langchain_community.vectorstores.elasticsearch.ElasticsearchStore

class langchain_community.vectorstores.elasticsearch.ElasticsearchStore(index_name: str, *, embedding: ~typing.Optional[~langchain_core.embeddings.Embeddings] = None, es_connection: ~typing.Optional[Elasticsearch] = None, es_url: ~typing.Optional[str] = None, es_cloud_id: ~typing.Optional[str] = None, es_user: ~typing.Optional[str] = None, es_api_key: ~typing.Optional[str] = None, es_password: ~typing.Optional[str] = None, vector_query_field: str = 'vector', query_field: str = 'text', distance_strategy: ~typing.Optional[~typing.Literal[<DistanceStrategy.COSINE: 'COSINE'>, <DistanceStrategy.DOT_PRODUCT: 'DOT_PRODUCT'>, <DistanceStrategy.EUCLIDEAN_DISTANCE: 'EUCLIDEAN_DISTANCE'>]] = None, strategy: ~langchain_community.vectorstores.elasticsearch.BaseRetrievalStrategy = <langchain_community.vectorstores.elasticsearch.ApproxRetrievalStrategy object>, es_params: ~typing.Optional[~typing.Dict[str, ~typing.Any]] = None)[source]

Elasticsearch vector store.

Example

from langchain_community.vectorstores import ElasticsearchStore
from langchain_community.embeddings.openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings()
vectorstore = ElasticsearchStore(
    embedding=OpenAIEmbeddings(),
    index_name="langchain-demo",
    es_url="http://localhost:9200"
)
Parameters
  • index_name – Name of the Elasticsearch index to create.

  • es_url – URL of the Elasticsearch instance to connect to.

  • cloud_id – Cloud ID of the Elasticsearch instance to connect to.

  • es_user – Username to use when connecting to Elasticsearch.

  • es_password – Password to use when connecting to Elasticsearch.

  • es_api_key – API key to use when connecting to Elasticsearch.

  • es_connection – Optional pre-existing Elasticsearch connection.

  • vector_query_field – Optional. Name of the field to store the embedding vectors in.

  • query_field – Optional. Name of the field to store the texts in.

  • strategy – Optional. Retrieval strategy to use when searching the index. Defaults to ApproxRetrievalStrategy. Can be one of ExactRetrievalStrategy, ApproxRetrievalStrategy, or SparseRetrievalStrategy.

  • distance_strategy – Optional. Distance strategy to use when searching the index. Defaults to COSINE. Can be one of COSINE, EUCLIDEAN_DISTANCE, or DOT_PRODUCT.

If you want to use a cloud hosted Elasticsearch instance, you can pass in the cloud_id argument instead of the es_url argument.

Example

from langchain_community.vectorstores import ElasticsearchStore
from langchain_community.embeddings.openai import OpenAIEmbeddings

vectorstore = ElasticsearchStore(
    embedding=OpenAIEmbeddings(),
    index_name="langchain-demo",
    es_cloud_id="<cloud_id>"
    es_user="elastic",
    es_password="<password>"
)

You can also connect to an existing Elasticsearch instance by passing in a pre-existing Elasticsearch connection via the es_connection argument.

Example

from langchain_community.vectorstores import ElasticsearchStore
from langchain_community.embeddings.openai import OpenAIEmbeddings

from elasticsearch import Elasticsearch

es_connection = Elasticsearch("http://localhost:9200")

vectorstore = ElasticsearchStore(
    embedding=OpenAIEmbeddings(),
    index_name="langchain-demo",
    es_connection=es_connection
)

ElasticsearchStore by default uses the ApproxRetrievalStrategy, which uses the HNSW algorithm to perform approximate nearest neighbor search. This is the fastest and most memory efficient algorithm.

If you want to use the Brute force / Exact strategy for searching vectors, you can pass in the ExactRetrievalStrategy to the ElasticsearchStore constructor.

