Find and rerank documents (C#)

Finds documents in a collection and reranks the results using a reranker model. This command supports two retrieval modes:

Hybrid search: Combines results from a vector search and a lexical search before reranking. For more information about hybrid search mechanics and best practices, see Find data with hybrid search.
Vector search with reranking: Reranks results from a vector search alone, without a lexical search.

To find documents using vector search, lexicographical matching, and filters without reranking, see Find documents (C#).

This method requires a collection with the following:

Vector enabled.
Rerank enabled. Alternatively, collections without rerank enabled can use the rerank override option. For an example, see Override the collection’s rerank provider.
Lexical enabled (only required for hybrid search).

For an example of creating a collection with vector, rerank, and lexical enabled, see Create a collection that supports hybrid search.

For hybrid search, documents must have both the $lexical and $vector fields populated. Documents missing either field are excluded from hybrid search. For vector search with reranking, only the $vector field is required.

Ready to write code? See the examples for this method to get started. If you are new to the Data API, check out the quickstart.

Data residency

When Hybrid Search (reranking) is enabled, query data is processed by a self-hosted reranking model hosted in the United States.

This may result in the transfer of content, including personal data, outside the region where your data is stored. Clients with data residency requirements restricting cross-border transfers should not use this feature.

Refer to the Data Processing Addendum (DPA) for additional details on processing locations and subprocessors.

Result

Returns a CollectionFindAndRerankCursor for iterating over the documents returned by the reranker. The object supports fluent chaining of options to modify the FindAndRerank operation.

This object implements IEnumerable and IAsyncEnumerable for iteration. Iterating over the cursor yields RerankedResult objects, which represent the returned documents.

The fields included in the returned documents depend on the subset of fields that were requested in the projection.

Each RerankedResult object also includes a map of the scores from the retrieval process. If scores were not requested, the map is empty.

If requested, the result also includes the sort vector used for the underlying vector search. The sort vector can be read by calling the GetSortVector() method on the returned cursor.

Signature

Use the FindAndRerank method, which belongs to the Collection class.

public CollectionFindAndRerankCursor<T> FindAndRerank(
  CollectionFindAndRerankOptions<T> options = null
);

public CollectionFindAndRerankCursor<T> FindAndRerank(
  CollectionFilter<T> filter,
  CollectionFindAndRerankOptions<T> options = null
);

public CollectionFindAndRerankCursor<T, RerankedResult<TResult>> FindAndRerank<TResult>(
  CollectionFindAndRerankOptions<T> options = null
) where TResult : class;

public CollectionFindAndRerankCursor<T, RerankedResult<TResult>> FindAndRerank<TResult>(
  CollectionFilter<T> filter,
  CollectionFindAndRerankOptions<T> options = null
) where TResult : class;

Parameters

Name Type Summary

Name	Type	Summary
`filter`	`CollectionFilter`	Optional. An object that defines filter criteria using the Data API filter syntax. The method only finds documents that match the filter criteria. Filters can improve performance by reducing the number of documents that the Data API processes. You must use `&` to escape any `.` or `&` in field names in the filter clause. You cannot use `&` to escape any other characters. For more information, see Work with `.` and `&` in field names (C#). For a list of available filter operators and more examples, see Filter operators for collections (C#). Filters can use only indexed fields. If you apply selective indexing when you create a collection, you cannot reference non-indexed fields in a filter. For an example, see Use filters to restrict the search.
`commandOptions`	`CollectionFindAndRerankOptions`	Optional. Options for this operation. For more information and examples for general options such as timeout, see Customize API interaction. For options specific to this method, see Method-specific properties of the `CollectionFindAndRerankOptions` class.

filter

CollectionFilter

Optional. An object that defines filter criteria using the Data API filter syntax. The method only finds documents that match the filter criteria. Filters can improve performance by reducing the number of documents that the Data API processes.

You must use & to escape any . or & in field names in the filter clause. You cannot use & to escape any other characters. For more information, see Work with . and & in field names (C#).

