ArcadeDBDocumentStore

Store and retrieve documents using ArcadeDB, a multi-model database that supports vector similarity search alongside graph, document, and key-value data models.

Key Features

• Stores documents in ArcadeDB with native vector search support.
• Supports cosine, Euclidean, and dot product similarity functions.
• Supports automatic database and type (collection) creation on initialization.
• Configurable embedding dimensions to match your embedding model.

Configuration

Add Workspace-Level Integration

1. Click your profile icon and choose Settings.
2. Go to Workspace>Integrations.
3. Find the provider you want to connect and click Connect next to them.
4. Enter the API key and any other required details.
5. Click Connect. You can use this integration in pipelines and indexes in the current workspace.

Add Organization-Level Integration

1. Click your profile icon and choose Settings.
2. Go to Organization>Integrations.
3. Find the provider you want to connect and click Connect next to them.
4. Enter the API key and any other required details.
5. Click Connect. You can use this integration in pipelines and indexes in all workspaces in the current organization.

1. Install and run ArcadeDB (default endpoint: http://localhost:2480).
2. Set the ARCADEDB_USERNAME and ARCADEDB_PASSWORD environment variables if authentication is enabled. For instructions, see Create Secrets.
3. Configure the ArcadeDBDocumentStore in your pipeline YAML with the appropriate connection parameters.

Source Code

To check this component's source code, open document_store.py in the Haystack Core Integrations repository.

Usage Examples

Basic Configuration

  ArcadeDBDocumentStore:
    type: haystack_integrations.document_stores.arcadedb.document_store.ArcadeDBDocumentStore
    init_parameters:
      url: http://localhost:2480
      database: my_haystack_db
      username:
        type: env_var
        env_vars:
        - ARCADEDB_USERNAME
        strict: false
      password:
        type: env_var
        env_vars:
        - ARCADEDB_PASSWORD
        strict: false
      embedding_dimension: 768
      similarity_function: cosine

Parameters

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
url	str	http://localhost:2480	The URL of the ArcadeDB server.
database	str	haystack	The name of the database to use.
username	Secret	Secret.from_env_var("ARCADEDB_USERNAME", strict=False)	The ArcadeDB username.
password	Secret	Secret.from_env_var("ARCADEDB_PASSWORD", strict=False)	The ArcadeDB password.
type_name	str	Document	The name of the document type (collection) to use.
embedding_dimension	int	768	The dimensionality of document embeddings. Must match your embedding model's output.
similarity_function	str	cosine	The vector similarity function. One of cosine, euclidean, or dot.
recreate_type	bool	False	Whether to drop and recreate the document type on initialization.
create_database	bool	True	Whether to create the database if it doesn't exist.

Related Information

• ArcadeDBEmbeddingRetriever
• Pipeline Components