
  }
  ```
</ResponseExample>

<ParamField path="query" type="string" required>
  Inputs that need to be embedded
</ParamField>

<ParamField path="texts" type="string[]" required>
  Inputs that need to be embedded
</ParamField>

<ParamField path="raw_scores" type="boolean" default="false">
  Output the raw reranker score or the normalized score between 0-1.
  When `false`, score is between 0 and 1, otherwise range is indeterminate
</ParamField>

<ParamField path="return_text" type="boolean" default="false">
  Return the text with along with each rank
</ParamField>

<ParamField path="truncate" type="boolean" default="false">
  Automatically truncate inputs that are longer than the maximum supported size
</ParamField>

<ParamField path="truncate_direction" type="&#x22;right&#x22; | &#x22;left&#x22;" default="right" />