For a list of available filter operators and more examples, see Filter operators for collections (C#).

Filters can use only indexed fields. If you apply selective indexing when you create a collection, you cannot reference non-indexed fields in a filter.

For an example, see Use filters to restrict the search.

commandOptions

CollectionFindAndRerankOptions

Optional. Options for this operation. For more information and examples for general options such as timeout, see Customize API interaction. For options specific to this method, see Method-specific properties of the CollectionFindAndRerankOptions class.

Method-specific properties of the `CollectionFindAndRerankOptions` class
Name	Type	Summary
`Sort`	`FindAndRerankSortBuilder<T>`	Specifies queries for the underlying vector and lexical searches. The sort builder provides three methods to configure hybrid search: `Hybrid(float[] vector, string lexical)` specifies separate queries: `vector`: An array of floats that serves as a search vector for the underlying vector search. `lexical`: A string of space-separated keywords or terms for the underlying lexical search. When using this method, you must also specify the `RerankQuery` and `RerankOn` options. `Hybrid(string vectorize, string lexical)` specifies separate query strings: `vectorize`: A string that the configured embedding provider converts into a search vector for the underlying vector search. `lexical`: A string of space-separated keywords or terms for the underlying lexical search. This method requires vectorize to be enabled on the collection. `Hybrid(string hybrid)` uses a single query string for both vector (via vectorize) and lexical searches. This method requires vectorize to be enabled on the collection. For examples, see Find documents with a hybrid search and Use shorthand to specify a single search string.
`Projection`	`IProjectionBuilder`	Optional. Controls which fields are included or excluded in the returned document. You must use `&` to escape any `.` or `&` in field names in the projection clause. You cannot use `&` to escape any other characters. For more information, see Work with `.` and `&` in field names (C#). For more information, see Projections for collections (C#). Default: The default projection for the collection. All fields prefixed with `$` are excluded by default and will only be returned if you include them in the projection. `_id` is included by default and will always be returned unless you exclude it from the projection. For an example, see Include only specific fields in the response.
`Limit`	`int`	Optional. Limit the total number of documents returned. Once `limit` is reached, or the cursor is exhausted due to lack of matching documents, nothing more is returned. For an example, see Limit the number of documents returned. Default: The limit set by the Data API.
`HybridLimits`	`int`	Optional. The maximum number of documents to retrieve for each of the underlying vector and lexical searches. If you set `HybridLimits`, you can’t set `LexicalLimit` or `VectorLimit`. Default: The value of `Limit`.
`LexicalLimit`	`int`	Optional. The maximum number of documents to retrieve for the underlying lexical search. If you set `LexicalLimit`, you can’t set `HybridLimits` and you must set `VectorLimit`. Default: The value of `Limit`.
`VectorLimit`	`int`	Optional. The maximum number of documents to retrieve for the underlying vector search. If you set `VectorLimit`, you can’t set `HybridLimits` and you must set `LexicalLimit`. Default: The value of `Limit`.
`IncludeScores`	`bool`	Optional. Whether to include the scores from the reranking process in the response. These scores can be inspected in the `Scores` attribute of each `RerankedResult` object yielded by the `CollectionFindAndRerankCursor`. If false, the `Scores` attribute of each `RerankedResult` object is an empty dictionary. For an example, see Include the scores in the response. Default: False
`IncludeSortVector`	`bool`	Optional. Whether to include the sort vector that was used for the underlying vector search in the response. This can be useful if you query through the `$vectorize` field instead of the `$vector` field, since you don’t know the sort vector in advance. The sort vector can be read by calling the `GetSortVector()` method on the returned cursor. For an example, see Include the sort vector in the response. Default: False
`RerankOn`	`string`	Required if you use `vector` in `Sort`; otherwise optional. The document field to use for the reranking step. Once the underlying vector and lexical searches complete, the reranker compares the `RerankQuery` text with each document’s `RerankOn` field. The reserved `$vectorize` field is often used for this parameter, but you can specify any field that stores a string. Documents without this field or with a null or non-string value are excluded. Default unless you use `vector` in `Sort`: `"$vectorize"`.
`RerankQuery`	`string`	Required if you use `vector` in `Sort`; otherwise optional. Query text for the reranker step. Once the underlying vector and lexical searches complete, the reranker compares the `RerankQuery` text with each document’s `RerankOn` field. For an example, see Use a different query in the reranking step. Default unless you use `vector` in `Sort`: the query used for the underlying vector search, which is specified by the `Sort` parameter.
`Service`	`RerankServiceOptions`	Optional. Overrides the reranking service configured for the collection, even if the collection does not have a reranking service configured. Only the NVIDIA llama-3.2-nv-rerankqa-1b-v2 reranking model reranker model is supported. For an example, see Override the collection’s rerank provider.

