Back to Langflow

Weaviate

docs/versioned_docs/version-1.8.0/Components/bundles-weaviate.mdx

1.10.0.dev202.4 KB
Original Source

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

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

Weaviate vector store

The Weaviate component reads and writes to Weaviate vector stores using an instance of Weaviate vector store.

<details> <summary>About vector store instances</summary> <PartialVectorStoreInstance /> </details> <PartialVectorSearchResults />

:::tip For a tutorial using a vector database in a flow, see Create a vector RAG chatbot. :::

Weaviate 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 Weaviate documentation or inspect component code.

NameTypeDescription
weaviate_urlStringInput parameter. The default instance URL.
api_keySecretStringInput parameter. The optional API key for authentication.
index_nameStringInput parameter. The optional index name.
text_keyStringInput parameter. The default text extraction key.
inputData or DataFrameInput parameter. The document or record.
cache_vector_storeCache Vector StoreInput parameter. If true, the component caches the vector store in memory for faster reads. Default: Enabled (true).
embeddingEmbeddingsInput parameter. Connect an embedding model component.
number_of_resultsIntegerInput parameter. The number of search results to return. Default: 4.
search_by_textBooleanInput parameter. Indicates whether to search by text. Default: Disabled (false).