AsyncElasticsearchEmbeddings#

class langchain_elasticsearch.embeddings.AsyncElasticsearchEmbeddings(client: MlClient, model_id: str, *, input_field: str = 'text_field')[source]#

Initialize the ElasticsearchEmbeddings instance.

Parameters:

client (MlClient) – An Elasticsearch ML client object.
model_id (str) – The model_id of the model deployed in the Elasticsearch cluster.
input_field (str) – The name of the key for the input text field in the document. Defaults to ‘text_field’.

Methods

`__init__`(client, model_id, *[, input_field])	Initialize the ElasticsearchEmbeddings instance.
`aembed_documents`(texts)	Generate embeddings for a list of documents.
`aembed_query`(text)	Generate an embedding for a single query text.
`embed_documents`(texts)	Embed search docs.
`embed_query`(text)	Embed query text.
`from_credentials`(model_id, *[, es_cloud_id, ...])	Instantiate embeddings from Elasticsearch credentials.
`from_es_connection`(model_id, es_connection)	Instantiate embeddings from an existing Elasticsearch connection.

__init__(client: MlClient, model_id: str, *, input_field: str = 'text_field')[source]#

Initialize the ElasticsearchEmbeddings instance.

Parameters:

client (MlClient) – An Elasticsearch ML client object.
model_id (str) – The model_id of the model deployed in the Elasticsearch cluster.
input_field (str) – The name of the key for the input text field in the document. Defaults to ‘text_field’.

async aembed_documents(texts: List[str]) → List[List[float]][source]#

Generate embeddings for a list of documents.

Parameters:

texts (List[str]) – A list of document text strings to generate embeddings for.

Returns:

A list of embeddings, one for each document in the input: list.

Return type:

List[List[float]]

async aembed_query(text: str) → List[float][source]#

Generate an embedding for a single query text.

Parameters:: text (str) – The query text to generate an embedding for.
Returns:: The embedding for the input query text.
Return type:: List[float]

embed_documents(texts: List[str]) → List[List[float]][source]#

Embed search docs.

Parameters:: texts (List[str]) – List of text to embed.
Returns:: List of embeddings.
Return type:: List[List[float]]

embed_query(text: str) → List[float][source]#

Embed query text.

Parameters:: text (str) – Text to embed.
Returns:: Embedding.
Return type:: List[float]

classmethod from_credentials(model_id: str, *, es_cloud_id: str | None = None, es_api_key: str | None = None, input_field: str = 'text_field') → AsyncElasticsearchEmbeddings[source]#

Instantiate embeddings from Elasticsearch credentials.

Parameters:

model_id (str) – The model_id of the model deployed in the Elasticsearch cluster.
input_field (str) – The name of the key for the input text field in the document. Defaults to ‘text_field’.
es_cloud_id (str | None) – (str, optional): The Elasticsearch cloud ID to connect to.
es_user – (str, optional): Elasticsearch username.
es_password – (str, optional): Elasticsearch password.
es_api_key (str | None)

Return type:

AsyncElasticsearchEmbeddings

Example

from langchain_elasticserach.embeddings import ElasticsearchEmbeddings

# Define the model ID and input field name (if different from default)
model_id = "your_model_id"
# Optional, only if different from 'text_field'
input_field = "your_input_field"

# Credentials can be passed in two ways. Either set the env vars
# ES_CLOUD_ID, ES_USER, ES_PASSWORD and they will be automatically
# pulled in, or pass them in directly as kwargs.
embeddings = ElasticsearchEmbeddings.from_credentials(
    model_id,
    input_field=input_field,
    # es_cloud_id="foo",
    # es_user="bar",
    # es_password="baz",
)

documents = [
    "This is an example document.",
    "Another example document to generate embeddings for.",
]
embeddings_generator.embed_documents(documents)

classmethod from_es_connection(model_id: str, es_connection: AsyncElasticsearch, input_field: str = 'text_field') → AsyncElasticsearchEmbeddings[source]#

Instantiate embeddings from an existing Elasticsearch connection.

This method provides a way to create an instance of the ElasticsearchEmbeddings class using an existing Elasticsearch connection. The connection object is used to create an MlClient, which is then used to initialize the ElasticsearchEmbeddings instance.

Args: model_id (str): The model_id of the model deployed in the Elasticsearch cluster. es_connection (elasticsearch.Elasticsearch): An existing Elasticsearch connection object. input_field (str, optional): The name of the key for the input text field in the document. Defaults to ‘text_field’.

Returns: ElasticsearchEmbeddings: An instance of the ElasticsearchEmbeddings class.

Example

from elasticsearch import Elasticsearch

from langchain_elasticsearch.embeddings import ElasticsearchEmbeddings

# Define the model ID and input field name (if different from default)
model_id = "your_model_id"
# Optional, only if different from 'text_field'
input_field = "your_input_field"

# Create Elasticsearch connection
es_connection = Elasticsearch(
    hosts=["localhost:9200"], http_auth=("user", "password")
)

# Instantiate ElasticsearchEmbeddings using the existing connection
embeddings = ElasticsearchEmbeddings.from_es_connection(
    model_id,
    es_connection,
    input_field=input_field,
)

documents = [
    "This is an example document.",
    "Another example document to generate embeddings for.",
]
embeddings_generator.embed_documents(documents)

Parameters:

model_id (str)
es_connection (AsyncElasticsearch)
input_field (str)

Return type:

AsyncElasticsearchEmbeddings