Examples

The following examples demonstrate how to find documents with hybrid search.

Find documents with a hybrid search

With $vectorize

Use the Sort parameter to specify the queries for the underlying vector search and lexical search.

The lexical query is a string of space-separated keywords or terms.

The vectorize query is a string that the configured embedding provider will convert into a search vector. Alternatively, you can use a vector query, as the "Without $vectorize" example demonstrates.

using System.Text.Json;
using DataStax.AstraDB.DataApi;
using DataStax.AstraDB.DataApi.Collections;
using DataStax.AstraDB.DataApi.Core;
using DataStax.AstraDB.DataApi.Core.Query;

namespace Examples;

public class Program
{
  static async Task Main()
  {
    // Get an existing collection
    var client = new DataAPIClient();
    var database = client.GetDatabase(
      "API_ENDPOINT",
      "APPLICATION_TOKEN"
    );
    var collection = database.GetCollection("COLLECTION_NAME");

    // Find documents
    var result = collection.FindAndRerank(
      new CollectionFindAndRerankOptions<Document>
      {
        Sort = Builders<Document>.CollectionFindAndRerankSort.Hybrid(
          "A tree in the woods",
          "house hill grassy"
        ),
      }
    );

    await foreach (var document in result)
    {
      Console.WriteLine(JsonSerializer.Serialize(document.Document));
    }
  }
}

Without $vectorize

Use the Sort parameter to specify the queries for the underlying vector search and lexical search.

The lexical query is a string of space-separated keywords or terms.

The vector query is an array of floats.

You must also specify the RerankQuery and RerankOn options.

using System.Text.Json;
using DataStax.AstraDB.DataApi;
using DataStax.AstraDB.DataApi.Collections;
using DataStax.AstraDB.DataApi.Core;
using DataStax.AstraDB.DataApi.Core.Query;

namespace Examples;

public class Program
{
  static async Task Main()
  {
    // Get an existing collection
    var client = new DataAPIClient();
    var database = client.GetDatabase(
      "API_ENDPOINT",
      "APPLICATION_TOKEN"
    );
    var collection = database.GetCollection("COLLECTION_NAME");

    // Find documents
    var result = collection.FindAndRerank(
      new CollectionFindAndRerankOptions<Document>
      {
        Sort = Builders<Document>.CollectionFindAndRerankSort.Hybrid(
          new float[] { 0.08f, -0.62f, 0.39f },
          "house hill grassy"
        ),
        RerankQuery = "A tree in the woods",
        RerankOn = "$lexical",
      }
    );

    await foreach (var document in result)
    {
      Console.WriteLine(JsonSerializer.Serialize(document.Document));
    }
  }
}

Find documents with vector search and reranking

With $vectorize

Use the Sort parameter to specify the query for the underlying vector search.

using System.Text.Json;
using DataStax.AstraDB.DataApi;
using DataStax.AstraDB.DataApi.Collections;
using DataStax.AstraDB.DataApi.Core;
using DataStax.AstraDB.DataApi.Core.Query;

namespace Examples;

public class Program
{
  static async Task Main()
  {
    // Get an existing collection
    var client = new DataAPIClient();
    var database = client.GetDatabase(
      "API_ENDPOINT",
      "APPLICATION_TOKEN"
    );
    var collection = database.GetCollection("COLLECTION_NAME");

