Skip to main content

Vector store components in Langflow

Vector databases store vector data, which backs AI workloads like chatbots and Retrieval Augmented Generation.

Vector database components establish connections to existing vector databases or create in-memory vector stores for storing and retrieving vector data.

Vector database components are distinct from memory components, which are built specifically for storing and retrieving chat messages from external databases.

Use a vector store component in a flow

This example uses the Astra DB vector store component. Your vector store component's parameters and authentication may be different, but the document ingestion workflow is the same. A document is loaded from a local machine and chunked. The Astra DB vector store generates embeddings with the connected model component, and stores them in the connected Astra DB database.

This vector data can then be retrieved for workloads like Retrieval Augmented Generation.

The user's chat input is embedded and compared to the vectors embedded during document ingestion for a similarity search. The results are output from the vector database component as a Data object and parsed into text. This text fills the {context} variable in the Prompt component, which informs the Open AI model component's responses.

Alternatively, connect the vector database component's Retriever port to a retriever tool, and then to an agent component. This enables the agent to use your vector database as a tool and make decisions based on the available data.

Astra DB Vector Store

This component implements a Vector Store using Astra DB with search capabilities.

For more information, see the DataStax documentation.

Parameters

Inputs

NameDisplay NameInfo
tokenAstra DB Application TokenThe authentication token for accessing Astra DB.
environmentEnvironmentThe environment for the Astra DB API Endpoint. For example, dev or prod.
database_nameDatabaseThe database name for the Astra DB instance.
api_endpointAstra DB API EndpointThe API endpoint for the Astra DB instance. This supersedes the database selection.
collection_nameCollectionThe name of the collection within Astra DB where the vectors are stored.
keyspaceKeyspaceAn optional keyspace within Astra DB to use for the collection.
embedding_choiceEmbedding Model or Astra VectorizeChoose an embedding model or use Astra vectorize.
embedding_modelEmbedding ModelSpecify the embedding model. Not required for Astra vectorize collections.
number_of_resultsNumber of Search ResultsThe number of search results to return. Default:4.
search_typeSearch TypeThe search type to use. The options are Similarity, Similarity with score threshold, and MMR (Max Marginal Relevance).
search_score_thresholdSearch Score ThresholdThe minimum similarity score threshold for search results when using the Similarity with score threshold option.
advanced_search_filterSearch Metadata FilterAn optional dictionary of filters to apply to the search query.
autodetect_collectionAutodetect CollectionA boolean flag to determine whether to autodetect the collection.
content_fieldContent FieldA field to use as the text content field for the vector store.
deletion_fieldDeletion Based On FieldWhen provided, documents in the target collection with metadata field values matching the input metadata field value are deleted before new data is loaded.
ignore_invalid_documentsIgnore Invalid DocumentsA boolean flag to determine whether to ignore invalid documents at runtime.
astradb_vectorstore_kwargsAstraDBVectorStore ParametersAn optional dictionary of additional parameters for the AstraDBVectorStore.

Outputs

NameDisplay NameInfo
vector_storeVector StoreThe Astra DB vector store instance configured with the specified parameters.
search_resultsSearch ResultsThe results of the similarity search as a list of Data objects.

Generate embeddings

The Astra DB Vector Store component offers two methods for generating embeddings.

  1. Embedding Model: Use your own embedding model by connecting an Embeddings component in Langflow.

  2. Astra Vectorize: Use Astra DB's built-in embedding generation service. When creating a new collection, choose the embeddings provider and models, including NVIDIA's NV-Embed-QA model hosted by Datastax.

important

The embedding model selection is made when creating a new collection and cannot be changed later.

For an example of using the Astra DB Vector Store component with an embedding model, see the Vector Store RAG starter project.

For more information, see the Astra DB Serverless documentation.

The Astra DB component includes hybrid search, which is enabled by default.

The component fields related to hybrid search are Search Query, Lexical Terms, and Reranker.

  • Search Query finds results by vector similarity.
  • Lexical Terms is a comma-separated string of keywords, like features, data, attributes, characteristics.
  • Reranker is the re-ranker model used in the hybrid search. The re-ranker model is nvidia/llama-3.2-nv.reranker.

Hybrid search performs a vector similarity search and a lexical search, compares the results of both searches, and then returns the most relevant results overall.

important

To use hybrid search, your collection must be created with vector, lexical, and rerank capabilities enabled. These capabilities are enabled by default when you create a collection in a database in the AWS us-east-2 region. For more information, see the DataStax documentation.

