Find reranking providers

Hybrid search, lexical search, and reranking are currently in public preview. Development is ongoing, and the features and functionality are subject to change. Astra DB Serverless, and the use of such, is subject to the DataStax Preview Terms.

Get information about reranking providers for the find and rerank command, including supported providers, models, and configuration parameters.

You need an application token with permission to interact with the target database, such as the Database Administrator role.

For more information, see Get endpoint and token.

Result

Python
TypeScript
Java
curl

Returns:

FindRerankingProvidersResult - An object representing the full response from the findRerankingProviders Data API command.

The information in the response is arranged as a hierarchy of nested classes, structured like the Data API JSON response. Refer to the following examples or consult the involved classes in the client reference:

Result

FindRerankingProvidersResult(reranking_providers=nvidia)

You can navigate the response by looping, filtering and inspecting nested objects. The actual response depends on the models available for a given database.

Returns:

Promise<FindRerankingProvidersResult> - An object representing the full response from the findRerankingProviders API command.

The object contains a single key, rerankingProviders, which holds an untyped map with provide names as keys, and objects describing the provider as values.

You can navigate the response by looping, filtering and inspecting nested objects. The actual response depends on the models available for a given database.

Returns:

FindRerankingProvidersResult - An object representing the full response from the findRerankingProviders Data API command.

The object contains a single attribute, rerankingProviders, which holds an untyped map with provider names as keys, and objects describing the provider as values.

You can navigate the response by looping, filtering, and inspecting nested objects. The actual response depends on the models available for a given database.

Returns:

A successful response returns a JSON object describing the reranking providers and settings available for the specified database.

Result

This example response is formatted and edited for clarity.

{
  "status": {
    "rerankingProviders": {
      "nvidia": {
        "isDefault": true,
        "displayName": "Nvidia",
        "supportedAuthentication": {
          "NONE": {
            "enabled": true,
            "tokens": []
          }
        },
        "models": [
          {
            "name": "nvidia/llama-3.2-nv-rerankqa-1b-v2",
            "isDefault": true,
            "url": "https://...",
            "properties": null
          }
        ]
      }
    }
  }
}

Parameters

Python
TypeScript
Java
curl

reranking_providers = db_admin.find_reranking_providers()

Parameters:

Name Type Summary

Name	Type	Summary
`filter_model_status`	`ModelStatus` or an equivalent string	Filters the available models by status. Default: `ModelStatus.SUPPORTED`
`database_admin_timeout_ms`	`int`	A timeout, in milliseconds, for the underlying HTTP request. If not provided, the Database Admin setting is used. This parameter is aliased as `request_timeout_ms` and `timeout_ms` for convenience.

filter_model_status

ModelStatus or an equivalent string

Filters the available models by status.

Default: ModelStatus.SUPPORTED

database_admin_timeout_ms

int

A timeout, in milliseconds, for the underlying HTTP request. If not provided, the Database Admin setting is used. This parameter is aliased as request_timeout_ms and timeout_ms for convenience.

const rerankingProviders = await dbAdmin.findRerankingProviders();

Parameters:

Name Type Summary

Name	Type	Summary
`options`	`FindRerankingProvidersOptions`	Optional. The options for this operation. See Properties of `options` for more details.

options

FindRerankingProvidersOptions

Optional. The options for this operation. See Properties of options for more details.

Properties of `options`
Name	Type	Summary
`filterModelStatus`	ModelLifecycleStatus \| ""	Filters the available models by status. Default: `SUPPORTED`
`timeout`	`number` \| `TimeoutDescriptor`	Optional. The client-side timeout for this operation.

FindRerankingProvidersResult findRerankingProviders();

Parameters:

Name Type Summary

Name	Type	Summary
`options`	`FindRerankingProvidersOptions`	Options for this command, including a filter for the available models by status. By default, the command returns only the supported models.

options

FindRerankingProvidersOptions

Options for this command, including a filter for the available models by status. By default, the command returns only the supported models.

Use the findRerankingProviders Data API command to get information about reranking providers for find and rerank command. Don’t include a keyspace in the request URL.

The application token must have sufficient permissions to perform the requested operations, such as the Database Administrator role.

Parameters:

Name Type Summary

Name	Type	Summary
`options.filterModelStatus`	`string`	Optional. Filters the available models by status. Can be one of: `"SUPPORTED"`, `"DEPRECATED"`, `"END_OF_LIFE"`, `""` (no filter). Default: `"SUPPORTED"`

options.filterModelStatus

string

Optional. Filters the available models by status. Can be one of: "SUPPORTED", "DEPRECATED", "END_OF_LIFE", "" (no filter).

