LanceDB#

LanceDB vector store.

To use, you should have lancedb python package installed. You can install it with pip install lancedb.

Parameters:

connection (Optional[Any]) – LanceDB connection to use. If not provided, a new connection will be created.
embedding (Optional[Embeddings]) – Embedding to use for the vectorstore.
vector_key (Optional[str]) – Key to use for the vector in the database. Defaults to vector.
id_key (Optional[str]) – Key to use for the id in the database. Defaults to id.
text_key (Optional[str]) – Key to use for the text in the database. Defaults to text.
table_name (Optional[str]) – Name of the table to use. Defaults to vectorstore.
api_key (Optional[str]) – API key to use for LanceDB cloud database.
region (Optional[str]) – Region to use for LanceDB cloud database.
mode (Optional[str]) – Mode to use for adding data to the table. Valid values are append and overwrite. Defaults to overwrite.
uri (Optional[str])
table (Optional[Any])
distance (Optional[str])
reranker (Optional[Any])
relevance_score_fn (Optional[Callable[[float], float]])
limit (int)

Example

Initialize with Lance DB vectorstore

Attributes

embeddings

Access the query embedding object if available.

Methods

`__init__`([connection, embedding, uri, ...])	Initialize with Lance DB vectorstore
`aadd_documents`(documents, **kwargs)	Async run more documents through the embeddings and add to the vectorstore.
`aadd_texts`(texts[, metadatas, ids])	Async run more texts through the embeddings and add to the vectorstore.
`add_documents`(documents, **kwargs)	Add or update documents in the vectorstore.
`add_images`(uris[, metadatas, ids])	Run more images through the embeddings and add to the vectorstore.
`add_texts`(texts[, metadatas, ids])	Turn texts into embedding and add it to the database
`adelete`([ids])	Async delete by vector ID or other criteria.
`afrom_documents`(documents, embedding, **kwargs)	Async return VectorStore initialized from documents and embeddings.
`afrom_texts`(texts, embedding[, metadatas, ids])	Async return VectorStore initialized from texts and embeddings.
`aget_by_ids`(ids, /)	Async get documents by their IDs.
`amax_marginal_relevance_search`(query[, k, ...])	Async return docs selected using the maximal marginal relevance.
`amax_marginal_relevance_search_by_vector`(...)	Async return docs selected using the maximal marginal relevance.
`as_retriever`(**kwargs)	Return VectorStoreRetriever initialized from this VectorStore.
`asearch`(query, search_type, **kwargs)	Async return docs most similar to query using a specified search type.
`asimilarity_search`(query[, k])	Async return docs most similar to query.
`asimilarity_search_by_vector`(embedding[, k])	Async return docs most similar to embedding vector.
`asimilarity_search_with_relevance_scores`(query)	Async return docs and relevance scores in the range [0, 1].
`asimilarity_search_with_score`(args, *kwargs)	Async run similarity search with distance.
`create_index`([col_name, vector_col, ...])	Create a scalar(for non-vector cols) or a vector index on a table.
`delete`([ids, delete_all, filter, ...])	Allows deleting rows by filtering, by ids or drop columns from the table.
`encode_image`(uri)	Get base64 string from image URI.
`from_documents`(documents, embedding, **kwargs)	Return VectorStore initialized from documents and embeddings.
`from_texts`(texts, embedding[, metadatas, ...])	Return VectorStore initialized from texts and embeddings.
`get_by_ids`(ids, /)	Get documents by their IDs.
`get_table`([name, set_default])	Fetches a table object from the database.
`max_marginal_relevance_search`(query[, k, ...])	Return docs selected using the maximal marginal relevance.
`max_marginal_relevance_search_by_vector`(...)	Return docs selected using the maximal marginal relevance.
`results_to_docs`(results[, score])
`search`(query, search_type, **kwargs)	Return docs most similar to query using a specified search type.
`similarity_search`(query[, k, name, filter, fts])	Return documents most similar to the query
`similarity_search_by_vector`(embedding[, k, ...])	Return documents most similar to the query vector.
`similarity_search_by_vector_with_relevance_scores`(...)	Return documents most similar to the query vector with relevance scores.
`similarity_search_with_relevance_scores`(query)	Return docs and relevance scores in the range [0, 1].
`similarity_search_with_score`(query[, k, filter])	Return documents most similar to the query with relevance scores.

