Elasticsearch

ElasticsearchVectorStore

Bases: BaseVectorStore

Provides functionality to interact with Elasticsearch for storing and querying document embeddings.

Attributes:

Name	Type	Description
index_name	str	Name of the Elasticsearch index.
url	str	Elasticsearch instance URL.
embed_model	BaseEmbedding	Embedding model used to compute vectors.
user	str	Elasticsearch username.
password	str	Elasticsearch password.
batch_size	int	Batch size for bulk operations. Defaults to 200.
ssl	bool	Whether to use SSL. Defaults to False.
distance_strategy	str	Distance strategy for similarity search. Currently supports "cosine", "dot_product", and "l2_norm". Defaults to cosine.
text_field	str	Name of the field containing text. Defaults to text.
vector_field	str	Name of the field containing vector embeddings. Defaults to embedding.

Example

from beekeeper.embeddings.huggingface import HuggingFaceEmbedding
from beekeeper.vector_stores.elasticsearch import ElasticsearchVectorStore

embedding = HuggingFaceEmbedding()
es_vector_store = ElasticsearchVectorStore(
    index_name="beekeeper-index",
    url="http://localhost:9200",
    embed_model=embedding,
)

model_post_init

model_post_init(__context)

Initialize Elasticsearch client after Pydantic validation.

add_documents

add_documents(documents: list[Document], create_index_if_not_exists: bool = True) -> list[str]

Add documents to the Elasticsearch index.

Parameters:

Name	Type	Description	Default
documents	list[Document]	List of documents to add to the index.	required
create_index_if_not_exists	bool	Whether to create the index if it doesn't exist. Defaults to True.	True

query_documents

query_documents(query: str, top_k: int = 4) -> list[DocumentWithScore]

Performs a similarity search for the top-k most similar documents.

Parameters:

Name	Type	Description	Default
query	str	Query text.	required
top_k	int	Number of top results to return. Defaults to 4.	4

Returns:

Type	Description
list[DocumentWithScore]	list[DocumentWithScore]: List of the most similar documents.

delete_documents

delete_documents(ids: list[str]) -> None

Delete documents from the Elasticsearch index.

Parameters:

Name	Type	Description	Default
ids	list[str]	List of documents IDs to delete.	required

get_all_documents

get_all_documents(include_fields: list[str] | None = None) -> list[Document]

Get all documents from vector store.