To use Hybrid search in the Astra DB component, do the following:

  1. Click New Flow > RAG > Hybrid Search RAG.
  2. In the OpenAI model component, add your OpenAI API key.
  3. In the Astra DB vector store component, add your Astra DB Application Token.
  4. In the Database field, select your database.
  5. In the Collection field, select or create a collection with hybrid search capabilities enabled.
  6. In the Playground, enter a question about your data, such as What are the features of my data? Your query is sent to two components: an OpenAI model component and the Astra DB vector database component. The OpenAI component contains a prompt for creating the lexical query from your input:

_10
You are a database query planner that takes a user's requests, and then converts to a search against the subject matter in question.
_10
You should convert the query into:
_10
1. A list of keywords to use against a Lucene text analyzer index, no more than 4. Strictly unigrams.
_10
2. A question to use as the basis for a QA embedding engine.
_10
Avoid common keywords associated with the user's subject matter.

  1. To view the keywords and questions the OpenAI component generates from your collection, in the OpenAI component, click .

_10
1. Keywords: features, data, attributes, characteristics
_10
2. Question: What characteristics can be identified in my data?

  1. To view the DataFrame generated from the OpenAI component's response, in the Structured Output component, click . The DataFrame is passed to a Parser component, which parses the contents of the Keywords column into a string.

    This string of comma-separated words is passed to the Lexical Terms port of the Astra DB component. Note that the Search Query port of the Astra DB port is connected to the Chat Input component from step 6. This Search Query is vectorized, and both the Search Query and Lexical Terms content are sent to the reranker at the find_and_rerank endpoint.

    The reranker compares the vector search results against the string of terms from the lexical search. The highest-ranked results of your hybrid search are returned to the Playground.

For more information, see the DataStax documentation.

AstraDB Graph vector store

This component implements a Vector Store using AstraDB with graph capabilities. For more information, see the Astra DB Serverless documentation.

Parameters

Inputs

NameDisplay NameInfo
collection_nameCollection NameThe name of the collection within AstraDB where the vectors are stored. Required.
tokenAstra DB Application TokenAuthentication token for accessing AstraDB. Required.
api_endpointAPI EndpointAPI endpoint URL for the AstraDB service. Required.
search_inputSearch InputQuery string for similarity search.
ingest_dataIngest DataData to be ingested into the vector store.
namespaceNamespaceOptional namespace within AstraDB to use for the collection.
embeddingEmbedding ModelEmbedding model to use.
metricMetricDistance metric for vector comparisons. The options are "cosine", "euclidean", "dot_product".
setup_modeSetup ModeConfiguration mode for setting up the vector store. The options are "Sync", "Async", "Off".
pre_delete_collectionPre Delete CollectionBoolean flag to determine whether to delete the collection before creating a new one.
number_of_resultsNumber of ResultsNumber of results to return in similarity search. Default: 4.
search_typeSearch TypeSearch type to use. The options are "Similarity", "Graph Traversal", "Hybrid".
traversal_depthTraversal DepthMaximum depth for graph traversal searches. Default: 1.
search_score_thresholdSearch Score ThresholdMinimum similarity score threshold for search results.
search_filterSearch Metadata FilterOptional dictionary of filters to apply to the search query.

Outputs

NameDisplay NameInfo
vector_storeVector StoreThe Graph RAG vector store instance configured with the specified parameters.
search_resultsSearch ResultsThe results of the similarity search as a list of Data objects.

Cassandra

This component creates a Cassandra Vector Store with search capabilities. For more information, see the Cassandra documentation.

Parameters

Inputs

NameTypeDescription
database_refStringContact points for the database or AstraDB database ID.
usernameStringUsername for the database (leave empty for AstraDB).
tokenSecretStringUser password for the database or AstraDB token.
keyspaceStringTable Keyspace or AstraDB namespace.
table_nameStringName of the table or AstraDB collection.
ttl_secondsIntegerTime-to-live for added texts.
batch_sizeIntegerNumber of data to process in a single batch.
setup_modeStringConfiguration mode for setting up the Cassandra table.
cluster_kwargsDictAdditional keyword arguments for the Cassandra cluster.
search_queryStringQuery for similarity search.
ingest_dataDataData to be ingested into the vector store.
embeddingEmbeddingsEmbedding function to use.
number_of_resultsIntegerNumber of results to return in search.
search_typeStringType of search to perform.
search_score_thresholdFloatMinimum similarity score for search results.
search_filterDictMetadata filters for search query.
body_searchStringDocument textual search terms.
enable_body_searchBooleanFlag to enable body search.

