Class LanceDB

A wrapper for an open-source database for vector-search with persistent storage. It simplifies retrieval, filtering, and management of embeddings.

Hierarchy (View Summary)

BaseDynamicToolInput
- LanceDB

Index

Constructors

Methods

_vectorstoreType addDocuments addVectors similaritySearchVectorWithScore fromDocuments fromTexts

Constructors

constructor

new LanceDB(embeddings: EmbeddingsInterface, args?: LanceDBArgs): LanceDB
Parameters
- embeddings: EmbeddingsInterface
- Optionalargs: LanceDBArgs
Returns LanceDB
Overrides VectorStore.constructor
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain-community/src/vectorstores/lancedb.ts:34

Methods

_vectorstoreType

_vectorstoreType(): string
Returns string
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain-community/src/vectorstores/lancedb.ts:57

addDocuments

addDocuments(documents: Document[]): Promise<void>
Adds documents to the database.
Parameters
- documents: Document[]
  The documents to be added.
Returns Promise<void>
A Promise that resolves when the documents have been added.
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain-community/src/vectorstores/lancedb.ts:49

addVectors

addVectors(vectors: number[][], documents: Document[]): Promise<void>
Adds vectors and their corresponding documents to the database.
Parameters
- vectors: number[][]
  The vectors to be added.
- documents: Document[]
  The corresponding documents to be added.
Returns Promise<void>
A Promise that resolves when the vectors and documents have been added.
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain-community/src/vectorstores/lancedb.ts:67

similaritySearchVectorWithScore

similaritySearchVectorWithScore(
query: number[],
k: number,
): Promise<[Document, number][]>
Performs a similarity search on the vectors in the database and returns the documents and their scores.
Parameters
- query: number[]
  The query vector.
- k: number
  The number of results to return.
Returns Promise<[Document, number][]>
A Promise that resolves with an array of tuples, each containing a Document and its score.
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain-community/src/vectorstores/lancedb.ts:104

`Static`fromDocuments

fromDocuments(
    docs: Document[],
    embeddings: EmbeddingsInterface,
    dbConfig?: LanceDBArgs,
): Promise<LanceDB>
Creates a new instance of LanceDB from documents.
Parameters
- docs: Document[]
  The documents to be added to the database.
- embeddings: EmbeddingsInterface
  The embeddings to be managed.
- OptionaldbConfig: LanceDBArgs
  The configuration for the LanceDB instance.
Returns Promise<LanceDB>
A Promise that resolves with a new instance of LanceDB.
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain-community/src/vectorstores/lancedb.ts:172

`Static`fromTexts

fromTexts(
    texts: string[],
    metadatas: object | object[],
    embeddings: EmbeddingsInterface,
    dbConfig?: LanceDBArgs,
): Promise<LanceDB>
Creates a new instance of LanceDB from texts.
Parameters
- texts: string[]
  The texts to be converted into documents.
- metadatas: object | object[]
  The metadata for the texts.
- embeddings: EmbeddingsInterface
  The embeddings to be managed.
- OptionaldbConfig: LanceDBArgs
  The configuration for the LanceDB instance.
Returns Promise<LanceDB>
A Promise that resolves with a new instance of LanceDB.
- Defined in remotes/langchain-ai/langchainjs/v1/libs/langchain-community/src/vectorstores/lancedb.ts:147