Initialize with Lance DB vectorstore

Parameters:

connection (Any | None)
embedding (Embeddings | None)
uri (str | None)
vector_key (str | None)
id_key (str | None)
text_key (str | None)
table_name (str | None)
api_key (str | None)
region (str | None)
mode (str | None)
table (Any | None)
distance (str | None)
reranker (Any | None)
relevance_score_fn (Callable[[float], float] | None)
limit (int)

async aadd_documents(documents: list[Document], **kwargs: Any) → list[str]#

Async run more documents through the embeddings and add to the vectorstore.

Parameters:

documents (list[Document]) – Documents to add to the vectorstore.
kwargs (Any) – Additional keyword arguments.

Returns:

List of IDs of the added texts.

Raises:

ValueError – If the number of IDs does not match the number of documents.

Return type:

list[str]

async aadd_texts(texts: Iterable[str], metadatas: list[dict] | None = None, *, ids: list[str] | None = None, **kwargs: Any) → list[str]#

Async run more texts through the embeddings and add to the vectorstore.

Parameters:

texts (Iterable[str]) – Iterable of strings to add to the vectorstore.
metadatas (list[dict] | None) – Optional list of metadatas associated with the texts. Default is None.
ids (list[str] | None) – Optional list
**kwargs (Any) – vectorstore specific parameters.

Returns:

List of ids from adding the texts into the vectorstore.

Raises:

ValueError – If the number of metadatas does not match the number of texts.
ValueError – If the number of ids does not match the number of texts.

Return type:

list[str]

add_documents(documents: list[Document], **kwargs: Any) → list[str]#

Add or update documents in the vectorstore.

Parameters:

documents (list[Document]) – Documents to add to the vectorstore.
kwargs (Any) – Additional keyword arguments. if kwargs contains ids and documents contain ids, the ids in the kwargs will receive precedence.

Returns:

List of IDs of the added texts.

Raises:

ValueError – If the number of ids does not match the number of documents.

Return type:

list[str]

add_images(uris: List[str], metadatas: List[dict] | None = None, ids: List[str] | None = None, **kwargs: Any) → List[str][source]#

Run more images through the embeddings and add to the vectorstore.

Parameters:

List[str] (uris) – File path to the image.
metadatas (Optional[List[dict]], optional) – Optional list of metadatas.
ids (Optional[List[str]], optional) – Optional list of IDs.
uris (List[str])
kwargs (Any)

Returns:

List of IDs of the added images.

Return type:

List[str]

add_texts(texts: Iterable[str], metadatas: List[dict] | None = None, ids: List[str] | None = None, **kwargs: Any) → List[str][source]#

Turn texts into embedding and add it to the database

Parameters:

texts (Iterable[str]) – Iterable of strings to add to the vectorstore.
metadatas (List[dict] | None) – Optional list of metadatas associated with the texts.
ids (List[str] | None) – Optional list of ids to associate with the texts.
ids – Optional list of ids to associate with the texts.
kwargs (Any)

Returns:

List of ids of the added texts.

Return type:

List[str]

async adelete(ids: list[str] | None = None, **kwargs: Any) → bool | None#

Async delete by vector ID or other criteria.

Parameters:

ids (list[str] | None) – List of ids to delete. If None, delete all. Default is None.
**kwargs (Any) – Other keyword arguments that subclasses might use.

Returns:

True if deletion is successful, False otherwise, None if not implemented.

Return type:

Optional[bool]

async classmethod afrom_documents(documents: list[Document], embedding: Embeddings, **kwargs: Any) → VST#

Async return VectorStore initialized from documents and embeddings.

Parameters:

documents (list[Document]) – List of Documents to add to the vectorstore.
embedding (Embeddings) – Embedding function to use.
kwargs (Any) – Additional keyword arguments.

Returns:

VectorStore initialized from documents and embeddings.

Return type:

VectorStore

async classmethod afrom_texts(texts: list[str], embedding: Embeddings, metadatas: list[dict] | None = None, *, ids: list[str] | None = None, **kwargs: Any) → VST#

Async return VectorStore initialized from texts and embeddings.

Parameters:

texts (list[str]) – Texts to add to the vectorstore.
embedding (Embeddings) – Embedding function to use.
metadatas (list[dict] | None) – Optional list of metadatas associated with the texts. Default is None.
ids (list[str] | None) – Optional list of IDs associated with the texts.
kwargs (Any) – Additional keyword arguments.

Returns:

VectorStore initialized from texts and embeddings.

Return type:

VectorStore

async aget_by_ids(ids: Sequence[str], /) → list[Document]#

Async get documents by their IDs.

The returned documents are expected to have the ID field set to the ID of the document in the vector store.

