SurrealDBStore#

class langchain_community.vectorstores.surrealdb.SurrealDBStore(embedding_function: Embeddings, **kwargs: Any)[source]#

SurrealDB as Vector Store.

To use, you should have the surrealdb python package installed.

Parameters:

embedding_function (Embeddings) – Embedding function to use.
dburl – SurrealDB connection url
ns – surrealdb namespace for the vector store. (default: “langchain”)
db – surrealdb database for the vector store. (default: “database”)
collection – surrealdb collection for the vector store. (default: “documents”)
db_pass ((optional) db_user and) – surrealdb credentials
kwargs (Any)

Example

from langchain_community.vectorstores.surrealdb import SurrealDBStore
from langchain_community.embeddings import HuggingFaceEmbeddings

model_name = "sentence-transformers/all-mpnet-base-v2"
embedding_function = HuggingFaceEmbeddings(model_name=model_name)
dburl = "ws://localhost:8000/rpc"
ns = "langchain"
db = "docstore"
collection = "documents"
db_user = "root"
db_pass = "root"

sdb = SurrealDBStore.from_texts(
        texts=texts,
        embedding=embedding_function,
        dburl,
        ns, db, collection,
        db_user=db_user, db_pass=db_pass)

Attributes

embeddings

Access the query embedding object if available.

Methods

`__init__`(embedding_function, **kwargs)
`aadd_documents`(documents, **kwargs)	Async run more documents through the embeddings and add to the vectorstore.
`aadd_texts`(texts[, metadatas])	Add list of text along with embeddings to the vector store asynchronously
`add_documents`(documents, **kwargs)	Add or update documents in the vectorstore.
`add_texts`(texts[, metadatas])	Add list of text along with embeddings to the vector store
`adelete`([ids])	Delete by document ID asynchronously.
`afrom_documents`(documents, embedding, **kwargs)	Async return VectorStore initialized from documents and embeddings.
`afrom_texts`(texts, embedding[, metadatas])	Create SurrealDBStore from list of text asynchronously
`aget_by_ids`(ids, /)	Async get documents by their IDs.
`amax_marginal_relevance_search`(query[, k, ...])	Return docs selected using the maximal marginal relevance.
`amax_marginal_relevance_search_by_vector`(...)	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, filter])	Run similarity search on query asynchronously
`asimilarity_search_by_vector`(embedding[, k, ...])	Run similarity search on query embedding asynchronously
`asimilarity_search_with_relevance_scores`(query)	Run similarity search asynchronously and return relevance scores
`asimilarity_search_with_score`(query[, k, filter])	Run similarity search asynchronously and return distance scores
`delete`([ids])	Delete by document ID.
`from_documents`(documents, embedding, **kwargs)	Return VectorStore initialized from documents and embeddings.
`from_texts`(texts, embedding[, metadatas])	Create SurrealDBStore from list of text
`get_by_ids`(ids, /)	Get documents by their IDs.
`initialize`()	Initialize connection to surrealdb database and authenticate if credentials are provided
`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.
`search`(query, search_type, **kwargs)	Return docs most similar to query using a specified search type.
`similarity_search`(query[, k, filter])	Run similarity search on query
`similarity_search_by_vector`(embedding[, k, ...])	Run similarity search on query embedding
`similarity_search_with_relevance_scores`(query)	Run similarity search synchronously and return relevance scores
`similarity_search_with_score`(query[, k, filter])	Run similarity search synchronously and return distance scores

__init__(embedding_function: Embeddings, **kwargs: Any) → None[source]#

Parameters:

embedding_function (Embeddings)
kwargs (Any)

Return type:

None

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, **kwargs: Any) → List[str][source]#

Add list of text along with embeddings to the vector store asynchronously

Parameters:

texts (Iterable[str]) – collection of text to add to the database
metadatas (List[dict] | None)
kwargs (Any)

Returns:

List of ids for the newly inserted documents

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

Add list of text along with embeddings to the vector store

Parameters:

texts (Iterable[str]) – collection of text to add to the database
metadatas (List[dict] | None)
kwargs (Any)

Returns:

List of ids for the newly inserted documents

Return type:

List[str]

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

Delete by document ID asynchronously.

Parameters:

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

Returns:

True if deletion is successful, False otherwise.

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, **kwargs: Any) → SurrealDBStore[source]#

Create SurrealDBStore from list of text asynchronously

Parameters:

texts (List[str]) – list of text to vectorize and store
embedding (Optional[Embeddings]) – Embedding function.
dburl (str) – SurrealDB connection url (default: “ws://localhost:8000/rpc”)
ns (str) – surrealdb namespace for the vector store. (default: “langchain”)
db (str) – surrealdb database for the vector store. (default: “database”)
collection (str) – surrealdb collection for the vector store. (default: “documents”)
db_pass ((optional) db_user and) – surrealdb credentials
metadatas (List[dict] | None)
kwargs (Any)

Returns:

SurrealDBStore object initialized and ready for use.