    // Find documents
    var result = collection.FindAndRerank(
      new CollectionFindAndRerankOptions<Document>
      {
        Sort = Builders<Document>.CollectionFindAndRerankSort.Hybrid(
          "A tree in the woods",
          null
        ),
      }
    );

    await foreach (var document in result)
    {
      Console.WriteLine(JsonSerializer.Serialize(document.Document));
    }
  }
}

Without $vectorize

Use the Sort parameter to specify the query for the underlying vector search.

The vector query is an array of floats.

You must also specify the RerankQuery and RerankOn options.

using System.Text.Json;
using DataStax.AstraDB.DataApi;
using DataStax.AstraDB.DataApi.Collections;
using DataStax.AstraDB.DataApi.Core;
using DataStax.AstraDB.DataApi.Core.Query;

namespace Examples;

public class Program
{
  static async Task Main()
  {
    // Get an existing collection
    var client = new DataAPIClient();
    var database = client.GetDatabase(
      "API_ENDPOINT",
      "APPLICATION_TOKEN"
    );
    var collection = database.GetCollection("COLLECTION_NAME");

    // Find documents
    var result = collection.FindAndRerank(
      new CollectionFindAndRerankOptions<Document>
      {
        Sort = Builders<Document>.CollectionFindAndRerankSort.Hybrid(
          new float[] { 0.08f, -0.62f, 0.39f },
          null
        ),
        RerankQuery = "A tree in the woods",
        RerankOn = "example_field",
      }
    );

    await foreach (var document in result)
    {
      Console.WriteLine(JsonSerializer.Serialize(document.Document));
    }
  }
}

Use shorthand to specify a single search string

If your collection has vectorize enabled, you can use shorthand to specify the same string for both the $vectorize and $lexical queries.

using System.Text.Json;
using DataStax.AstraDB.DataApi;
using DataStax.AstraDB.DataApi.Collections;
using DataStax.AstraDB.DataApi.Core;
using DataStax.AstraDB.DataApi.Core.Query;

namespace Examples;

public class Program
{
  static async Task Main()
  {
    // Get an existing collection
    var client = new DataAPIClient();
    var database = client.GetDatabase(
      "API_ENDPOINT",
      "APPLICATION_TOKEN"
    );
    var collection = database.GetCollection("COLLECTION_NAME");

    // Find documents
    var result = collection.FindAndRerank(
      new CollectionFindAndRerankOptions<Document>
      {
        Sort = Builders<Document>.CollectionFindAndRerankSort.Hybrid(
          "A tree in the woods"
        ),
      }
    );

    await foreach (var document in result)
    {
      Console.WriteLine(JsonSerializer.Serialize(document.Document));
    }
  }
}

Use a different query in the reranking step

The results of the underlying vector search and lexical search are run through a reranker model. The reranker uses a search string to rerank the documents that were returned by the underlying searches.

If you query through the $vector field, you must specify the search string for the reranker to use and the field to rerank the documents on.

If you query through the $vectorize field, the reranker will use the string that was used to perform the underlying vector search unless you specify a different string. It will also rerank documents on their $vectorize field, unless you specify a different field.

Use filters to restrict the search

You can use a filter to find documents that match specific criteria. For example, you can find documents with an is_checked_out value of false and a number_of_pages value less than 300.

Only documents that match the filter will be included in the hybrid search.

For a list of available filter operators and more examples, see Filter operators for collections (C#).

Filters can use only indexed fields. If you apply selective indexing when you create a collection, you cannot reference non-indexed fields in a filter.