Outputs

NameTypeDescription
vector_storeCassandraThe Cassandra vector store instance configured with the specified parameters.
search_resultsList[Data]The results of the similarity search as a list of Data objects.

Cassandra Graph Vector Store

This component implements a Cassandra Graph Vector Store with search capabilities.

Parameters

Inputs

NameDisplay NameInfo
database_refContact Points / Astra Database IDThe contact points for the database or AstraDB database ID. Required.
usernameUsernameThe username for the database. Leave this field empty for AstraDB.
tokenPassword / AstraDB TokenThe user password for the database or AstraDB token. Required.
keyspaceKeyspaceThe table Keyspace or AstraDB namespace. Required.
table_nameTable NameThe name of the table or AstraDB collection where vectors are stored. Required.
setup_modeSetup ModeThe configuration mode for setting up the Cassandra table. The options are "Sync" or "Off". Default: "Sync".
cluster_kwargsCluster argumentsAn optional dictionary of additional keyword arguments for the Cassandra cluster.
search_querySearch QueryThe query string for similarity search.
ingest_dataIngest DataThe list of data to be ingested into the vector store.
embeddingEmbeddingThe embedding model to use.
number_of_resultsNumber of ResultsThe number of results to return in similarity search. Default: 4.
search_typeSearch TypeThe search type to use. The options are "Traversal", "MMR traversal", "Similarity", "Similarity with score threshold", or "MMR (Max Marginal Relevance)". Default: "Traversal".
depthDepth of traversalThe maximum depth of edges to traverse. Used for "Traversal" or "MMR traversal" search types. Default: 1.
search_score_thresholdSearch Score ThresholdThe minimum similarity score threshold for search results. Used for "Similarity with score threshold" search types.
search_filterSearch Metadata FilterAn optional dictionary of filters to apply to the search query.

Outputs

NameDisplay NameInfo
vector_storeVector StoreThe Cassandra Graph vector store instance configured with the specified parameters.
search_resultsSearch ResultsThe results of the similarity search as a list of Data objects.

Chroma DB

This component creates a Chroma Vector Store with search capabilities.

The Chroma DB component creates an ephemeral vector database for experimentation and vector storage.

  1. To use this component in a flow, connect it to a component that outputs Data or DataFrame. This example splits text from a URL component, and computes embeddings with the connected OpenAI Embeddings component. Chroma DB computes embeddings by default, but you can connect your own embeddings model, as seen in this example.

ChromaDB receiving split text

  1. In the Chroma DB component, in the Collection field, enter a name for your embeddings collection.
  2. Optionally, to persist the Chroma database, in the Persist field, enter a directory to store the chroma.sqlite3 file. This example uses ./chroma-db to create a directory relative to where Langflow is running.
  3. To load data and embeddings into your Chroma database, in the Chroma DB component, click .
tip

When loading duplicate documents, enable the Allow Duplicates option in Chroma DB if you want to store multiple copies of the same content, or disable it to automatically deduplicate your data.

  1. To view the split data, in the Split Text component, click .
  2. To query your loaded data, open the Playground and query your database. Your input is converted to vector data and compared to the stored vectors in a vector similarity search.

For more information, see the Chroma documentation.

Parameters

Inputs

NameTypeDescription
collection_nameStringThe name of the Chroma collection. Default: "langflow".
persist_directoryStringThe directory to persist the Chroma database.
search_queryStringThe query to search for in the vector store.
ingest_dataDataThe data to ingest into the vector store (list of Data objects).
embeddingEmbeddingsThe embedding function to use for the vector store.
chroma_server_cors_allow_originsStringThe CORS allow origins for the Chroma server.
chroma_server_hostStringThe host for the Chroma server.
chroma_server_http_portIntegerThe HTTP port for the Chroma server.
chroma_server_grpc_portIntegerThe gRPC port for the Chroma server.
chroma_server_ssl_enabledBooleanEnable SSL for the Chroma server.
allow_duplicatesBooleanAllow duplicate documents in the vector store.
search_typeStringThe type of search to perform: "Similarity" or "MMR".
number_of_resultsIntegerThe number of results to return from the search. Default: 10.
limitIntegerThe limit of the number of records to compare when Allow Duplicates is False.