Example

from langchain_community.vectorstores import ElasticsearchStore
from langchain_community.embeddings.openai import OpenAIEmbeddings

vectorstore = ElasticsearchStore(
    embedding=OpenAIEmbeddings(),
    index_name="langchain-demo",
    es_url="http://localhost:9200",
    strategy=ElasticsearchStore.ExactRetrievalStrategy()
)

Both strategies require that you know the similarity metric you want to use when creating the index. The default is cosine similarity, but you can also use dot product or euclidean distance.

Example

from langchain_community.vectorstores import ElasticsearchStore
from langchain_community.embeddings.openai import OpenAIEmbeddings
from langchain_community.vectorstores.utils import DistanceStrategy

vectorstore = ElasticsearchStore(
    embedding=OpenAIEmbeddings(),
    index_name="langchain-demo",
    es_url="http://localhost:9200",
    distance_strategy="DOT_PRODUCT"
)

Attributes

embeddings

Access the query embedding object if available.

Methods

ApproxRetrievalStrategy([query_model_id, ...])

Used to perform approximate nearest neighbor search using the HNSW algorithm.

ExactRetrievalStrategy()

Used to perform brute force / exact nearest neighbor search via script_score.

SparseVectorRetrievalStrategy([model_id])

Used to perform sparse vector search via text_expansion.

__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_embeddings(text_embeddings[, metadatas, ...])

Add the given texts and embeddings to the vectorstore.

add_texts(texts[, metadatas, ids, ...])

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

adelete([ids])

Delete by vector ID or other criteria.

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)

Return VectorStoreRetriever initialized from this VectorStore.

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

asimilarity_search_with_score(*args, **kwargs)

Run similarity search with distance asynchronously.

connect_to_elasticsearch(*[, es_url, ...])

delete([ids, refresh_indices])

Delete documents from the Elasticsearch index.

from_documents(documents[, embedding, ...])

Construct ElasticsearchStore wrapper from documents.

from_texts(texts[, embedding, metadatas, ...])

Construct ElasticsearchStore wrapper from raw documents.

get_user_agent()

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, fetch_k, filter])

Return Elasticsearch documents most similar to query.

similarity_search_by_vector(embedding[, k])

Return docs most similar to embedding vector.

similarity_search_by_vector_with_relevance_scores(...)

Return Elasticsearch documents most similar to query, along with 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 Elasticsearch documents most similar to query, along with scores.

static ApproxRetrievalStrategy(query_model_id: Optional[str] = None, hybrid: Optional[bool] = False, rrf: Optional[Union[dict, bool]] = True) ApproxRetrievalStrategy[source]

Used to perform approximate nearest neighbor search using the HNSW algorithm.

At build index time, this strategy will create a dense vector field in the index and store the embedding vectors in the index.

At query time, the text will either be embedded using the provided embedding function or the query_model_id will be used to embed the text using the model deployed to Elasticsearch.

if query_model_id is used, do not provide an embedding function.

Parameters
  • query_model_id – Optional. ID of the model to use to embed the query text within the stack. Requires embedding model to be deployed to Elasticsearch.

  • hybrid – Optional. If True, will perform a hybrid search using both the knn query and a text query. Defaults to False.

  • rrf

    Optional. rrf is Reciprocal Rank Fusion. When hybrid is True,

    and rrf is True, then rrf: {}. and rrf is False, then rrf is omitted. and isinstance(rrf, dict) is True, then pass in the dict values.

    rrf could be passed for adjusting ‘rank_constant’ and ‘window_size’.

static ExactRetrievalStrategy() ExactRetrievalStrategy[source]

Used to perform brute force / exact nearest neighbor search via script_score.

static SparseVectorRetrievalStrategy(model_id: Optional[str] = None) SparseRetrievalStrategy[source]

Used to perform sparse vector search via text_expansion. Used for when you want to use ELSER model to perform document search.

At build index time, this strategy will create a pipeline that will embed the text using the ELSER model and store the resulting tokens in the index.

At query time, the text will be embedded using the ELSER model and the resulting tokens will be used to perform a text_expansion query.

Parameters

model_id – Optional. Default is “.elser_model_1”. ID of the model to use to embed the query text within the stack. Requires embedding model to be deployed to Elasticsearch.