With $vectorize

using System.Text.Json;
using DataStax.AstraDB.DataApi;
using DataStax.AstraDB.DataApi.Collections;
using DataStax.AstraDB.DataApi.Core;
using DataStax.AstraDB.DataApi.Core.Query;

namespace Examples;

public class Program
{
  static async Task Main()
  {
    // Get an existing collection
    var client = new DataAPIClient();
    var database = client.GetDatabase(
      "API_ENDPOINT",
      "APPLICATION_TOKEN"
    );
    var collection = database.GetCollection("COLLECTION_NAME");

    // Find documents
    var filterBuilder = Builders<Document>.CollectionFilter;
    var filter = filterBuilder.And(
      filterBuilder.Eq("is_checked_out", false),
      filterBuilder.Lt("number_of_pages", 300)
    );
    var result = collection.FindAndRerank(
      filter,
      new CollectionFindAndRerankOptions<Document>
      {
        Sort = Builders<Document>.CollectionFindAndRerankSort.Hybrid(
          "A tree in the woods"
        ),
      }
    );

    await foreach (var document in result)
    {
      Console.WriteLine(JsonSerializer.Serialize(document.Document));
    }
  }
}

Without $vectorize

using System.Text.Json;
using DataStax.AstraDB.DataApi;
using DataStax.AstraDB.DataApi.Collections;
using DataStax.AstraDB.DataApi.Core;
using DataStax.AstraDB.DataApi.Core.Query;

namespace Examples;

public class Program
{
  static async Task Main()
  {
    // Get an existing collection
    var client = new DataAPIClient();
    var database = client.GetDatabase(
      "API_ENDPOINT",
      "APPLICATION_TOKEN"
    );
    var collection = database.GetCollection("COLLECTION_NAME");

    // Find documents
    var filterBuilder = Builders<Document>.CollectionFilter;
    var filter = filterBuilder.And(
      filterBuilder.Eq("is_checked_out", false),
      filterBuilder.Lt("number_of_pages", 300)
    );
    var result = collection.FindAndRerank(
      filter,
      new CollectionFindAndRerankOptions<Document>
      {
        Sort = Builders<Document>.CollectionFindAndRerankSort.Hybrid(
          new float[] { 0.08f, -0.62f, 0.39f },
          "house hill grassy"
        ),
        RerankQuery = "A tree in the woods",
        RerankOn = "$lexical",
      }
    );

    await foreach (var document in result)
    {
      Console.WriteLine(JsonSerializer.Serialize(document.Document));
    }
  }
}

Limit the number of documents returned

Specify a limit to only fetch up to a certain number of documents.

With $vectorize

using System.Text.Json;
using DataStax.AstraDB.DataApi;
using DataStax.AstraDB.DataApi.Collections;
using DataStax.AstraDB.DataApi.Core;
using DataStax.AstraDB.DataApi.Core.Query;

namespace Examples;

public class Program
{
  static async Task Main()
  {
    // Get an existing collection
    var client = new DataAPIClient();
    var database = client.GetDatabase(
      "API_ENDPOINT",
      "APPLICATION_TOKEN"
    );
    var collection = database.GetCollection("COLLECTION_NAME");

    // Find documents
    var result = collection.FindAndRerank(
      new CollectionFindAndRerankOptions<Document>
      {
        Sort = Builders<Document>.CollectionFindAndRerankSort.Hybrid(
          "A tree in the woods"
        ),
        Limit = 2,
      }
    );

    await foreach (var document in result)
    {
      Console.WriteLine(JsonSerializer.Serialize(document.Document));
    }
  }
}

Without $vectorize

using System.Text.Json;
using DataStax.AstraDB.DataApi;
using DataStax.AstraDB.DataApi.Collections;
using DataStax.AstraDB.DataApi.Core;
using DataStax.AstraDB.DataApi.Core.Query;

namespace Examples;

public class Program
{
  static async Task Main()
  {
    // Get an existing collection
    var client = new DataAPIClient();
    var database = client.GetDatabase(
      "API_ENDPOINT",
      "APPLICATION_TOKEN"
    );
    var collection = database.GetCollection("COLLECTION_NAME");