Outputs

NameTypeDescription
vector_storeChromaThe Chroma vector store instance.
search_resultsList[Data]The results of the similarity search as a list of Data objects.

Clickhouse

This component implements a Clickhouse Vector Store with search capabilities. For more information, see the Clickhouse Documentation.

Parameters

Inputs

NameDisplay NameInfo
hosthostnameThe Clickhouse server hostname. Required. Default: "localhost".
portportThe Clickhouse server port. Required. Default: 8123.
databasedatabaseThe Clickhouse database name. Required.
tableTable nameThe Clickhouse table name. Required.
usernameThe ClickHouse user name.Username for authentication. Required.
passwordThe password for username.Password for authentication. Required.
index_typeindex_typeType of the index. The options are "annoy" and "vector_similarity". Default: "annoy".
metricmetricMetric to compute distance. The options are "angular", "euclidean", "manhattan", "hamming", "dot". Default: "angular".
secureUse https/TLSOverrides inferred values from the interface or port arguments. Default: false.
index_paramParam of the indexIndex parameters. Default: "'L2Distance',100".
index_query_paramsindex query paramsAdditional index query parameters.
search_querySearch QueryThe query string for similarity search.
ingest_dataIngest DataThe data to be ingested into the vector store.
embeddingEmbeddingThe embedding model to use.
number_of_resultsNumber of ResultsThe number of results to return in similarity search. Default: 4.
score_thresholdScore thresholdThe threshold for similarity scores.

Outputs

NameDisplay NameInfo
vector_storeVector StoreThe Clickhouse vector store.
search_resultsSearch ResultsThe results of the similarity search as a list of Data objects.

Couchbase

This component creates a Couchbase Vector Store with search capabilities. For more information, see the Couchbase documentation.

Parameters

Inputs

NameTypeDescription
couchbase_connection_stringSecretStringCouchbase Cluster connection string. Required.
couchbase_usernameStringCouchbase username. Required.
couchbase_passwordSecretStringCouchbase password. Required.
bucket_nameStringName of the Couchbase bucket. Required.
scope_nameStringName of the Couchbase scope. Required.
collection_nameStringName of the Couchbase collection. Required.
index_nameStringName of the Couchbase index. Required.
search_queryStringThe query to search for in the vector store.
ingest_dataDataThe list of data to ingest into the vector store.
embeddingEmbeddingsThe embedding function to use for the vector store.
number_of_resultsIntegerNumber of results to return from the search. Default: 4.

Outputs

NameTypeDescription
vector_storeCouchbaseVectorStoreA Couchbase vector store instance configured with the specified parameters.

Local DB

The Local DB component is Langflow's enhanced version of Chroma DB.

The component adds a user-friendly interface with two modes (Ingest and Retrieve), automatic collection management, and built-in persistence in Langflow's cache directory.

Local DB includes Ingest and Retrieve modes.

The Ingest mode works similarly to ChromaDB, and persists your database to the Langflow cache directory. The Langflow cache directory location is specified in LANGFLOW_CONFIG_DIR. For more information, see Environment variables.

The Retrieve mode can query your Chroma DB collections.

Local DB retrieving vectors

For more information, see the Chroma documentation.

Parameters

Inputs

NameTypeDescription
collection_nameStringThe name of the Chroma collection. Default: "langflow".
persist_directoryStringCustom base directory to save the vector store. Collections are stored under {directory}/vector_stores/{collection_name}. If not specified, it will use your system's cache folder.
existing_collectionsStringSelect a previously created collection to search through its stored data.
embeddingEmbeddingsThe embedding function to use for the vector store.
allow_duplicatesBooleanIf false, will not add documents that are already in the Vector Store.
search_typeStringType of search to perform: "Similarity" or "MMR".
ingest_dataData/DataFrameData to store. It is embedded and indexed for semantic search.
search_queryStringEnter text to search for similar content in the selected collection.
number_of_resultsIntegerNumber of results to return. Default: 10.
limitIntegerLimit the number of records to compare when Allow Duplicates is False.

