Class SingleStoreVectorStore

Class for interacting with SingleStoreDB, a high-performance distributed SQL database. It provides vector storage and vector functions.

Hierarchy

VectorStore
- SingleStoreVectorStore

Constructors

constructor

new SingleStoreVectorStore(embeddings, config): SingleStoreVectorStore
Parameters
- embeddings: EmbeddingsInterface
- config: SingleStoreVectorStoreConfig
Returns SingleStoreVectorStore
Overrides VectorStore.constructor
- Defined in libs/langchain-community/src/vectorstores/singlestore.ts:145

Properties

FilterType

FilterType: string | object

Defines the filter type used in search and delete operations. Can be an object for structured conditions or a string for simpler filtering.

connectionPool

connectionPool: Pool

contentColumnName

contentColumnName: string

distanceMetric

distanceMetric: DistanceMetrics

embeddings

embeddings: EmbeddingsInterface

Embeddings interface for generating vector embeddings from text queries, enabling vector-based similarity searches.

idColumnName

idColumnName: string

metadataColumnName

metadataColumnName: string

searchConfig

searchConfig: SearchConfig

tableName

tableName: string

useFullTextIndex

useFullTextIndex: boolean

useVectorIndex

useVectorIndex: boolean

vectorColumnName

vectorColumnName: string

vectorIndexName

vectorIndexName: string

vectorIndexOptions

vectorIndexOptions: Metadata

vectorSize

vectorSize: number

Methods

addDocuments

addDocuments(documents): Promise<void>
Adds new documents to the SingleStoreDB database.
Parameters
- documents: Document<Record<string, any>>[]
  An array of Document objects.
Returns Promise<void>
Overrides VectorStore.addDocuments
- Defined in libs/langchain-community/src/vectorstores/singlestore.ts:231

addVectors

addVectors(vectors, documents): Promise<void>
Adds new vectors to the SingleStoreDB database.
Parameters
- vectors: number[][]
  An array of vectors.
- documents: Document<Record<string, any>>[]
  An array of Document objects.
Returns Promise<void>
Overrides VectorStore.addVectors
- Defined in libs/langchain-community/src/vectorstores/singlestore.ts:242

asRetriever

asRetriever(kOrFields?, filter?, callbacks?, tags?, metadata?, verbose?): VectorStoreRetriever<SingleStoreVectorStore>
Creates a VectorStoreRetriever instance with flexible configuration options.
Parameters
- OptionalkOrFields: number | Partial<VectorStoreRetrieverInput<SingleStoreVectorStore>>
  If a number is provided, it sets the k parameter (number of items to retrieve).
  - If an object is provided, it should contain various configuration options.
- Optionalfilter: string | object
  Optional filter criteria to limit the items retrieved based on the specified filter type.
- Optionalcallbacks: Callbacks
  Optional callbacks that may be triggered at specific stages of the retrieval process.
- Optionaltags: string[]
  Tags to categorize or label the VectorStoreRetriever. Defaults to an empty array if not provided.
- Optionalmetadata: Record<string, unknown>
  Additional metadata as key-value pairs to add contextual information for the retrieval process.
- Optionalverbose: boolean
  If true, enables detailed logging for the retrieval process. Defaults to false.
Returns VectorStoreRetriever<SingleStoreVectorStore>
- A configured VectorStoreRetriever instance based on the provided parameters.
Example
Basic usage with a k value:
```
const retriever = myVectorStore.asRetriever(5);
```
Usage with a configuration object:
```
const retriever = myVectorStore.asRetriever({
  k: 10,
  filter: myFilter,
  tags: ['example', 'test'],
  verbose: true,
  searchType: 'mmr',
  searchKwargs: { alpha: 0.5 },
});
```
Inherited from VectorStore.asRetriever
- Defined in langchain-core/dist/vectorstores.d.ts:596

createTableIfNotExists

createTableIfNotExists(): Promise<void>
Creates a new table in the SingleStoreDB database if it does not already exist.