    // Find documents
    var result = collection.FindAndRerank(
      new CollectionFindAndRerankOptions<Document>
      {
        Sort = Builders<Document>.CollectionFindAndRerankSort.Hybrid(
          new float[] { 0.08f, -0.62f, 0.39f },
          "house hill grassy"
        ),
        RerankQuery = "A tree in the woods",
        RerankOn = "$lexical",
        Limit = 2,
      }
    );

    await foreach (var document in result)
    {
      Console.WriteLine(JsonSerializer.Serialize(document.Document));
    }
  }
}

Limit the number of documents returned by the underlying searches

You can customize the number of documents returned by the underlying vector and lexical searches.

You can provide a single number, which is then used for both the vector search and the lexical search. Or, you can specify a different limit for each search. Specifying different limits can help boost the importance of one type of search over the other.

By default, each underlying search uses the same limit as the overall method.

With $vectorize

using System.Text.Json;
using DataStax.AstraDB.DataApi;
using DataStax.AstraDB.DataApi.Collections;
using DataStax.AstraDB.DataApi.Core;
using DataStax.AstraDB.DataApi.Core.Query;

namespace Examples;

public class Program
{
  static async Task Main()
  {
    // Get an existing collection
    var client = new DataAPIClient();
    var database = client.GetDatabase(
      "API_ENDPOINT",
      "APPLICATION_TOKEN"
    );
    var collection = database.GetCollection("COLLECTION_NAME");

    // Find documents
    var result = collection.FindAndRerank(
      new CollectionFindAndRerankOptions<Document>
      {
        Sort = Builders<Document>.CollectionFindAndRerankSort.Hybrid(
          "A tree in the woods"
        ),
        VectorLimit = 8,
        LexicalLimit = 20,
      }
    );

    await foreach (var document in result)
    {
      Console.WriteLine(JsonSerializer.Serialize(document.Document));
    }
  }
}

Without $vectorize

using System.Text.Json;
using DataStax.AstraDB.DataApi;
using DataStax.AstraDB.DataApi.Collections;
using DataStax.AstraDB.DataApi.Core;
using DataStax.AstraDB.DataApi.Core.Query;

namespace Examples;

public class Program
{
  static async Task Main()
  {
    // Get an existing collection
    var client = new DataAPIClient();
    var database = client.GetDatabase(
      "API_ENDPOINT",
      "APPLICATION_TOKEN"
    );
    var collection = database.GetCollection("COLLECTION_NAME");

    // Find documents
    var result = collection.FindAndRerank(
      new CollectionFindAndRerankOptions<Document>
      {
        Sort = Builders<Document>.CollectionFindAndRerankSort.Hybrid(
          new float[] { 0.08f, -0.62f, 0.39f },
          "house hill grassy"
        ),
        VectorLimit = 8,
        LexicalLimit = 20,
        RerankQuery = "A tree in the woods",
        RerankOn = "$lexical",
      }
    );

    await foreach (var document in result)
    {
      Console.WriteLine(JsonSerializer.Serialize(document.Document));
    }
  }
}

Include the scores in the response

You can request the scores to be returned alongside the documents.

The reranking retrieval process assigns scores to each document, such as vector similarity and reranker scores, and then compares those scores across all retrieved documents to determine the best overall results.

For general information, see Find data with vector search and Find data with hybrid search.

Include the sort vector in the response

You can include the sort vector in the result. This can be useful if you use $vectorize and a search string in the sort parameter, since you don’t know the sort vector in advance.

Include only specific fields in the response

To specify which fields to include or exclude in the returned documents, use a projection.

All fields prefixed with $ are excluded by default and will only be returned if you include them in the projection. _id is included by default and will always be returned unless you exclude it from the projection.