Default: "SUPPORTED"

Examples

The following examples demonstrate how to find reranking providers.

Python
TypeScript
Java
curl

find_r_p_result = db_admin.find_reranking_providers()
find_r_p_result
#  FindRerankingProvidersResult(reranking_providers=nvidia)

find_r_p_result.reranking_providers.keys()
#  dict_keys(['nvidia'])

find_r_p_result.reranking_providers['nvidia']
#  RerankingProvider(
#    <Default> display_name='Nvidia',
#    models=[
#      RerankingProviderModel(
#        <Default> name='nvidia/llama-3.2-nv-rerankqa-1b-v2'
#      )
#    ]
#  )

find_r_p_result.reranking_providers['nvidia'].display_name
#  'Nvidia'

find_r_p_result.reranking_providers['nvidia'].is_default
#  True

find_r_p_result.reranking_providers['nvidia'].parameters
#  []

find_r_p_result.reranking_providers['nvidia'].supported_authentication
#  {'NONE': RerankingProviderAuthentication(enabled=True, tokens=)}

my_model = find_r_p_result.reranking_providers['nvidia'].models[0]
my_model
#  RerankingProviderModel(
#    <Default> name='nvidia/llama-3.2-nv-rerankqa-1b-v2'
#  )

my_model.is_default
#  True

my_model.parameters
#  []

import { DataAPIClient } from '@datastax/astra-db-ts'

// Spawn an AstraDbAdmin instance
const admin = new DataAPIClient('TOKEN').admin();
const dbAdmin = admin.dbAdmin('ENDPOINT');

(async function () {
  const { rerankingProviders: info } = await dbAdmin.findRerankingProviders();

  // { nvidia: { ... }, ... }
  console.log(info);

  // ['nvidia', ...]
  console.log(Object.keys(info))

  // { displayName: 'Nvidia', models: [...], ... }
  console.log(info.nvidia);

  // 'Nvidia'
  console.log(info.nvidia.displayName);

  // true
  console.log(info.nvidia.isDefault);

  // []
  console.log(info.nvidia.parameters);

  // { NONE: { enabled: true, ... } }
  console.log(info.nvidia.supportedAuthentication);

  // { name: 'nvidia/llama-3.2-nv-rerankqa-1b-v2', parameters: [] }
  console.log(info.nvidia.models[0]);

  // true
  console.log(info.nvidia.models[0].isDefault);

  // []
  console.log(info.nvidia.models[0].parameters);
})();

import com.datastax.astra.client.DataAPIClient;
import com.datastax.astra.client.admin.DatabaseAdmin;
import com.datastax.astra.client.databases.Database;
import com.datastax.astra.client.databases.commands.results.FindRerankingProvidersResult;

public class FindRerankingProviders {

 public static void main(String[] args) {
   Database db = new DataAPIClient("TOKEN")
     .getDatabase("API_ENDPOINT");

   DatabaseAdmin dbAdmin = db
     .getDatabaseAdmin();

   FindRerankingProvidersResult results = dbAdmin
     .findRerankingProviders();

   results.getRerankingProviders().forEach((name, provider) -> {;
     System.out.println("Provider: " + name);
     System.out.println("Display Name: " + provider.getDisplayName());
     System.out.println("Is Default: " + provider.getIsDefault());
     System.out.println("Parameters: " + provider.getParameters());
     System.out.println("Supported Authentication: " + provider.getSupportedAuthentication());
     System.out.println("Models: " + provider.getModels());
   });
  }
}

curl -sS -L -X POST "API_ENDPOINT/api/json/v1" \
--header "Token: APPLICATION_TOKEN" \
--header "Content-Type: application/json" \
--data '{
  "findRerankingProviders": {
    "options": {
      "filterModelStatus": "SUPPORTED"
    }
  }
}'

You can use | jq to filter the response:

curl -sS -L -X POST "API_ENDPOINT/api/json/v1" \
--header "Token: APPLICATION_TOKEN" \
--header "Content-Type: application/json" \
--data '{
  "findRerankingProviders": {
    "options": {
      "filterModelStatus": "SUPPORTED"
    }
  }
}' | jq .status.rerankingProviders.MODEL_NAME

Client reference

Python
TypeScript
Java
curl

For more information, see the client reference.

Client reference documentation is not applicable for HTTP.

Find reranking providers

Result

Parameters

Examples

Client reference

Was this helpful?

Give Feedback