Fewer documents may be returned than requested if some IDs are not found or if there are duplicated IDs.

Users should not assume that the order of the returned documents matches the order of the input IDs. Instead, users should rely on the ID field of the returned documents.

This method should NOT raise exceptions if no documents are found for some IDs.

Parameters:: ids (Sequence[str]) – List of ids to retrieve.
Returns:: List of Documents.
Return type:: list[Document]

Added in version 0.2.11.

async amax_marginal_relevance_search(query: str, k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, **kwargs: Any) → list[Document]#

Async return docs selected using the maximal marginal relevance.

Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents.

Parameters:

query (str) – Text to look up documents similar to.
k (int) – Number of Documents to return. Defaults to 4.
fetch_k (int) – Number of Documents to fetch to pass to MMR algorithm. Default is 20.
lambda_mult (float) – Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5.
kwargs (Any)

Returns:

List of Documents selected by maximal marginal relevance.

Return type:

list[Document]

async amax_marginal_relevance_search_by_vector(embedding: list[float], k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, **kwargs: Any) → list[Document]#

Async return docs selected using the maximal marginal relevance.

Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents.

Parameters:

embedding (list[float]) – Embedding to look up documents similar to.
k (int) – Number of Documents to return. Defaults to 4.
fetch_k (int) – Number of Documents to fetch to pass to MMR algorithm. Default is 20.
lambda_mult (float) – Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5.
**kwargs (Any) – Arguments to pass to the search method.

Returns:

List of Documents selected by maximal marginal relevance.

Return type:

list[Document]

as_retriever(**kwargs: Any) → VectorStoreRetriever#

Return VectorStoreRetriever initialized from this VectorStore.

Parameters:

**kwargs (Any) –

Keyword arguments to pass to the search function. Can include: search_type (Optional[str]): Defines the type of search that

the Retriever should perform. Can be “similarity” (default), “mmr”, or “similarity_score_threshold”.

search_kwargs (Optional[Dict]): Keyword arguments to pass to the

search function. Can include things like:

k: Amount of documents to return (Default: 4) score_threshold: Minimum relevance threshold

for similarity_score_threshold

fetch_k: Amount of documents to pass to MMR algorithm: (Default: 20)
lambda_mult: Diversity of results returned by MMR;: 1 for minimum diversity and 0 for maximum. (Default: 0.5)

filter: Filter by document metadata

Returns:

Retriever class for VectorStore.

Return type:

VectorStoreRetriever

Examples:

# Retrieve more documents with higher diversity
# Useful if your dataset has many similar documents
docsearch.as_retriever(
    search_type="mmr",
    search_kwargs={'k': 6, 'lambda_mult': 0.25}
)

# Fetch more documents for the MMR algorithm to consider
# But only return the top 5
docsearch.as_retriever(
    search_type="mmr",
    search_kwargs={'k': 5, 'fetch_k': 50}
)

# Only retrieve documents that have a relevance score
# Above a certain threshold
docsearch.as_retriever(
    search_type="similarity_score_threshold",
    search_kwargs={'score_threshold': 0.8}
)

# Only get the single most similar document from the dataset
docsearch.as_retriever(search_kwargs={'k': 1})

# Use a filter to only retrieve documents from a specific paper
docsearch.as_retriever(
    search_kwargs={'filter': {'paper_title':'GPT-4 Technical Report'}}
)

async asearch(query: str, search_type: str, **kwargs: Any) → list[Document]#

Async return docs most similar to query using a specified search type.

Parameters:

query (str) – Input text.
search_type (str) – Type of search to perform. Can be “similarity”, “mmr”, or “similarity_score_threshold”.
**kwargs (Any) – Arguments to pass to the search method.

Returns:

List of Documents most similar to the query.

Raises:

ValueError – If search_type is not one of “similarity”, “mmr”, or “similarity_score_threshold”.

Return type:

list[Document]

async asimilarity_search(query: str, k: int = 4, **kwargs: Any) → list[Document]#

Async return docs most similar to query.

Parameters:

query (str) – Input text.
k (int) – Number of Documents to return. Defaults to 4.
**kwargs (Any) – Arguments to pass to the search method.

Returns:

List of Documents most similar to the query.

Return type:

list[Document]

async asimilarity_search_by_vector(embedding: list[float], k: int = 4, **kwargs: Any) → list[Document]#

Async return docs most similar to embedding vector.

Parameters:

embedding (list[float]) – Embedding to look up documents similar to.
k (int) – Number of Documents to return. Defaults to 4.
**kwargs (Any) – Arguments to pass to the search method.

