mirror of
https://github.com/langflow-ai/langflow.git
synced 2026-07-25 04:10:28 +08:00
b36444f5d9
* fix: nightly now properly gets 1.9.0 branch (#12215) before it was attempting to pull release-notes as letters are alphanumerically after numbers when we sort -V then grab tail now we only look at branch names that follow the pattern '^release-[0-9]+\.[0-9]+\.[0-9]+$' * docs: add search icon (#12216) add-back-svg * initial-content * cut-1.8-release-and-include-next-version * stage-1.8.0-and-next --------- Co-authored-by: Adam-Aghili <149833988+Adam-Aghili@users.noreply.github.com>
107 lines
6.1 KiB
Plaintext
107 lines
6.1 KiB
Plaintext
---
|
|
title: Elastic
|
|
slug: /bundles-elastic
|
|
---
|
|
|
|
import Icon from "@site/src/components/icon";
|
|
import PartialParams from '@site/docs/_partial-hidden-params.mdx';
|
|
import PartialConditionalParams from '@site/docs/_partial-conditional-params.mdx';
|
|
import PartialVectorSearchResults from '@site/docs/_partial-vector-search-results.mdx';
|
|
import PartialVectorStoreInstance from '@site/docs/_partial-vector-store-instance.mdx';
|
|
|
|
<Icon name="Blocks" aria-hidden="true" /> [**Bundles**](/components-bundle-components) 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`](https://docs.langchain.com/oss/python/integrations/vectorstores/elasticsearch).
|
|
|
|
<details>
|
|
<summary>About vector store instances</summary>
|
|
|
|
<PartialVectorStoreInstance />
|
|
|
|
</details>
|
|
|
|
<PartialVectorSearchResults />
|
|
|
|
### 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.
|
|
|
|
<PartialParams />
|
|
|
|
<PartialConditionalParams />
|
|
|
|
For information about accepted values and functionality, see the [Elasticsearch documentation](https://www.elastic.co/guide/en/elasticsearch/reference/current/dense-vector.html) or inspect [component code](/concepts-components#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`](https://docs.langchain.com/oss/python/integrations/vectorstores/opensearch).
|
|
|
|
<details>
|
|
<summary>About vector store instances</summary>
|
|
|
|
<PartialVectorStoreInstance />
|
|
|
|
</details>
|
|
|
|
### 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.;
|
|
|
|
<PartialParams />
|
|
|
|
<PartialConditionalParams />
|
|
|
|
For information about accepted values and functionality, see the [OpenSearch documentation](https://opensearch.org/platform/search/vector-database.html) or inspect [component code](/concepts-components#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](/components-embedding-models) 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
|
|
|
|
<PartialVectorSearchResults />
|
|
|
|
<details>
|
|
<summary>Vector Store Connection port</summary>
|
|
|
|
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.
|
|
|
|
</details>
|