Return type:

SurrealDBStore

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, *, 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) – 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]

async amax_marginal_relevance_search_by_vector(embedding: List[float], k: int = 4, 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) – 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]

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, *, filter: Dict[str, str] | None = None, **kwargs: Any) → List[Document][source]#

Run similarity search on query asynchronously

Parameters:

query (str) – Query
k (int) – Number of results to return. Defaults to 4.
filter (Optional[Dict[str, str]]) – Filter by metadata. Defaults to None.
kwargs (Any)

Returns:

List of Documents most similar to the query

Return type:

List[Document]

async asimilarity_search_by_vector(embedding: List[float], k: int = 4, *, filter: Dict[str, str] | None = None, **kwargs: Any) → List[Document][source]#

Run similarity search on query embedding asynchronously

Parameters:

embedding (List[float]) – Query embedding
k (int) – Number of results to return. Defaults to 4.
filter (Optional[Dict[str, str]]) – Filter by metadata. Defaults to None.
kwargs (Any)

Returns:

List of Documents most similar to the query

Return type:

List[Document]

async asimilarity_search_with_relevance_scores(query: str, k: int = 4, *, filter: Dict[str, str] | None = None, **kwargs: Any) → List[Tuple[Document, float]][source]#

Run similarity search asynchronously and return relevance scores

Parameters:

query (str) – Query
k (int) – Number of results to return. Defaults to 4.
filter (Optional[Dict[str, str]]) – Filter by metadata. Defaults to None.
kwargs (Any)

Returns:

List of Documents most similar along with relevance scores

Return type:

List[Tuple[Document, float]]

async asimilarity_search_with_score(query: str, k: int = 4, *, filter: Dict[str, str] | None = None, **kwargs: Any) → List[Tuple[Document, float]][source]#

Run similarity search asynchronously and return distance scores

Parameters:

query (str) – Query
k (int) – Number of results to return. Defaults to 4.
filter (Optional[Dict[str, str]]) – Filter by metadata. Defaults to None.
kwargs (Any)

Returns:

List of Documents most similar along with relevance distance scores

Return type:

List[Tuple[Document, float]]

delete(ids: List[str] | None = None, **kwargs: Any) → bool | None[source]#

Delete by document ID.

Parameters:

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

Returns:

True if deletion is successful, False otherwise.

Return type:

Optional[bool]

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

classmethod from_texts(texts: List[str], embedding: Embeddings, metadatas: List[dict] | None = None, **kwargs: Any) → SurrealDBStore[source]#

Create SurrealDBStore from list of text

Parameters:

texts (List[str]) – list of text to vectorize and store
embedding (Optional[Embeddings]) – Embedding function.
dburl (str) – SurrealDB connection url
ns (str) – surrealdb namespace for the vector store. (default: “langchain”)
db (str) – surrealdb database for the vector store. (default: “database”)
collection (str) – surrealdb collection for the vector store. (default: “documents”)
db_pass ((optional) db_user and) – surrealdb credentials
metadatas (List[dict] | None)
kwargs (Any)

Returns:

SurrealDBStore object initialized and ready for use.

Return type:

SurrealDBStore

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.

async initialize() → None[source]#

Initialize connection to surrealdb database and authenticate if credentials are provided

Return type:: None

max_marginal_relevance_search(query: str, k: int = 4, 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) – 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 = 4, 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) – 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]

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 = 4, *, filter: Dict[str, str] | None = None, **kwargs: Any) → List[Document][source]#

Run similarity search on query

Parameters:

query (str) – Query
k (int) – Number of results to return. Defaults to 4.
filter (Optional[Dict[str, str]]) – Filter by metadata. Defaults to None.
kwargs (Any)

Returns:

List of Documents most similar to the query

Return type:

List[Document]

similarity_search_by_vector(embedding: List[float], k: int = 4, *, filter: Dict[str, str] | None = None, **kwargs: Any) → List[Document][source]#

Run similarity search on query embedding

Parameters:

embedding (List[float]) – Query embedding
k (int) – Number of results to return. Defaults to 4.
filter (Optional[Dict[str, str]]) – Filter by metadata. Defaults to None.
kwargs (Any)

Returns:

List of Documents most similar to the query

Return type:

List[Document]

similarity_search_with_relevance_scores(query: str, k: int = 4, *, filter: Dict[str, str] | None = None, **kwargs: Any) → List[Tuple[Document, float]][source]#

Run similarity search synchronously and return relevance scores

Parameters:

query (str) – Query
k (int) – Number of results to return. Defaults to 4.
filter (Optional[Dict[str, str]]) – Filter by metadata. Defaults to None.
kwargs (Any)

Returns:

List of Documents most similar along with relevance scores

Return type:

List[Tuple[Document, float]]

similarity_search_with_score(query: str, k: int = 4, *, filter: Dict[str, str] | None = None, **kwargs: Any) → List[Tuple[Document, float]][source]#

Run similarity search synchronously and return distance scores

Parameters:

query (str) – Query
k (int) – Number of results to return. Defaults to 4.
filter (Optional[Dict[str, str]]) – Filter by metadata. Defaults to None.
kwargs (Any)

Returns:

List of Documents most similar along with relevance distance scores

Return type:

List[Tuple[Document, float]]

Examples using SurrealDBStore

SurrealDB