__init__(index_name: str, *, embedding: ~typing.Optional[~langchain_core.embeddings.Embeddings] = None, es_connection: ~typing.Optional[Elasticsearch] = None, es_url: ~typing.Optional[str] = None, es_cloud_id: ~typing.Optional[str] = None, es_user: ~typing.Optional[str] = None, es_api_key: ~typing.Optional[str] = None, es_password: ~typing.Optional[str] = None, vector_query_field: str = 'vector', query_field: str = 'text', distance_strategy: ~typing.Optional[~typing.Literal[<DistanceStrategy.COSINE: 'COSINE'>, <DistanceStrategy.DOT_PRODUCT: 'DOT_PRODUCT'>, <DistanceStrategy.EUCLIDEAN_DISTANCE: 'EUCLIDEAN_DISTANCE'>]] = None, strategy: ~langchain_community.vectorstores.elasticsearch.BaseRetrievalStrategy = <langchain_community.vectorstores.elasticsearch.ApproxRetrievalStrategy object>, es_params: ~typing.Optional[~typing.Dict[str, ~typing.Any]] = None)[source]
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_embeddings(text_embeddings: Iterable[Tuple[str, List[float]]], metadatas: Optional[List[dict]] = None, ids: Optional[List[str]] = None, refresh_indices: bool = True, create_index_if_not_exists: bool = True, bulk_kwargs: Optional[Dict] = None, **kwargs: Any) List[str][source]

Add the given texts and embeddings to the vectorstore.

Parameters
  • text_embeddings – Iterable pairs of string and embedding to add to the vectorstore.

  • metadatas – Optional list of metadatas associated with the texts.

  • ids – Optional list of unique IDs.

  • refresh_indices – Whether to refresh the Elasticsearch indices after adding the texts.

  • create_index_if_not_exists – Whether to create the Elasticsearch index if it doesn’t already exist.

  • *bulk_kwargs

    Additional arguments to pass to Elasticsearch bulk. - chunk_size: Optional. Number of texts to add to the

    index at a time. Defaults to 500.

Returns

List of ids from adding the texts into the vectorstore.

add_texts(texts: Iterable[str], metadatas: Optional[List[Dict[Any, Any]]] = None, ids: Optional[List[str]] = None, refresh_indices: bool = True, create_index_if_not_exists: bool = True, bulk_kwargs: Optional[Dict] = None, **kwargs: Any) List[str][source]

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

Parameters
  • texts – Iterable of strings to add to the vectorstore.

  • metadatas – Optional list of metadatas associated with the texts.

  • ids – Optional list of ids to associate with the texts.

  • refresh_indices – Whether to refresh the Elasticsearch indices after adding the texts.

  • create_index_if_not_exists – Whether to create the Elasticsearch index if it doesn’t already exist.

  • *bulk_kwargs

    Additional arguments to pass to Elasticsearch bulk. - chunk_size: Optional. Number of texts to add to the

    index at a time. Defaults to 500.

Returns

List of ids from adding the texts into the vectorstore.

async adelete(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]

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.

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

Return VectorStoreRetriever initialized from this VectorStore.

Parameters
  • 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]

Return docs most similar to query using specified search type.

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

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)

async asimilarity_search_with_score(*args: Any, **kwargs: Any) List[Tuple[Document, float]]

Run similarity search with distance asynchronously.

static connect_to_elasticsearch(*, es_url: Optional[str] = None, cloud_id: Optional[str] = None, api_key: Optional[str] = None, username: Optional[str] = None, password: Optional[str] = None, es_params: Optional[Dict[str, Any]] = None) Elasticsearch[source]
delete(ids: Optional[List[str]] = None, refresh_indices: Optional[bool] = True, **kwargs: Any) Optional[bool][source]

Delete documents from the Elasticsearch index.

Parameters
  • ids – List of ids of documents to delete.

  • refresh_indices – Whether to refresh the index after deleting documents. Defaults to True.

classmethod from_documents(documents: List[Document], embedding: Optional[Embeddings] = None, bulk_kwargs: Optional[Dict] = None, **kwargs: Any) ElasticsearchStore[source]

Construct ElasticsearchStore wrapper from documents.