Outputs

NameTypeDescription
vector_storeChromaA local Chroma vector store instance configured with the specified parameters.
search_resultsListDataThe results of the similarity search as a list of Data objects.

Elasticsearch

This component creates an Elasticsearch Vector Store with search capabilities. For more information, see the Elasticsearch documentation.

Parameters

Inputs

NameTypeDescription
es_urlStringElasticsearch server URL.
es_userStringUsername for Elasticsearch authentication.
es_passwordSecretStringPassword for Elasticsearch authentication.
index_nameStringName of the Elasticsearch index.
strategyStringStrategy for vector search. The options are "approximate_k_nearest_neighbors" or "script_scoring".
distance_strategyStringStrategy for distance calculation. The options are "COSINE", "EUCLIDEAN_DISTANCE", or "DOT_PRODUCT".
search_queryStringQuery for similarity search.
ingest_dataDataData to be ingested into the vector store.
embeddingEmbeddingsEmbedding function to use.
number_of_resultsIntegerNumber of results to return in search. Default: 4.

Outputs

NameTypeDescription
vector_storeElasticsearchStoreThe Elasticsearch vector store instance.
search_resultsList[Data]The results of the similarity search as a list of Data objects.

FAISS

This component creates a FAISS Vector Store with search capabilities. For more information, see the FAISS documentation.

Parameters

Inputs

NameTypeDescription
index_nameStringThe name of the FAISS index. Default: "langflow_index".
persist_directoryStringPath to save the FAISS index. It is relative to where Langflow is running.
search_queryStringThe query to search for in the vector store.
ingest_dataDataThe list of data to ingest into the vector store.
allow_dangerous_deserializationBooleanSet to True to allow loading pickle files from untrusted sources. Default: True.
embeddingEmbeddingsThe embedding function to use for the vector store.
number_of_resultsIntegerNumber of results to return from the search. Default: 4.

Outputs

NameDisplay NameInfo
vector_storeVector StoreThe FAISS vector store instance configured with the specified parameters.
search_resultsSearch ResultsThe results of the similarity search as a list of Data objects.

Graph RAG

This component performs Graph RAG (Retrieval Augmented Generation) traversal in a vector store, enabling graph-based document retrieval. For more information, see the Graph RAG documentation.

For an example flow, see the Graph RAG template.

Parameters

Inputs

NameDisplay NameInfo
embedding_modelEmbedding ModelSpecify the embedding model. This is not required for collections embedded with Astra vectorize.
vector_storeVector Store ConnectionConnection to the vector store.
edge_definitionEdge DefinitionEdge definition for the graph traversal. For more information, see the GraphRAG documentation.
strategyTraversal StrategiesThe strategy to use for graph traversal. Strategy options are dynamically loaded from available strategies.
search_querySearch QueryThe query to search for in the vector store.
graphrag_strategy_kwargsStrategy ParametersOptional dictionary of additional parameters for the retrieval strategy. For more information, see the strategy documentation.

Outputs

NameTypeDescription
search_resultsList[Data]Results of the graph-based document retrieval as a list of Data objects.

Hyper-Converged Database (HCD)

This component implements a Vector Store using HCD.

To use the HCD vector store, add your deployment's collection name, username, password, and HCD Data API endpoint. The endpoint must be formatted like http[s]://**DOMAIN_NAME** or **IP_ADDRESS**[:port], for example, http://192.0.2.250:8181.

Replace DOMAIN_NAME or IP_ADDRESS with the domain name or IP address of your HCD Data API connection.

To use the HCD vector store for embeddings ingestion, connect it to an embeddings model and a file loader:

