langchain.vectorstores.elastic_vector_search.ElasticKnnSearch

class langchain.vectorstores.elastic_vector_search.ElasticKnnSearch(index_name: str, embedding: Embeddings, es_connection: Optional['Elasticsearch'] = None, es_cloud_id: Optional[str] = None, es_user: Optional[str] = None, es_password: Optional[str] = None, vector_query_field: Optional[str] = 'vector', query_field: Optional[str] = 'text')

Bases: VectorStore, ABC

ElasticKnnSearch is a class for performing k-nearest neighbor (k-NN) searches on text data using Elasticsearch.

This class is used to create an Elasticsearch index of text data that can be searched using k-NN search. The text data is transformed into vector embeddings using a provided embedding model, and these embeddings are stored in the Elasticsearch index.

index_name

The name of the Elasticsearch index.

Type

str

embedding

The embedding model to use for transforming text data into vector embeddings.

Type

Embeddings

es_connection

An existing Elasticsearch connection.

Type

Elasticsearch, optional

es_cloud_id

The Cloud ID of your Elasticsearch Service deployment.

Type

str, optional

es_user

The username for your Elasticsearch Service deployment.

Type

str, optional

es_password

The password for your Elasticsearch Service deployment.

Type

str, optional

vector_query_field

The name of the field in the Elasticsearch index that contains the vector embeddings.

Type

str, optional

query_field

The name of the field in the Elasticsearch index that contains the original text data.

Type

str, optional

Usage:

>>> from embeddings import Embeddings
>>> embedding = Embeddings.load('glove')
>>> es_search = ElasticKnnSearch('my_index', embedding)
>>> es_search.add_texts(['Hello world!', 'Another text'])
>>> results = es_search.knn_search('Hello')
[(Document(page_content='Hello world!', metadata={}), 0.9)]

Methods

__init__(index_name, embedding[, ...])
aadd_documents(documents, **kwargs)	Run more documents through the embeddings and add to the vectorstore.
aadd_texts(texts[, metadatas])	Run more texts through the embeddings and add to the vectorstore.
add_documents(documents, **kwargs)	Run more documents through the embeddings and add to the vectorstore.
add_texts(texts[, metadatas, model_id, ...])	Add a list of texts to the Elasticsearch index.
afrom_documents(documents, embedding, **kwargs)	Return VectorStore initialized from documents and embeddings.
afrom_texts(texts, embedding[, metadatas])	Return VectorStore initialized from texts and embeddings.
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)
asearch(query, search_type, **kwargs)	Return docs most similar to query using specified search type.
asimilarity_search(query[, k])	Return docs most similar to query.
asimilarity_search_by_vector(embedding[, k])	Return docs most similar to embedding vector.
asimilarity_search_with_relevance_scores(query)	Return docs most similar to query.
create_knn_index(mapping)	Create a new k-NN index in Elasticsearch.
delete([ids])	Delete by vector ID or other criteria.
from_documents(documents, embedding, **kwargs)	Return VectorStore initialized from documents and embeddings.
from_texts(texts, embedding[, metadatas])	Create a new ElasticKnnSearch instance and add a list of texts to the
knn_hybrid_search([query, k, query_vector, ...])	Perform a hybrid k-NN and text search on the Elasticsearch index.
knn_search([query, k, query_vector, ...])	Perform a k-NN search on the Elasticsearch index.
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 specified search type.
similarity_search(query[, k, filter])	Pass through to knn_search
similarity_search_by_vector(embedding[, k])	Return docs most similar to embedding vector.
similarity_search_with_relevance_scores(query)	Return docs and relevance scores in the range [0, 1].
similarity_search_with_score(query[, k])	Pass through to knn_search including score

Attributes

embeddings

Access the query embedding object if available.

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

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

Parameters

(List[Document] (documents) – Documents to add to the vectorstore.

Returns

List of IDs of the added texts.

Return type

List[str]

async aadd_texts(texts: Iterable[str], metadatas: Optional[List[dict]] = None, **kwargs: Any) → List[str]

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

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

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

Parameters

(List[Document] (documents) – Documents to add to the vectorstore.

Returns

List of IDs of the added texts.

Return type

List[str]

add_texts(texts: Iterable[str], metadatas: Optional[List[Dict[Any, Any]]] = None, model_id: Optional[str] = None, refresh_indices: bool = False, **kwargs: Any) → List[str]

Add a list of texts to the Elasticsearch index.

Parameters

• texts (Iterable[str]) – The texts to add to the index.

• metadatas (List[Dict[Any, Any]], optional) – A list of metadata dictionaries to associate with the texts.

• model_id (str, optional) – The ID of the model to use for transforming the texts into vectors.

• refresh_indices (bool, optional) – Whether to refresh the Elasticsearch indices after adding the texts.

• **kwargs – Arbitrary keyword arguments.

Returns

A list of IDs for the added texts.

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

Return VectorStore initialized from documents and embeddings.

async classmethod afrom_texts(texts: List[str], embedding: Embeddings, metadatas: Optional[List[dict]] = None, **kwargs: Any) → VST

Return VectorStore initialized from texts and embeddings.

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

Return docs selected using the maximal marginal relevance.

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]

Return docs selected using the maximal marginal relevance.

as_retriever(**kwargs: Any) → VectorStoreRetriever

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

Return docs most similar to query using specified search type.

