Tablestore:Overview

Scenarios

The KNN vector query feature is suitable for the following scenarios:

• RAG

  RAG is an AI framework that combines retrieval capabilities with the capabilities of large language models (LLMs) to improve the accuracy of outputs generated by LLMs, especially in the field of private data or professional data. RAG is widely used in knowledge bases.

• Recommendation system

  KNN vector query can be used by platforms such as e-commerce, social media, and video streaming platforms. For example, a platform can encode content, such as user behaviors, preferences, and content features, as vectors and store the vectors. Then, KNN vector query can be used to quickly find products, articles, or videos that match user interests. This way, the platform can provide custom recommendations to improve user experience and loyalty.

• Similarity detection

  In content recognition scenarios, such as image recognition, video recognition, speech recognition, voiceprint recognition, and facial recognition, unstructured data is converted to vectors and stored. Then, the system uses KNN vector query to quickly find the most similar content. For example, after a user uploads an image of a commodity to an e-commerce platform, the system can quickly find the images of commodities that are similar to the uploaded image in style, color, or pattern.

• NLP and semantic search

  In the NLP field, text is converted to vectors by using techniques such as Word2Vec and Bidirectional Encoder Representations from Transformers (BERT). Then, KNN vector query is used to understand the semantics of query statements and find the most semantically relevant content such as documents, news, and Q&A pairs. This helps improve the relevance of query results and user experience.

• Knowledge graph and intelligent conversational search

  The nodes and relationships of nodes in knowledge graphs can be represented by vectors. Then, KNN vector query can be used to accelerate entity linking, relational inference, and the response of an intelligent conversational search system. This helps the system accurately understand the questions and provide answers to complex questions.

Features

You can use the KNN vector query feature to perform an approximate nearest neighbor search based on vectors. This way, you can find data items that have the highest similarity to the vector that you want to query in a large-scale dataset.

KNN vector query is an out-of-the-box feature that inherits all the features of search indexes. You can use the KNN vector query feature in pay-as-you-go mode, without the need to build or deploy a system. KNN vector query supports the streaming mode of search indexes. Data can be queried in near real time after the data is written to tables. KNN vector query also supports high-throughput insert, update, and delete operations. The query performance is comparable to that of systems that use the hierarchical navigable small world (HNSW) algorithm.

When you use the KNN vector query feature, you must specify the vector for which you want to query the similarity, the vector field that you want to query, and the top K query results that have the highest similarity to the vector that you want to query. You can also use the features of other query methods in combination with KNN vector query to filter the query results.

Benefits

Billing rules

During the public preview, you are not charged for the billable items specific to the KNN vector query feature when you use the feature. You are charged for other billable items based on the existing billing rules.

When you use a search index to query data, you are charged for the read throughput that is consumed. For more information, see Billable items of search indexes.

Prerequisites

A vector field is specified when you create a search index. For more information, see Create a search index.

Usage notes

When you use the KNN vector query feature, take note of the following items:

• Limits are imposed on the number of vector fields and the number of dimensions for a vector field. For more information, see Search index limits.

• The search index server has multiple partitions. Each partition of the search index server returns the top K neighbors nearest to the vector that you want to query. The top K nearest neighbors returned by the partitions are aggregated on the client node. If you want to use tokens to query all data by page, the total number of rows in the response is related to the number of partitions of the search index server.

• The KNN vector query feature is supported in the following regions: China (Hangzhou), China (Shanghai), China (Qingdao), China (Beijing), China (Zhangjiakou), China (Ulanqab), China (Shenzhen), China (Guangzhou), China (Chengdu), China (Hong Kong), Singapore, Malaysia (Kuala Lumpur), Thailand (Bangkok), US (Virginia), Indonesia (Jakarta), Japan (Tokyo), Germany (Frankfurt), UK (London), SAU (Riyadh - Partner Region), and Philippines (Manila).

API operation

You can call the Search operation and set the query type to KnnVectorQuery to use the KNN vector query feature.

Parameters

Methods

You can use the Tablestore console or Tablestore SDKs to use the KNN vector query feature. Before you use the KNN vector query feature to query data, make sure that the following requirements are met:

• You have an Alibaba Cloud account or a Resource Access Management (RAM) user that has permissions to perform operations on Tablestore. For more information about how to grant the operation permissions on Tablestore to a RAM user, see Use a RAM policy to grant permissions to a RAM user.

