milvus-logo
LFAI
Home
  • User Guide

Conduct a Vector Query

This topic describes how to conduct a vector query.

Unlike a vector similarity search, a vector query retrieves vectors via scalar filtering based on boolean expression. Milvus supports many data types in the scalar fields and a variety of boolean expressions. The boolean expression filters on scalar fields or the primary key field, and it retrieves all results that match the filters.

The following example shows how to perform a vector query on a 2000-row dataset of book ID (primary key), word count (scalar field), and book introduction (vector field), simulating the situation where you query for certain books based on their IDs.

Load collection

All search and query operations within Milvus are executed in memory. Load the collection to memory before conducting a vector query.

Python Java GO Node.js CLI 
from pymilvus import Collection
collection = Collection("book")      # Get an existing collection.
collection.load()

await milvusClient.collectionManager.loadCollection({
  collection_name: "book",
});

err := milvusClient.LoadCollection(
  context.Background(),   // ctx
  "book",                 // CollectionName
  false                   // async
)
if err != nil {
  log.Fatal("failed to load collection:", err.Error())
}

milvusClient.loadCollection(
  LoadCollectionParam.newBuilder()
    .withCollectionName("book")
    .build()
);

load -c book

Conduct a vector query

The following example filters the vectors with certain book_id values, and returns the book_id field and book_intro of the results.

Milvus supports setting consistency level specifically for a search or query (only on PyMilvus currently). The consistency level set in the search or query requests overwrites the one set while creating the collection. In this example, the consistency level of the search request is set as Strong, meaning Milvus will read the most updated data view at the exact time point when a search or query request comes. Without specifying the consistency level during a search or query, Milvus adopts the original consistency level of the collection.

Python Java GO Node.js CLI 
res = collection.query(
  expr = "book_id in [2,4,6,8]", 
  output_fields = ["book_id", "book_intro"],
  consistency_level="Strong"
)

const results = await milvusClient.dataManager.query({
  collection_name: "book",
  expr: "book_id in [2,4,6,8]",
  output_fields: ["book_id", "book_intro"],
});

queryResult, err := milvusClient.Query(
    context.Background(),                                   // ctx
    "book",                                                 // CollectionName
    "",                                                     // PartitionName
    entity.NewColumnInt64("book_id", []int64{2,4,6,8}),     // expr
    []string{"book_id", "book_intro"}                       // OutputFields
)
if err != nil {
    log.Fatal("fail to query collection:", err.Error())
}

List<String> query_output_fields = Arrays.asList("book_id", "word_count");
QueryParam queryParam = QueryParam.newBuilder()
  .withCollectionName("book")
  .withExpr("book_id in [2,4,6,8]")
  .withOutFields(query_output_fields)
  .build();
R<QueryResults> respQuery = milvusClient.query(queryParam);

query

collection_name: book

The query expression: book_id in [2,4,6,8]

Name of partitions that contain entities(split by "," if multiple) []:

A list of fields to return(split by "," if multiple) []: book_id, book_intro

timeout []:
Parameter Description
expr Boolean expression used to filter attribute. Find more expression details in Boolean Expression Rules.
output_fields (optional) List of names of the field to return.
partition_names (optional) List of names of the partitions to query on.
consistency_level (optional) Consistency level of the query.
Parameter Description
collection_name Name of the collection to query.
expr Boolean expression used to filter attribute. Find more expression details in Boolean Expression Rules.
output_fields (optional) List of names of the field to return.
partition_names (optional) List of names of the partitions to query on.
Parameter Description Options
ctx Context to control API invocation process. N/A
CollectionName Name of the collection to query. N/A
partitionName List of names of the partitions to load. All partitions will be queried if it is left empty. N/A
expr Boolean expression used to filter attribute. See Boolean Expression Rules for more information.
OutputFields Name of the field to return. Vector field is not supported in current release.
Parameter Description Options
CollectionName Name of the collection to load. N/A
OutFields Name of the field to return. Vector field is not supported in current release.
Expr Boolean expression used to filter attribute. See Boolean Expression Rules for more information.
Option Full name Description
--help n/a Displays help for using the command.

Check the returned results.

Python Java GO Node.js CLI 
sorted_res = sorted(res, key=lambda k: k['book_id'])
sorted_res

console.log(results.data)

fmt.Printf("%#v\n", queryResult)
for _, qr := range queryResult {
    fmt.Println(qr.IDs)
}

QueryResultsWrapper wrapperQuery = new QueryResultsWrapper(respQuery.getData());
System.out.println(wrapperQuery.getFieldWrapper("book_id").getFieldData());
System.out.println(wrapperQuery.getFieldWrapper("word_count").getFieldData());

# Milvus CLI automatically returns the entities with the pre-defined output fields.

What's next

Table of contents
Feedback

Was this page helpful?