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

Return docs most similar to query.

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

Return docs most similar to embedding vector.

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

Return docs most similar to query.

create_knn_index(mapping: Dict) → None

Create a new k-NN index in Elasticsearch.

Parameters

mapping (Dict) – The mapping to use for the new index.

Returns

None

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

Delete by vector ID or other criteria.

Parameters

• ids – List of ids to delete.

• **kwargs – Other keyword arguments that subclasses might use.

Returns

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

Return type

Optional[bool]

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

Return VectorStore initialized from documents and embeddings.

classmethod from_texts(texts: List[str], embedding: Embeddings, metadatas: Optional[List[Dict[Any, Any]]] = None, **kwargs: Any) → ElasticKnnSearch

Create a new ElasticKnnSearch instance and add a list of texts to the

Elasticsearch index.

Parameters

• texts (List[str]) – The texts to add to the index.

• embedding (Embeddings) – The embedding model to use for transforming the texts into vectors.

• metadatas (List[Dict[Any, Any]], optional) – A list of metadata dictionaries to associate with the texts.

• **kwargs – Arbitrary keyword arguments.

Returns

A new ElasticKnnSearch instance.

knn_hybrid_search(query: Optional[str] = None, k: Optional[int] = 10, query_vector: Optional[List[float]] = None, model_id: Optional[str] = None, size: Optional[int] = 10, source: Optional[bool] = True, knn_boost: Optional[float] = 0.9, query_boost: Optional[float] = 0.1, fields: Optional[Union[List[Mapping[str, Any]], Tuple[Mapping[str, Any], ...]]] = None, page_content: Optional[str] = 'text') → List[Tuple[Document, float]]

Perform a hybrid k-NN and text search on the Elasticsearch index.

Parameters

• query (str, optional) – The query text to search for.

• k (int, optional) – The number of nearest neighbors to return.

• query_vector (List[float], optional) – The query vector to search for.

• model_id (str, optional) – The ID of the model to use for transforming the query text into a vector.

• size (int, optional) – The number of search results to return.

• source (bool, optional) – Whether to return the source of the search results.

• knn_boost (float, optional) – The boost value to apply to the k-NN search results.

• query_boost (float, optional) – The boost value to apply to the text search results.

• fields (List[Mapping[str, Any]], optional) – The fields to return in the search results.

• page_content (str, optional) – The name of the field that contains the page content.

Returns

A list of tuples, where each tuple contains a Document object and a score.

knn_search(query: Optional[str] = None, k: Optional[int] = 10, query_vector: Optional[List[float]] = None, model_id: Optional[str] = None, size: Optional[int] = 10, source: Optional[bool] = True, fields: Optional[Union[List[Mapping[str, Any]], Tuple[Mapping[str, Any], ...]]] = None, page_content: Optional[str] = 'text') → List[Tuple[Document, float]]

Perform a k-NN search on the Elasticsearch index.

Parameters

• query (str, optional) – The query text to search for.

• k (int, optional) – The number of nearest neighbors to return.

• query_vector (List[float], optional) – The query vector to search for.

• model_id (str, optional) – The ID of the model to use for transforming the query text into a vector.

• size (int, optional) – The number of search results to return.

• source (bool, optional) – Whether to return the source of the search results.

• fields (List[Mapping[str, Any]], optional) – The fields to return in the search results.

• page_content (str, optional) – The name of the field that contains the page content.

Returns

A list of tuples, where each tuple contains a Document object and a score.

max_marginal_relevance_search(query: str, k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, **kwargs: Any) → List[Document]

Return docs selected using the maximal marginal relevance.

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

Parameters

• query – Text to look up documents similar to.

• k – Number of Documents to return. Defaults to 4.

• fetch_k – Number of Documents to fetch to pass to MMR algorithm.

• lambda_mult – 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.

Returns

List of Documents selected by maximal marginal relevance.

max_marginal_relevance_search_by_vector(embedding: List[float], k: int = 4, fetch_k: int = 20, lambda_mult: float = 0.5, **kwargs: Any) → List[Document]

Return docs selected using the maximal marginal relevance.

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

Parameters

• embedding – Embedding to look up documents similar to.

• k – Number of Documents to return. Defaults to 4.

• fetch_k – Number of Documents to fetch to pass to MMR algorithm.

• lambda_mult – 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.

Returns

List of Documents selected by maximal marginal relevance.

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

Return docs most similar to query using specified search type.

similarity_search(query: str, k: int = 4, filter: Optional[dict] = None, **kwargs: Any) → List[Document]

Pass through to knn_search

similarity_search_by_vector(embedding: List[float], k: int = 4, **kwargs: Any) → List[Document]

Return docs most similar to embedding vector.

Parameters

• embedding – Embedding to look up documents similar to.

• k – Number of Documents to return. Defaults to 4.

Returns

List of Documents most similar to the query vector.

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 – input text

• k – Number of Documents to return. Defaults to 4.

• **kwargs –

  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)

similarity_search_with_score(query: str, k: int = 10, **kwargs: Any) → List[Tuple[Document, float]]

Pass through to knn_search including score

property embeddings: Optional[langchain.embeddings.base.Embeddings]

Access the query embedding object if available.

Examples using ElasticKnnSearch

• ElasticSearch