Qdrant 向量存储

🌐 Qdrant Vector Store

QdrantVector 类使用 Qdrant 提供向量搜索，Qdrant 是一个向量相似性搜索引擎。它提供了一个可投入生产的服务，通过便捷的 API 来存储、搜索和管理向量，并支持额外的负载信息和扩展的过滤功能。

🌐 The QdrantVector class provides vector search using Qdrant, a vector similarity search engine. It provides a production-ready service with a convenient API to store, search, and manage vectors with additional payload and extended filtering support.

构造函数选项

🌐 Constructor Options

url:

string

REST URL of the Qdrant instance. Eg. https://xyz-example.eu-central.aws.cloud.qdrant.io:6333

apiKey:

string

Optional Qdrant API key

https:

boolean

Whether to use TLS when setting up the connection. Recommended.

方法

🌐 Methods

createIndex()

indexName:

string

Name of the index to create

dimension:

number

Vector dimension (must match your embedding model). Required for single-vector collections.

metric?:

'cosine' | 'euclidean' | 'dotproduct'

= cosine

Distance metric for similarity search

namedVectors?:

Record<string, { size: number; distance: 'cosine' | 'euclidean' | 'dotproduct' }>

Configuration for named vector spaces. When provided, creates a collection with multiple named vector fields.

创建命名向量集合

🌐 Creating a Named Vectors Collection

// Create a collection with multiple named vector spaces
await store.createIndex({
  indexName: "multi_modal",
  dimension: 768, // fallback
  namedVectors: {
    text: { size: 768, distance: "cosine" },
    image: { size: 512, distance: "euclidean" },
  },
});

upsert()

indexName:

string

Name of the index to upsert into

vectors:

number[][]

Array of embedding vectors

metadata?:

Record<string, any>[]

Metadata for each vector

ids?:

string[]

Optional vector IDs (auto-generated if not provided)

vectorName?:

string

Name of the vector space to upsert into when using named vectors.

向命名向量空间上插入或更新

🌐 Upserting into Named Vector Spaces

// Upsert into the "text" vector space
await store.upsert({
  indexName: "multi_modal",
  vectors: textEmbeddings,
  metadata: textMetadata,
  vectorName: "text",
});

// Upsert into the "image" vector space
await store.upsert({
  indexName: "multi_modal",
  vectors: imageEmbeddings,
  metadata: imageMetadata,
  vectorName: "image",
});

query()

indexName:

string

Name of the index to query

queryVector:

number[]

Query vector to find similar vectors

topK?:

number

= 10

Number of results to return

filter?:

Record<string, any>

Metadata filters for the query

includeVector?:

boolean

= false

Whether to include vectors in the results

using?:

string

Name of the vector field to query when using named vectors. Use this when your collection has multiple named vector fields.

命名向量

🌐 Named Vectors

Qdrant 支持命名向量，允许每个集合有多个向量字段。使用 using 参数指定要查询的命名向量：

🌐 Qdrant supports named vectors, allowing multiple vector fields per collection. Use the using parameter to specify which named vector to query against:

const results = await store.query({
  indexName: "my_index",
  queryVector: embedding,
  topK: 10,
  using: "title_embedding", // Query against a specific named vector
});

listIndexes()

返回一个由索引名称组成的字符串数组。

🌐 Returns an array of index names as strings.

describeIndex()

indexName:

string

Name of the index to describe

返回：

🌐 Returns:

interface IndexStats {
  dimension: number;
  count: number;
  metric: "cosine" | "euclidean" | "dotproduct";
}

deleteIndex()

indexName:

string

Name of the index to delete

updateVector()

通过 ID 或元数据过滤器更新单个向量。必须提供 id 或 filter 中的一个，但不能同时提供两者。

🌐 Update a single vector by ID or by metadata filter. Either id or filter must be provided, but not both.

indexName:

string

Name of the index to update

id?:

string

ID of the vector to update (mutually exclusive with filter)

filter?:

Record<string, any>

Metadata filter to identify vector(s) to update (mutually exclusive with id)

update:

{ vector?: number[]; metadata?: Record<string, any>; }

Object containing the vector and/or metadata to update

在指定索引中更新向量和/或其元数据。如果同时提供向量和元数据，则两者都会被更新。如果只提供其中一个，则只更新该部分。

🌐 Updates a vector and/or its metadata in the specified index. If both vector and metadata are provided, both will be updated. If only one is provided, only that will be updated.

deleteVector()

indexName:

string

Name of the index from which to delete the vector

id:

string

ID of the vector to delete

根据 ID 删除指定索引的向量。

🌐 Deletes a vector from the specified index by its ID.

deleteVectors()

通过 ID 或元数据过滤器删除多个向量。必须提供 ids 或 filter 中的一个，但不能同时提供两者。

🌐 Delete multiple vectors by IDs or by metadata filter. Either ids or filter must be provided, but not both.

indexName:

string

Name of the index containing the vectors to delete

ids?:

string[]

Array of vector IDs to delete (mutually exclusive with filter)

filter?:

Record<string, any>

Metadata filter to identify vectors to delete (mutually exclusive with ids)

createPayloadIndex()

在集合字段上创建一个负载（元数据）索引，以实现高效过滤。这对于 Qdrant Cloud 以及任何带有 strict_mode_config = true 的 Qdrant 实例是必需的。

🌐 Creates a payload (metadata) index on a collection field to enable efficient filtering. This is required for Qdrant Cloud and any Qdrant instance with strict_mode_config = true.

indexName:

string

Name of the collection to create the payload index on

fieldName:

string

Name of the payload field to index

fieldSchema:

'keyword' | 'integer' | 'float' | 'geo' | 'text' | 'bool' | 'datetime' | 'uuid'

The schema type for the payload field

wait?:

boolean

= true

Whether to wait for the operation to complete

// Create a keyword index for filtering by source
await store.createPayloadIndex({
  indexName: "my_index",
  fieldName: "source",
  fieldSchema: "keyword",
});

const results = await store.query({
  indexName: "my_index",
  queryVector: queryVector,
  filter: { source: "document-a" },
});

deletePayloadIndex()

从集合字段中移除有效负载索引。

🌐 Removes a payload index from a collection field.

indexName:

string

Name of the collection to delete the payload index from

fieldName:

string

Name of the payload field index to delete

wait?:

boolean

= true

Whether to wait for the operation to complete

响应类型

🌐 Response Types

查询结果以此格式返回：

🌐 Query results are returned in this format:

interface QueryResult {
  id: string;
  score: number;
  metadata: Record<string, any>;
  vector?: number[]; // Only included if includeVector is true
}

错误处理

🌐 Error Handling

该存储会抛出可以被捕获的类型化错误：

🌐 The store throws typed errors that can be caught:

try {
  await store.query({
    indexName: "index_name",
    queryVector: queryVector,
  });
} catch (error) {
  if (error instanceof VectorStoreError) {
    console.log(error.code); // 'connection_failed' | 'invalid_dimension' | etc
    console.log(error.details); // Additional error context
  }
}

相关

🌐 Related

• 元数据过滤器