Returns Promise<void>
- Defined in libs/langchain-community/src/vectorstores/singlestore.ts:175

delete

delete(_params?): Promise<void>
Deletes documents from the vector store based on the specified parameters.
Parameters
- Optional_params: Record<string, any>
  Flexible key-value pairs defining conditions for document deletion.
Returns Promise<void>
A promise that resolves once the deletion is complete.
Inherited from VectorStore.delete
- Defined in langchain-core/dist/vectorstores.d.ts:477

end

end(): Promise<void>
Ends the connection to the SingleStoreDB database.

Returns Promise<void>
- Defined in libs/langchain-community/src/vectorstores/singlestore.ts:209

`Optional`maxMarginalRelevanceSearch

maxMarginalRelevanceSearch(query, options, _callbacks): Promise<DocumentInterface<Record<string, any>>[]>
Return documents selected using the maximal marginal relevance. Maximal marginal relevance optimizes for similarity to the query AND diversity among selected documents.
Parameters
- query: string
  Text to look up documents similar to.
- options: MaxMarginalRelevanceSearchOptions<string | object>
- _callbacks: undefined | Callbacks
Returns Promise<DocumentInterface<Record<string, any>>[]>
- List of documents selected by maximal marginal relevance.
Inherited from VectorStore.maxMarginalRelevanceSearch
- Defined in langchain-core/dist/vectorstores.d.ts:527

setSearchConfig

setSearchConfig(config): Promise<void>
Sets the search configuration for the SingleStoreVectorStore instance.
Parameters
- config: SearchConfig
  A SearchConfig object.
Returns Promise<void>
- Defined in libs/langchain-community/src/vectorstores/singlestore.ts:217

similaritySearch

similaritySearch(query, k?, filter?, _callbacks?): Promise<DocumentInterface<Metadata>[]>
Performs a similarity search on the texts stored in the SingleStoreDB
Parameters
- query: string
  A string representing the query text.
- Optionalk: number
  The number of nearest neighbors to return. By default, it is 4.
- Optionalfilter: Metadata
  Optional metadata to filter the texts by.
- Optional_callbacks: Callbacks
  Callbacks object, not used in this implementation.
Returns Promise<DocumentInterface<Metadata>[]>
Top matching documents
Overrides VectorStore.similaritySearch
- Defined in libs/langchain-community/src/vectorstores/singlestore.ts:472

similaritySearchTextAndVectorWithScore

similaritySearchTextAndVectorWithScore(query, vector, k, filter?): Promise<[Document<Record<string, any>>, number][]>
Performs a similarity search on the texts stored in the SingleStoreDB using the specified search strategy and distance metric.
Parameters
- query: string
  A string representing the query text.
- vector: number[]
  An array of numbers representing the query vector.
- k: number
  The number of nearest neighbors to return.
- Optionalfilter: Metadata
  Optional metadata to filter the texts by.
Returns Promise<[Document<Record<string, any>>, number][]>
Top matching documents with score
- Defined in libs/langchain-community/src/vectorstores/singlestore.ts:283

similaritySearchVectorWithScore

similaritySearchVectorWithScore(query, k, filter?): Promise<[Document<Record<string, any>>, number][]>
Performs a similarity search on the vectors stored in the SingleStoreDB database.
Parameters
- query: number[]
  An array of numbers representing the query vector.
- k: number
  The number of nearest neighbors to return.
- Optionalfilter: Metadata
  Optional metadata to filter the vectors by.
Returns Promise<[Document<Record<string, any>>, number][]>
Top matching vectors with score
Overrides VectorStore.similaritySearchVectorWithScore
- Defined in libs/langchain-community/src/vectorstores/singlestore.ts:520