Returns:

List of Documents most similar to the query vector.

Return type:

list[Document]

async asimilarity_search_with_relevance_scores(query: str, k: int = 4, **kwargs: Any) → list[tuple[Document, float]]#

Async return docs and relevance scores in the range [0, 1].

0 is dissimilar, 1 is most similar.

Parameters:

query (str) – Input text.
k (int) – Number of Documents to return. Defaults to 4.
**kwargs (Any) –
kwargs to be passed to similarity search. Should include: score_threshold: Optional, a floating point value between 0 to 1 to

filter the resulting set of retrieved docs

Returns:

List of Tuples of (doc, similarity_score)

Return type:

list[tuple[Document, float]]

async asimilarity_search_with_score(*args: Any, **kwargs: Any) → list[tuple[Document, float]]#

Async run similarity search with distance.

Parameters:

*args (Any) – Arguments to pass to the search method.
**kwargs (Any) – Arguments to pass to the search method.

Returns:

List of Tuples of (doc, similarity_score).

Return type:

list[tuple[Document, float]]

Create a scalar(for non-vector cols) or a vector index on a table. Make sure your vector column has enough data before creating an index on it.

Parameters:

vector_col (str | None) – Provide if you want to create index on a vector column.
col_name (str | None) – Provide if you want to create index on a non-vector column.
metric (str | None) – Provide the metric to use for vector index. Defaults to ‘L2’ choice of metrics: ‘L2’, ‘dot’, ‘cosine’
num_partitions (int | None) – Number of partitions to use for the index. Defaults to 256.
num_sub_vectors (int | None) – Number of sub-vectors to use for the index. Defaults to 96.
index_cache_size (int | None) – Size of the index cache. Defaults to None.
name (str | None) – Name of the table to create index on. Defaults to None.

Returns:

None

Return type:

None

Allows deleting rows by filtering, by ids or drop columns from the table.

Parameters:

filter (str | None) – Provide a string SQL expression - “{col} {operation} {value}”.
ids (List[str] | None) – Provide list of ids to delete from the table.
drop_columns (List[str] | None) – Provide list of columns to drop from the table.
delete_all (bool | None) – If True, delete all rows from the table.
name (str | None)
kwargs (Any)

Return type:

None

encode_image(uri: str) → str[source]#

Get base64 string from image URI.

Parameters:: uri (str)
Return type:: str

classmethod from_documents(documents: list[Document], embedding: Embeddings, **kwargs: Any) → VST#

Return VectorStore initialized from documents and embeddings.

Parameters:

documents (list[Document]) – List of Documents to add to the vectorstore.
embedding (Embeddings) – Embedding function to use.
kwargs (Any) – Additional keyword arguments.

Returns:

VectorStore initialized from documents and embeddings.

Return type:

VectorStore

Return VectorStore initialized from texts and embeddings.

Parameters:

texts (List[str]) – Texts to add to the vectorstore.
embedding (Embeddings) – Embedding function to use.
metadatas (List[dict] | None) – Optional list of metadatas associated with the texts. Default is None.
ids – Optional list of IDs associated with the texts.
kwargs (Any) – Additional keyword arguments.
connection (Any | None)
vector_key (str | None)
id_key (str | None)
text_key (str | None)
table_name (str | None)
api_key (str | None)
region (str | None)
mode (str | None)
distance (str | None)
reranker (Any | None)
relevance_score_fn (Callable[[float], float] | None)

Returns:

VectorStore initialized from texts and embeddings.

Return type:

VectorStore

get_by_ids(ids: Sequence[str], /) → list[Document]#

Get documents by their IDs.

The returned documents are expected to have the ID field set to the ID of the document in the vector store.

Fewer documents may be returned than requested if some IDs are not found or if there are duplicated IDs.

Users should not assume that the order of the returned documents matches the order of the input IDs. Instead, users should rely on the ID field of the returned documents.

This method should NOT raise exceptions if no documents are found for some IDs.

Parameters:: ids (Sequence[str]) – List of ids to retrieve.
Returns:: List of Documents.
Return type:: list[Document]

Added in version 0.2.11.

get_table(name: str | None = None, set_default: bool | None = False) → Any[source]#

Fetches a table object from the database.

Parameters:

name (str, optional) – The name of the table to fetch. Defaults to None and fetches current table object.
set_default (bool, optional) – Sets fetched table as the default table. Defaults to False.

Returns:

The fetched table object.