HCD vector store embeddings ingestion

Parameters

Inputs

NameDisplay NameInfo
collection_nameCollection NameThe name of the collection within HCD where the vectors will be stored. Required.
usernameHCD UsernameAuthentication username for accessing HCD. Default is "hcd-superuser". Required.
passwordHCD PasswordAuthentication password for accessing HCD. Required.
api_endpointHCD API EndpointAPI endpoint URL for the HCD service. Required.
search_inputSearch InputQuery string for similarity search.
ingest_dataIngest DataData to be ingested into the vector store.
namespaceNamespaceOptional namespace within HCD to use for the collection. Default is "default_namespace".
ca_certificateCA CertificateOptional CA certificate for TLS connections to HCD.
metricMetricOptional distance metric for vector comparisons. Options are "cosine", "dot_product", "euclidean".
batch_sizeBatch SizeOptional number of data to process in a single batch.
bulk_insert_batch_concurrencyBulk Insert Batch ConcurrencyOptional concurrency level for bulk insert operations.
bulk_insert_overwrite_concurrencyBulk Insert Overwrite ConcurrencyOptional concurrency level for bulk insert operations that overwrite existing data.
bulk_delete_concurrencyBulk Delete ConcurrencyOptional concurrency level for bulk delete operations.
setup_modeSetup ModeConfiguration mode for setting up the vector store. Options are "Sync", "Async", "Off". Default is "Sync".
pre_delete_collectionPre Delete CollectionBoolean flag to determine whether to delete the collection before creating a new one.
metadata_indexing_includeMetadata Indexing IncludeOptional list of metadata fields to include in the indexing.
embeddingEmbedding or Astra VectorizeAllows either an embedding model or an Astra Vectorize configuration.
metadata_indexing_excludeMetadata Indexing ExcludeOptional list of metadata fields to exclude from the indexing.
collection_indexing_policyCollection Indexing PolicyOptional dictionary defining the indexing policy for the collection.
number_of_resultsNumber of ResultsNumber of results to return in similarity search. Default is 4.
search_typeSearch TypeSearch type to use. Options are "Similarity", "Similarity with score threshold", "MMR (Max Marginal Relevance)". Default is "Similarity".
search_score_thresholdSearch Score ThresholdMinimum similarity score threshold for search results. Default is 0.
search_filterSearch Metadata FilterOptional dictionary of filters to apply to the search query.

Outputs

NameTypeDescription
vector_storeHyperConvergedDatabaseVectorStoreThe HCD vector store instance.
search_resultsList[Data]The results of the similarity search as a list of Data objects.

Milvus

This component creates a Milvus Vector Store with search capabilities. For more information, see the Milvus documentation.

Parameters

Inputs

NameTypeDescription
collection_nameStringName of the Milvus collection.
collection_descriptionStringDescription of the Milvus collection.
uriStringConnection URI for Milvus.
passwordSecretStringPassword for Milvus.
usernameSecretStringUsername for Milvus.
batch_sizeIntegerNumber of data to process in a single batch.
search_queryStringQuery for similarity search.
ingest_dataDataData to be ingested into the vector store.
embeddingEmbeddingsEmbedding function to use.
number_of_resultsIntegerNumber of results to return in search.
search_typeStringType of search to perform.
search_score_thresholdFloatMinimum similarity score for search results.
search_filterDictMetadata filters for search query.
setup_modeStringConfiguration mode for setting up the vector store.
vector_dimensionsIntegerNumber of dimensions of the vectors.
pre_delete_collectionBooleanWhether to delete the collection before creating a new one.

Outputs

NameTypeDescription
vector_storeMilvusA Milvus vector store instance configured with the specified parameters.

MongoDB Atlas

This component creates a MongoDB Atlas Vector Store with search capabilities. For more information, see the MongoDB Atlas documentation.

Parameters

Inputs

NameTypeDescription
mongodb_atlas_cluster_uriSecretStringThe connection URI for your MongoDB Atlas cluster. Required.
enable_mtlsBooleanEnable mutual TLS authentication. Default: false.
mongodb_atlas_client_certSecretStringClient certificate combined with private key for mTLS authentication. Required if mTLS is enabled.
db_nameStringThe name of the database to use. Required.
collection_nameStringThe name of the collection to use. Required.
index_nameStringThe name of the Atlas Search index, it should be a Vector Search. Required.
insert_modeStringHow to insert new documents into the collection. The options are "append" or "overwrite". Default: "append".
embeddingEmbeddingsThe embedding model to use.
number_of_resultsIntegerNumber of results to return in similarity search. Default: 4.
index_fieldStringThe field to index. Default: "embedding".
filter_fieldStringThe field to filter the index.
number_dimensionsIntegerEmbedding context length. Default: 1536.
similarityStringThe method used to measure similarity between vectors. The options are "cosine", "euclidean", or "dotProduct". Default: "cosine".
quantizationStringQuantization reduces memory costs by converting 32-bit floats to smaller data types. The options are "scalar" or "binary".

Outputs

NameTypeDescription
vector_storeMongoDBAtlasVectorSearchThe MongoDB Atlas vector store instance.
search_resultsList[Data]The results of the similarity search as a list of Data objects.

