Migrate to a new embedding model for a table (C#)

Follow this migration guide if you want to switch embedding models for a column in your table.

This migration only works if you stored the original text in another column in your table. If you did not store the original text in your table, then you must modify the migration script below to get the original text from another source.

If your new embedding model supports a larger context window, then you might also want to re-chunk your data.

  1. Add a new vector column with the desired embedding provider integration to your table. For examples, see Add a vector column and configure an embedding provider integration.

  2. Populate the new vector column with the contents of the column that stores the original text.

    The embedding provider integration for your new column will automatically generate vector embeddings based on the text.

    For example:

    using DataStax.AstraDB.DataApi;
    using DataStax.AstraDB.DataApi.Core;
    using DataStax.AstraDB.DataApi.Core.Enumeration;
    using DataStax.AstraDB.DataApi.Core.Query;
    using DataStax.AstraDB.DataApi.Tables;
    
    namespace Examples;
    
    public class Program
    {
      static async Task Main()
      {
        var client = new DataAPIClient();
        var database = client.GetDatabase(
          "API_ENDPOINT",
          "APPLICATION_TOKEN"
        );
    
        var table = database.GetTable("TABLE_NAME");
    
        string? pageState = null;
        int migratedCount = 0;
    
        // Use an empty filter to migrate all rows
        var filterBuilder = Builders<Row>.TableFilter;
        var filter = filterBuilder.Empty();
    
        // You must include ALL primary key columns for your table
        var primaryKeyColumns = new List<string>
        {
          "PRIMARY_KEY_1",
          "PRIMARY_KEY_2",
        };
    
        var originalTextColumn = "NAME_OF_ORIGINAL_TEXT_COLUMN";
        var newVectorColumn = "NAME_OF_NEW_VECTOR_COLUMN";
    
        // The projection should include ALL primary key columns
        // and the column that stores the original text
        var projectionBuilder = Builders<Row>.Projection;
        var projection = projectionBuilder.Include(primaryKeyColumns[0]);
        foreach (var column in primaryKeyColumns.Skip(1))
        {
          projection = projection.Include(column);
        }
        projection = projection.Include(originalTextColumn);
    
        while (true)
        {
          TableFindCursor<Row> cursor;
          if (pageState != null)
          {
            cursor = table.Find(
              filter,
              new TableFindOptions<Row>()
              {
                InitialPageState = pageState,
                Projection = projection,
              }
            );
          }
          else
          {
            cursor = table.Find(
              filter,
              new TableFindOptions<Row>() { Projection = projection }
            );
          }
    
          var page = await cursor.FetchNextPageAsync();
          var rows = page.Results;
          pageState = page.NextPageState;
    
          if (rows.Count == 0)
          {
            Console.WriteLine("No more rows. Migration complete.");
            break;
          }
    
          // Build the updates
          var updatedRows = new List<Row>();
          foreach (var row in rows)
          {
            if (
              row.TryGetValue(originalTextColumn, out var textValue)
              && textValue != null
            )
            {
              var updatedRow = new Row();
    
              // Include the full primary key
              foreach (var column in primaryKeyColumns)
              {
                if (row.TryGetValue(column, out var pkValue))
                {
                  updatedRow[column] = pkValue;
                }
              }
    
              // Set the new vector column to the original text
              updatedRow[newVectorColumn] = textValue;
    
              updatedRows.Add(updatedRow);
            }
          }
    
          // Inserting a row with a primary key that already exists in the table will
          // overwrite the specified column but leave unspecified columns unchanged.
          await table.InsertManyAsync(updatedRows);
          migratedCount += updatedRows.Count;
    
          Console.WriteLine(
            $"Migrated {migratedCount} rows. Page state: {pageState}"
          );
    
          if (pageState == null)
          {
            Console.WriteLine("Reached final page. Migration complete.");
            break;
          }
        }
      }
    }
  3. Optionally, delete the column that stores the old vector embeddings.

Was this helpful?

Give Feedback

How can we improve the documentation?

© Copyright IBM Corporation 2026 | Privacy policy | Terms of use Manage Privacy Choices

Apache, Apache Cassandra, Cassandra, Apache Tomcat, Tomcat, Apache Lucene, Apache Solr, Apache Hadoop, Hadoop, Apache Pulsar, Pulsar, Apache Spark, Spark, Apache TinkerPop, TinkerPop, Apache Kafka and Kafka are either registered trademarks or trademarks of the Apache Software Foundation or its subsidiaries in Canada, the United States and/or other countries. Kubernetes is the registered trademark of the Linux Foundation.

General Inquiries: Contact IBM