With $vectorize

using System.Text.Json;
using DataStax.AstraDB.DataApi;
using DataStax.AstraDB.DataApi.Collections;
using DataStax.AstraDB.DataApi.Core;
using DataStax.AstraDB.DataApi.Core.Query;

namespace Examples;

public class Program
{
  static async Task Main()
  {
    // Get an existing collection
    var client = new DataAPIClient();
    var database = client.GetDatabase(
      "API_ENDPOINT",
      "APPLICATION_TOKEN"
    );
    var collection = database.GetCollection("COLLECTION_NAME");

    // Find documents
    var result = collection.FindAndRerank(
      new CollectionFindAndRerankOptions<Document>
      {
        Sort = Builders<Document>.CollectionFindAndRerankSort.Hybrid(
          "A tree in the woods"
        ),
        Projection = Builders<Document>
          .Projection.Include("is_checked_out")
          .Include("title"),
      }
    );

    await foreach (var document in result)
    {
      Console.WriteLine(JsonSerializer.Serialize(document.Document));
    }
  }
}

Without $vectorize

using System.Text.Json;
using DataStax.AstraDB.DataApi;
using DataStax.AstraDB.DataApi.Collections;
using DataStax.AstraDB.DataApi.Core;
using DataStax.AstraDB.DataApi.Core.Query;

namespace Examples;

public class Program
{
  static async Task Main()
  {
    // Get an existing collection
    var client = new DataAPIClient();
    var database = client.GetDatabase(
      "API_ENDPOINT",
      "APPLICATION_TOKEN"
    );
    var collection = database.GetCollection("COLLECTION_NAME");

    // Find documents
    var result = collection.FindAndRerank(
      new CollectionFindAndRerankOptions<Document>
      {
        Sort = Builders<Document>.CollectionFindAndRerankSort.Hybrid(
          new float[] { 0.08f, -0.62f, 0.39f },
          "house hill grassy"
        ),
        Projection = Builders<Document>
          .Projection.Include("is_checked_out")
          .Include("title"),
        RerankQuery = "A tree in the woods",
        RerankOn = "$lexical",
      }
    );

    await foreach (var document in result)
    {
      Console.WriteLine(JsonSerializer.Serialize(document.Document));
    }
  }
}

Override the collection’s rerank provider

You can override the reranking service configured for the collection, even if the collection does not have a reranking service configured.

Only the NVIDIA llama-3.2-nv-rerankqa-1b-v2 reranking model reranker model is supported.

using System.Text.Json;
using DataStax.AstraDB.DataApi;
using DataStax.AstraDB.DataApi.Collections;
using DataStax.AstraDB.DataApi.Core;
using DataStax.AstraDB.DataApi.Core.Query;

namespace Examples;

public class Program
{
  static async Task Main()
  {
    // Get an existing collection
    var client = new DataAPIClient();
    var database = client.GetDatabase(
      "API_ENDPOINT",
      "APPLICATION_TOKEN"
    );
    var collection = database.GetCollection("COLLECTION_NAME");

    // Find documents
    var result = collection.FindAndRerank(
      new CollectionFindAndRerankOptions<Document>
      {
        Sort = Builders<Document>.CollectionFindAndRerankSort.Hybrid(
          "A tree in the woods"
        ),
        RerankQuery = "A house on a hill",
        Service = new()
        {
          ModelName = "nvidia/llama-3.2-nv-rerankqa-1b-v2",
          Provider = "nvidia",
        },
      }
    );

    await foreach (var document in result)
    {
      Console.WriteLine(JsonSerializer.Serialize(document.Document));
    }
  }
}

Client reference

For more information, see the client reference.

Find and rerank documents (C#)

Data residency

Result

Signature

Parameters

Examples

Find documents with a hybrid search

Find documents with vector search and reranking

Use shorthand to specify a single search string

Use a different query in the reranking step

Use filters to restrict the search

Limit the number of documents returned

Limit the number of documents returned by the underlying searches

Include the scores in the response

Include the sort vector in the response

Include only specific fields in the response

Override the collection’s rerank provider

Client reference

Was this helpful?

Give Feedback