Opensearch

This component creates an Opensearch vector store with search capabilities For more information, see Opensearch documentation.

Parameters

Inputs

NameTypeDescription
opensearch_urlStringURL for OpenSearch cluster, such as https://192.168.1.1:9200.
index_nameStringThe index name where the vectors are stored in OpenSearch cluster.
search_inputStringEnter a search query. Leave empty to retrieve all documents or if hybrid search is being used.
ingest_dataDataThe data to be ingested into the vector store.
embeddingEmbeddingsThe embedding function to use.
search_typeStringThe options are "similarity", "similarity_score_threshold", "mmr".
number_of_resultsIntegerThe number of results to return in search.
search_score_thresholdFloatThe minimum similarity score threshold for search results.
usernameStringThe username for the opensource cluster.
passwordSecretStringThe password for the opensource cluster.
use_sslBooleanUse SSL.
verify_certsBooleanVerify certificates.
hybrid_search_queryStringProvide a custom hybrid search query in JSON format. This allows you to combine vector similarity and keyword matching.

Outputs

NameTypeDescription
vector_storeOpenSearchVectorSearchOpenSearch vector store instance
search_resultsList[Data]The results of the similarity search as a list of Data objects.

PGVector

This component creates a PGVector Vector Store with search capabilities. For more information, see the PGVector documentation.

Parameters

Inputs

NameTypeDescription
pg_server_urlSecretStringThe PostgreSQL server connection string.
collection_nameStringThe table name for the vector store.
search_queryStringThe query for similarity search.
ingest_dataDataThe data to be ingested into the vector store.
embeddingEmbeddingsThe embedding function to use.
number_of_resultsIntegerThe number of results to return in search.

Outputs

NameDisplay NameInfo
vector_storeVector StoreThe PGVector vector store instance configured with the specified parameters.
search_resultsSearch ResultsThe results of the similarity search as a list of Data objects.

Pinecone

This component creates a Pinecone Vector Store with search capabilities. For more information, see the Pinecone documentation.

Parameters

Inputs

NameTypeDescription
index_nameStringThe name of the Pinecone index.
namespaceStringThe namespace for the index.
distance_strategyStringThe strategy for calculating distance between vectors.
pinecone_api_keySecretStringThe API key for Pinecone.
text_keyStringThe key in the record to use as text.
search_queryStringThe query for similarity search.
ingest_dataDataThe data to be ingested into the vector store.
embeddingEmbeddingsThe embedding function to use.
number_of_resultsIntegerThe number of results to return in search.

Outputs

NameDisplay NameInfo
vector_storeVector StoreThe Pinecone vector store instance configured with the specified parameters.
search_resultsSearch ResultsThe results of the similarity search as a list of Data objects.

Qdrant

This component creates a Qdrant Vector Store with search capabilities. For more information, see the Qdrant documentation.

Parameters

Inputs

NameTypeDescription
collection_nameStringThe name of the Qdrant collection.
hostStringThe Qdrant server host.
portIntegerThe Qdrant server port.
grpc_portIntegerThe Qdrant gRPC port.
api_keySecretStringThe API key for Qdrant.
prefixStringThe prefix for Qdrant.
timeoutIntegerThe timeout for Qdrant operations.
pathStringThe path for Qdrant.
urlStringThe URL for Qdrant.
distance_funcStringThe distance function for vector similarity.
content_payload_keyStringThe content payload key.
metadata_payload_keyStringThe metadata payload key.
search_queryStringThe query for similarity search.
ingest_dataDataThe data to be ingested into the vector store.
embeddingEmbeddingsThe embedding function to use.
number_of_resultsIntegerThe number of results to return in search.

Outputs

NameTypeDescription
vector_storeQdrantA Qdrant vector store instance.
search_resultsList[Data]The results of the similarity search as a list of Data objects.

Redis

This component creates a Redis Vector Store with search capabilities. For more information, see the Redis documentation.

Parameters

Inputs

NameTypeDescription
redis_server_urlSecretStringThe Redis server connection string.
redis_index_nameStringThe name of the Redis index.
codeStringThe custom code for Redis (advanced).
schemaStringThe schema for Redis index.
search_queryStringThe query for similarity search.
ingest_dataDataThe data to be ingested into the vector store.
number_of_resultsIntegerThe number of results to return in search.
embeddingEmbeddingsThe embedding function to use.

