Elastic

Bundles contain custom components that support specific third-party integrations with Langflow.

This page describes the components that are available in the Elastic bundle.

Elasticsearch

The Elasticsearch component reads and writes to an Elasticsearch instance using ElasticsearchStore.

About vector store instances

Because Langflow is based on LangChain, vector store components use an instance of LangChain vector store to drive the underlying read and write functions. These instances are provider-specific and configured according to the component's parameters, such as the connection string, index name, and schema.

In component code, this is often instantiated as vector_store, but some vector store components use a different name, such as the provider name.

Some LangChain classes don't expose all possible options as component parameters. Depending on the provider, these options might use default values or allow modification through environment variables, if they are supported in Langflow. For information about specific options, see the LangChain API reference and vector store provider's documentation.

If you use a vector store component to query your vector database, it produces search results that you can pass to downstream components in your flow as a list of Data objects or a tabular DataFrame. If both types are supported, you can set the format near the vector store component's output port in the visual editor.

Elasticsearch parameters

You can inspect a vector store component's parameters to learn more about the inputs it accepts, the features it supports, and how to configure it.

Some parameters are hidden by default in the visual editor. You can modify all parameters through the Controls in the component's header menu.

Some parameters are conditional, and they are only available after you set other parameters or select specific options for other parameters. Conditional parameters may not be visible on the Controls pane until you set the required dependencies.

For information about accepted values and functionality, see the Elasticsearch documentation or inspect component code.

Name	Type	Description
elasticsearch_url	String	Input parameter. Elasticsearch server URL.
cloud_id	String	Input parameter. Elasticsearch Cloud ID.
index_name	String	Input parameter. Name of the Elasticsearch index.
ingest_data	Data	Input parameter. Records to load into the vector store.
search_query	String	Input parameter. Query string for similarity search.
cache_vector_store	Boolean	Input parameter. If true, the component caches the vector store in memory for faster reads. Default: Enabled (true).
username	String	Input parameter. Username for Elasticsearch authentication. Required for all local deployments. Required for cloud deployments if api_key is empty.
password	SecretString	Input parameter. Password for Elasticsearch authentication. Required for all local deployments. Required for cloud deployments if api_key is empty
embedding	Embeddings	Input parameter. The embedding model to use.
search_type	String	Input parameter. The type of search to perform. Options are similarity (default) or mmr.
number_of_results	Integer	Input parameter. Number of search results to return. Default: 4.
search_score_threshold	Float	Input parameter. The minimum similarity score threshold for search results. Default: 0.
api_key	SecretString	Input parameter. API key for Elastic Cloud authentication. If provided, username and password aren't required.
verify_certs	Boolean	Input parameter. Whether to verify SSL certificates when connecting to Elasticsearch. Default: Enabled (true).

OpenSearch

The OpenSearch component reads and writes to OpenSearch instances using OpenSearchVectorSearch.

About vector store instances

Because Langflow is based on LangChain, vector store components use an instance of LangChain vector store to drive the underlying read and write functions. These instances are provider-specific and configured according to the component's parameters, such as the connection string, index name, and schema.

In component code, this is often instantiated as vector_store, but some vector store components use a different name, such as the provider name.

Some LangChain classes don't expose all possible options as component parameters. Depending on the provider, these options might use default values or allow modification through environment variables, if they are supported in Langflow. For information about specific options, see the LangChain API reference and vector store provider's documentation.

OpenSearch parameters

You can inspect a vector store component's parameters to learn more about the inputs it accepts, the features it supports, and how to configure it.;

Some parameters are hidden by default in the visual editor. You can modify all parameters through the Controls in the component's header menu.

Some parameters are conditional, and they are only available after you set other parameters or select specific options for other parameters. Conditional parameters may not be visible on the Controls pane until you set the required dependencies.

For information about accepted values and functionality, see the OpenSearch documentation or inspect component code.

Name	Type	Description
opensearch_url	String	Input parameter. URL for OpenSearch cluster, such as https://192.168.1.1:9200.
index_name	String	Input parameter. The index name where the vectors are stored in OpenSearch cluster. Default: langflow.
ingest_data	Data	Input parameter. The data to be ingested into the vector store.
search_input	String	Input parameter. Enter a search query. Leave empty to retrieve all documents or if hybrid search is being used.
cache_vector_store	Boolean	Input parameter. If true, the component caches the vector store in memory for faster reads. Default: Enabled (true).
embedding	Embeddings	Input parameter. Attach an embedding model component to use to generate an embedding from the search query.
search_type	String	Input parameter. The type of search to perform. Options are similarity (default), similarity_score_threshold, mmr.
number_of_results	Integer	Input parameter. The number of results to return in search. Default: 4.
search_score_threshold	Float	Input parameter. The minimum similarity score threshold for search results. Default: 0.
username	String	Input parameter. The username for the OpenSearch cluster. Default: admin.
password	SecretString	Input parameter. The password for the OpenSearch cluster.
use_ssl	Boolean	Input parameter. Whether to use SSL. Default: Enabled (true).
verify_certs	Boolean	Input parameter. Whether to verify SSL certificates. Default: Disabled (false).
hybrid_search_query	String	Input parameter. Provide a custom hybrid search query in JSON format. This allows you to combine vector similarity and keyword matching.

OpenSearch output

If you use a vector store component to query your vector database, it produces search results that you can pass to downstream components in your flow as a list of Data objects or a tabular DataFrame. If both types are supported, you can set the format near the vector store component's output port in the visual editor.

Vector Store Connection port

The OpenSearch component has an additional deprecated Vector Store Connection output. This output can only connect to a VectorStore input port, and it was intended for use with dedicated Graph RAG components.

The OpenSearch component doesn't require a separate Graph RAG component because OpenSearch instances support Graph traversal through built-in RAG functionality and plugins.