similaritySearchWithScore

similaritySearchWithScore(query, k?, filter?, _callbacks?): Promise<[DocumentInterface<Metadata>, number][]>
Performs a similarity search on the texts stored in the SingleStoreDB
Parameters
- query: string
  A string representing the query text.
- Optionalk: number
  The number of nearest neighbors to return. By default, it is 4.
- Optionalfilter: Metadata
  Optional metadata to filter the texts by.
- Optional_callbacks: Callbacks
Returns Promise<[DocumentInterface<Metadata>, number][]>
Top matching documents with score
Overrides VectorStore.similaritySearchWithScore
- Defined in libs/langchain-community/src/vectorstores/singlestore.ts:496

toJSON

toJSON(): Serialized
Returns Serialized
Inherited from VectorStore.toJSON
- Defined in langchain-core/dist/load/serializable.d.ts:69

toJSONNotImplemented

toJSONNotImplemented(): SerializedNotImplemented
Returns SerializedNotImplemented
Inherited from VectorStore.toJSONNotImplemented
- Defined in langchain-core/dist/load/serializable.d.ts:70

`Static`fromDocuments

fromDocuments(docs, embeddings, dbConfig): Promise<SingleStoreVectorStore>
Creates a new instance of the SingleStoreVectorStore class from a list of Document objects.
Parameters
- docs: Document<Record<string, any>>[]
  An array of Document objects.
- embeddings: EmbeddingsInterface
  An Embeddings object.
- dbConfig: SingleStoreVectorStoreConfig
  A SingleStoreVectorStoreConfig object.
Returns Promise<SingleStoreVectorStore>
A new SingleStoreVectorStore instance
Overrides VectorStore.fromDocuments
- Defined in libs/langchain-community/src/vectorstores/singlestore.ts:566

`Static`fromTexts

fromTexts(texts, metadatas, embeddings, dbConfig): Promise<SingleStoreVectorStore>
Creates a new instance of the SingleStoreVectorStore class from a list of texts.
Parameters
- texts: string[]
  An array of strings.
- metadatas: object[]
  An array of metadata objects.
- embeddings: EmbeddingsInterface
  An Embeddings object.
- dbConfig: SingleStoreVectorStoreConfig
  A SingleStoreVectorStoreConfig object.
Returns Promise<SingleStoreVectorStore>
A new SingleStoreVectorStore instance
Overrides VectorStore.fromTexts
- Defined in libs/langchain-community/src/vectorstores/singlestore.ts:542

Class SingleStoreVectorStore

Hierarchy

Index

Constructors

Properties

Methods

Constructors

constructor

Parameters

Returns SingleStoreVectorStore

Properties

FilterType

connectionPool

contentColumnName

distanceMetric

embeddings

idColumnName

metadataColumnName

searchConfig

tableName

useFullTextIndex

useVectorIndex

vectorColumnName

vectorIndexName

vectorIndexOptions

vectorSize

Methods

addDocuments

Parameters

Returns Promise<void>

addVectors

Parameters

Returns Promise<void>

asRetriever

Parameters

Returns VectorStoreRetriever<SingleStoreVectorStore>

Example

createTableIfNotExists

Returns Promise<void>

delete

Parameters

Returns Promise<void>

end

Returns Promise<void>

OptionalmaxMarginalRelevanceSearch

Parameters

Returns Promise<DocumentInterface<Record<string, any>>[]>

setSearchConfig

Parameters

Returns Promise<void>

similaritySearch

Parameters

Returns Promise<DocumentInterface<Metadata>[]>

similaritySearchTextAndVectorWithScore

Parameters

Returns Promise<[Document<Record<string, any>>, number][]>

similaritySearchVectorWithScore

Parameters

Returns Promise<[Document<Record<string, any>>, number][]>

similaritySearchWithScore

Parameters

Returns Promise<[DocumentInterface<Metadata>, number][]>

toJSON

Returns Serialized

toJSONNotImplemented

Returns SerializedNotImplemented

StaticfromDocuments

Parameters

Returns Promise<SingleStoreVectorStore>

StaticfromTexts

Parameters

Returns Promise<SingleStoreVectorStore>

Settings

On This Page

`Optional`maxMarginalRelevanceSearch

`Static`fromDocuments

`Static`fromTexts