Return type:

Any

Raises:

ValueError – If the specified table is not found in the database.

max_marginal_relevance_search(query: str, k: int | None = None, fetch_k: int = 20, lambda_mult: float = 0.5, filter: Dict[str, str] | None = None, **kwargs: Any) → List[Document][source]#

Return docs selected using the maximal marginal relevance. Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents.

Parameters:

query (str) – Text to look up documents similar to.
k (int | None) – Number of Documents to return. Defaults to 4.
fetch_k (int) – Number of Documents to fetch to pass to MMR algorithm.
lambda_mult (float) – Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5.
filter (Optional[Dict[str, str]]) – Filter by metadata. Defaults to None.
kwargs (Any)

Returns:

List of Documents selected by maximal marginal relevance.

Return type:

List[Document]

max_marginal_relevance_search_by_vector(embedding: List[float], k: int | None = None, fetch_k: int = 20, lambda_mult: float = 0.5, filter: Dict[str, str] | None = None, **kwargs: Any) → List[Document][source]#

Return docs selected using the maximal marginal relevance. Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents.

Parameters:

embedding (List[float]) – Embedding to look up documents similar to.
k (int | None) – Number of Documents to return. Defaults to 4.
fetch_k (int) – Number of Documents to fetch to pass to MMR algorithm.
lambda_mult (float) – Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5.
filter (Optional[Dict[str, str]]) – Filter by metadata. Defaults to None.
kwargs (Any)

Returns:

List of Documents selected by maximal marginal relevance.

Return type:

List[Document]

results_to_docs(results: Any, score: bool = False) → Any[source]#

Parameters:

results (Any)
score (bool)

Return type:

Any

search(query: str, search_type: str, **kwargs: Any) → list[Document]#

Return docs most similar to query using a specified search type.

Parameters:

query (str) – Input text
search_type (str) – Type of search to perform. Can be “similarity”, “mmr”, or “similarity_score_threshold”.
**kwargs (Any) – Arguments to pass to the search method.

Returns:

List of Documents most similar to the query.

Raises:

ValueError – If search_type is not one of “similarity”, “mmr”, or “similarity_score_threshold”.

Return type:

list[Document]

similarity_search(query: str, k: int | None = None, name: str | None = None, filter: Any | None = None, fts: bool | None = False, **kwargs: Any) → List[Document][source]#

Return documents most similar to the query

Parameters:

query (str) – String to query the vectorstore with.
k (int | None) – Number of documents to return.
filter (Optional[Dict]) –
Optional filter arguments sql_filter(Optional[string]): SQL filter to apply to the query. prefilter(Optional[bool]): Whether to apply the filter prior

to the vector search.
name (str | None)
fts (bool | None)
kwargs (Any)

Raises:

ValueError – If the specified table is not found in the database.

Returns:

List of documents most similar to the query.

Return type:

List[Document]

similarity_search_by_vector(embedding: List[float], k: int | None = None, filter: Dict[str, str] | None = None, name: str | None = None, **kwargs: Any) → Any[source]#

Return documents most similar to the query vector.

Parameters:

embedding (List[float])
k (int | None)
filter (Dict[str, str] | None)
name (str | None)
kwargs (Any)

Return type:

Any

similarity_search_by_vector_with_relevance_scores(embedding: List[float], k: int | None = None, filter: Dict[str, str] | None = None, name: str | None = None, **kwargs: Any) → Any[source]#

Return documents most similar to the query vector with relevance scores.

Parameters:

embedding (List[float])
k (int | None)
filter (Dict[str, str] | None)
name (str | None)
kwargs (Any)

Return type:

Any

similarity_search_with_relevance_scores(query: str, k: int = 4, **kwargs: Any) → list[tuple[Document, float]]#

Return docs and relevance scores in the range [0, 1].

0 is dissimilar, 1 is most similar.

Parameters:

query (str) – Input text.
k (int) – Number of Documents to return. Defaults to 4.
**kwargs (Any) –
kwargs to be passed to similarity search. Should include: score_threshold: Optional, a floating point value between 0 to 1 to

filter the resulting set of retrieved docs.

Returns:

List of Tuples of (doc, similarity_score).

Return type:

list[tuple[Document, float]]

similarity_search_with_score(query: str, k: int | None = None, filter: Dict[str, str] | None = None, **kwargs: Any) → Any[source]#

Return documents most similar to the query with relevance scores.

Parameters:

query (str)
k (int | None)
filter (Dict[str, str] | None)
kwargs (Any)

Return type:

Any

Examples using LanceDB