Outputs

NameTypeDescription
vector_storeRedisRedis vector store instance
search_resultsList[Data]The results of the similarity search as a list of Data objects.

Supabase

This component creates a connection to a Supabase Vector Store with search capabilities. For more information, see the Supabase documentation.

Parameters

Inputs

NameTypeDescription
supabase_urlStringThe URL of the Supabase instance.
supabase_service_keySecretStringThe service key for Supabase authentication.
table_nameStringThe name of the table in Supabase.
query_nameStringThe name of the query to use.
search_queryStringThe query for similarity search.
ingest_dataDataThe data to be ingested into the vector store.
embeddingEmbeddingsThe embedding function to use.
number_of_resultsIntegerThe number of results to return in search.

Outputs

NameTypeDescription
vector_storeSupabaseVectorStoreA Supabase vector store instance.
search_resultsList[Data]The results of the similarity search as a list of Data objects.

Upstash

This component creates an Upstash Vector Store with search capabilities. For more information, see the Upstash documentation.

Parameters

Inputs

NameTypeDescription
index_urlStringThe URL of the Upstash index.
index_tokenSecretStringThe token for the Upstash index.
text_keyStringThe key in the record to use as text.
namespaceStringThe namespace for the index.
search_queryStringThe query for similarity search.
metadata_filterStringFilter documents by metadata.
ingest_dataDataThe data to be ingested into the vector store.
embeddingEmbeddingsThe embedding function to use.
number_of_resultsIntegerThe number of results to return in search.

Outputs

NameTypeDescription
vector_storeUpstashVectorStoreAn Upstash vector store instance.
search_resultsList[Data]The results of the similarity search as a list of Data objects.

Vectara

This component creates a Vectara Vector Store with search capabilities. For more information, see the Vectara documentation.

Parameters

Inputs

NameTypeDescription
vectara_customer_idStringThe Vectara customer ID.
vectara_corpus_idStringThe Vectara corpus ID.
vectara_api_keySecretStringThe Vectara API key.
embeddingEmbeddingsThe embedding function to use (optional).
ingest_dataList[Document/Data]The data to be ingested into the vector store.
search_queryStringThe query for similarity search.
number_of_resultsIntegerThe number of results to return in search.

Outputs

NameTypeDescription
vector_storeVectaraVectorStoreVectara vector store instance.
search_resultsList[Data]The results of the similarity search as a list of Data objects.

This component searches a Vectara Vector Store for documents based on the provided input. For more information, see the Vectara documentation.

Parameters

Inputs

NameTypeDescription
search_typeStringThe type of search, such as "Similarity" or "MMR".
input_valueStringThe search query.
vectara_customer_idStringThe Vectara customer ID.
vectara_corpus_idStringThe Vectara corpus ID.
vectara_api_keySecretStringThe Vectara API key.
files_urlList[String]Optional URLs for file initialization.

Outputs

NameTypeDescription
search_resultsList[Data]The results of the similarity search as a list of Data objects.

Weaviate

This component facilitates a Weaviate Vector Store setup, optimizing text and document indexing and retrieval. For more information, see the Weaviate Documentation.

Parameters

Inputs

NameTypeDescription
weaviate_urlStringThe default instance URL.
search_by_textBooleanIndicates whether to search by text.
api_keySecretStringThe optional API key for authentication.
index_nameStringThe optional index name.
text_keyStringThe default text extraction key.
inputDocumentThe document or record.
embeddingEmbeddingsThe embedding model used.
attributesList[String]Optional additional attributes.

Outputs

NameTypeDescription
vector_storeWeaviateVectorStoreThe Weaviate vector store instance.

This component searches a Weaviate Vector Store for documents similar to the input. For more information, see the Weaviate Documentation.

Parameters

Inputs

NameTypeDescription
search_typeStringThe type of search, such as "Similarity" or "MMR"
input_valueStringThe search query.
weaviate_urlStringThe default instance URL.
search_by_textBooleanA boolean value that indicates whether to search by text.
api_keySecretStringThe optional API key for authentication.
index_nameStringThe optional index name.
text_keyStringThe default text extraction key.
embeddingEmbeddingsThe embeddings model used.
attributesList[String]Optional additional attributes.

Outputs

NameTypeDescription
search_resultsList[Data]The results of the similarity search as a list of Data objects.
Search