LanceDB

Langchain Vector store for LanceDB. Embedded database with local directory-based storage and approximate nearest neighbor search.

Install

pip install langchain-lancedb

or

uv add langchain-lancedb

API Reference

__init__

def __init__(
    self,
    embedding_function: Embeddings | None = None,
    uri: str | Path = "./.rag_cache/db/lancedb",
    table_name: str = "documents",
    namespace: str | None = None,
    **kwargs,
)

from_texts

def from_texts(
    cls,
    texts: list[str],
    embedding: Embeddings | None = None,
    metadatas: list[dict] | None = None,
    ids: list[str] | None = None,
    uri: str | Path = "./.rag_cache/db/lancedb",
    table_name: str | None = None,
    namespace: str | None = None,
    **kwargs,
) -> LanceDB

Returns: LanceDB — a new vector store with the texts indexed.

add_texts

def add_texts(
    self,
    texts: list[str],
    metadatas: list[dict] | None = None,
    ids: list[str] | None = None,
    **kwargs,
) -> list[str]

Returns: list[str] — the IDs of the added texts. On first call, automatically creates the LanceDB table with inferred schema.

delete

def delete(
    self,
    ids: list[str] | None = None,
    **kwargs,
) -> bool | None

Returns: bool \| None — True if deletion succeeded, False if no table exists. Raises ValueError if ids is None.

similarity_search

def similarity_search(
    self,
    query: str,
    k: int = 4,
    **kwargs,
) -> list[Document]

Returns: list[Document] — documents most similar to the query, ordered by distance (ascending).

similarity_search_with_score

def similarity_search_with_score(
    self,
    query: str,
    k: int = 4,
    **kwargs,
) -> list[tuple[Document, float]]

Returns: list[tuple[Document, float]] — tuples of (Document, distance). Lower distance = more similar. Uses LanceDB's built-in ANN search.