Example

from langchain_community.vectorstores import ElasticsearchStore
from langchain_community.embeddings.openai import OpenAIEmbeddings

db = ElasticsearchStore.from_documents(
    texts,
    embeddings,
    index_name="langchain-demo",
    es_url="http://localhost:9200"
)
Parameters
  • texts – List of texts to add to the Elasticsearch index.

  • embedding – Embedding function to use to embed the texts. Do not provide if using a strategy that doesn’t require inference.

  • metadatas – Optional list of metadatas associated with the texts.

  • index_name – Name of the Elasticsearch index to create.

  • es_url – URL of the Elasticsearch instance to connect to.

  • cloud_id – Cloud ID of the Elasticsearch instance to connect to.

  • es_user – Username to use when connecting to Elasticsearch.

  • es_password – Password to use when connecting to Elasticsearch.

  • es_api_key – API key to use when connecting to Elasticsearch.

  • es_connection – Optional pre-existing Elasticsearch connection.

  • vector_query_field – Optional. Name of the field to store the embedding vectors in.

  • query_field – Optional. Name of the field to store the texts in.

  • bulk_kwargs – Optional. Additional arguments to pass to Elasticsearch bulk.

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

Construct ElasticsearchStore wrapper from raw documents.

Example

from langchain_community.vectorstores import ElasticsearchStore
from langchain_community.embeddings.openai import OpenAIEmbeddings

db = ElasticsearchStore.from_texts(
    texts,
    // embeddings optional if using
    // a strategy that doesn't require inference
    embeddings,
    index_name="langchain-demo",
    es_url="http://localhost:9200"
)
Parameters
  • texts – List of texts to add to the Elasticsearch index.

  • embedding – Embedding function to use to embed the texts.

  • metadatas – Optional list of metadatas associated with the texts.

  • index_name – Name of the Elasticsearch index to create.

  • es_url – URL of the Elasticsearch instance to connect to.

  • cloud_id – Cloud ID of the Elasticsearch instance to connect to.

  • es_user – Username to use when connecting to Elasticsearch.

  • es_password – Password to use when connecting to Elasticsearch.

  • es_api_key – API key to use when connecting to Elasticsearch.

  • es_connection – Optional pre-existing Elasticsearch connection.

  • vector_query_field – Optional. Name of the field to store the embedding vectors in.

  • query_field – Optional. Name of the field to store the texts in.

  • distance_strategy – Optional. Name of the distance strategy to use. Defaults to “COSINE”. can be one of “COSINE”, “EUCLIDEAN_DISTANCE”, “DOT_PRODUCT”.

  • bulk_kwargs – Optional. Additional arguments to pass to Elasticsearch bulk.

static get_user_agent() str[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.

  • fields – Other fields to get from elasticsearch source. These fields will be added to the document metadata.

Returns

A 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, **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.

Return Elasticsearch documents most similar to query.

Parameters
  • query – Text to look up documents similar to.

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

  • fetch_k (int) – Number of Documents to fetch to pass to knn num_candidates.

  • filter – Array of Elasticsearch filter clauses to apply to the query.

Returns

List of Documents most similar to the query, in descending order of similarity.

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_by_vector_with_relevance_scores(embedding: List[float], k: int = 4, filter: Optional[List[Dict]] = None, **kwargs: Any) List[Tuple[Document, float]][source]

Return Elasticsearch documents most similar to query, along with scores.

Parameters
  • embedding – Embedding to look up documents similar to.

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

  • filter – Array of Elasticsearch filter clauses to apply to the query.

Returns

List of Documents most similar to the embedding and score for each

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 = 4, filter: Optional[List[dict]] = None, **kwargs: Any) List[Tuple[Document, float]][source]

Return Elasticsearch documents most similar to query, along with scores.

Parameters
  • query – Text to look up documents similar to.

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

  • filter – Array of Elasticsearch filter clauses to apply to the query.

Returns

List of Documents most similar to the query and score for each

Examples using ElasticsearchStore