  An AccessKey pair is created for your Alibaba Cloud account or RAM user if you want to use Tablestore SDKs or the Tablestore CLI to perform operations on Tablestore. For more information, see Create an AccessKey pair.

• A data table is created. For more information, see Operations on a data table.

• A search index is created for the data table. For more information, see Create a search index.

  A vector field is specified when you create the search index.

• An OTSClient instance is initialized if you want to use Tablestore SDKs to perform operations on Tablestore. For more information, see Initialize an OTSClient instance.

private static void knnVectorQuery(SyncClient client) {
    SearchQuery searchQuery = new SearchQuery();
    KnnVectorQuery query = new KnnVectorQuery();
    query.setFieldName("Col_Vector");
    query.setTopK(10); // Return the top 10 vectors in the table that have the highest similarity as the specified vector. 
    query.setFloat32QueryVector(new float[]{0.1f, 0.2f, 0.3f, 0.4f});
    // Specify the query conditions for the top 10 vectors: the value of the Col_Keyword column is hangzhou and the value of the Col_Long column is less than 4. 
    query.setFilter(QueryBuilders.bool()
            .must(QueryBuilders.term("Col_Keyword", "hangzhou"))
            .must(QueryBuilders.range("Col_Long").lessThan(4))
    );
    searchQuery.setQuery(query);
    searchQuery.setLimit(10);
    // Sort the query results based on scores. 
    searchQuery.setSort(new Sort(Collections.singletonList(new ScoreSort())));
    SearchRequest searchRequest = new SearchRequest("<TABLE_NAME>", "<SEARCH_INDEX_NAME>", searchQuery);
    SearchRequest.ColumnsToGet columnsToGet = new SearchRequest.ColumnsToGet();
    columnsToGet.setColumns(Arrays.asList("Col_Keyword", "Col_Long"));
    searchRequest.setColumnsToGet(columnsToGet);
    // Call the Search operation. 
    SearchResponse resp = client.search(searchRequest);
    for (SearchHit hit : resp.getSearchHits()) {
        // Display the scores. 
        System.out.println(hit.getScore());
        // Display the data. 
        System.out.println(hit.getRow());
    }
}

References

• When you use a search index to query data, you can use the following query methods: term query, terms query, match all query, match query, match phrase query, prefix query, range query, wildcard query, fuzzy query, Boolean query, geo query, nested query, KNN vector query, and exists query. You can select query methods based on your business requirements to query data from multiple dimensions.

  You can sort or paginate rows that meet the query conditions by using the sorting and paging features. For more information, see Perform sorting and paging.

  You can use the collapse (distinct) feature to collapse the result set based on a specific column. This way, data of the specified type appears only once in the query results. For more information, see Collapse (distinct).

• If you want to analyze data in a data table, you can use the aggregation feature of the Search operation or execute SQL statements. For example, you can obtain the minimum and maximum values, sum, and total number of rows. For more information, see Aggregation and SQL query.

• If you want to obtain all rows that meet the query conditions without the need to sort the rows, you can call the ParallelScan and ComputeSplits operations to use the parallel scan feature. For more information, see Parallel scan.

Appendix 1: Combination of KNN vector query and Boolean query

You can use KNN vector query and Boolean query in various combinations. The query performance varies based on the combination that you use. In the example in this section, a small amount of data meets the filter conditions.

In this example, 0.1 billion images are stored in a table and 50,000 images belong to User A. Among the 50,000 images, 50 images are stored in the previous seven days. User A wants to search for 10 images that have the highest similarity to the specified image among the 50 images. The following table describes two common combinations of KNN vector query and Boolean query that User A can use to meet the query requirements.

Appendix 2: Sample vector normalization

The following sample code provides an example on how to normalize vectors:

  public static float[] l2normalize(float[] v, boolean throwOnZero) {
    double squareSum = 0.0f;
    int dim = v.length;
    for (float x : v) {
      squareSum += x * x;
    }
    if (squareSum == 0) {
      if (throwOnZero) {
        throw new IllegalArgumentException("can't normalize a zero-length vector");
      } else {
        return v;
      }
    }
    double length = Math.sqrt(squareSum);
    for (int i = 0; i < dim; i++) {
      v[i] /= length;
    }
    return v;
  }