ArangoDocumentStore

Store and retrieve documents using ArangoDB, a multi-model database with native vector similarity search. Vector search requires ArangoDB 3.12 or later.

Key Features

• Stores documents in an ArangoDB collection with vector search support.
• Supports cosine, dot product, and L2 similarity functions.
• Creates the database and collection automatically if they do not exist.
• Configurable embedding dimensions to match your embedding model.
• Supports Haystack metadata filters at retrieval time.

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 ArangoDB 3.12 or later (default endpoint: http://localhost:8529).
2. Set the ARANGO_USERNAME and ARANGO_PASSWORD environment variables. For instructions, see Create Secrets.
3. Configure the ArangoDocumentStore 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

  ArangoDocumentStore:
    type: haystack_integrations.document_stores.arangodb.document_store.ArangoDocumentStore
    init_parameters:
      host: http://localhost:8529
      database: haystack
      username:
        type: env_var
        env_vars:
        - ARANGO_USERNAME
        strict: false
      password:
        type: env_var
        env_vars:
        - ARANGO_PASSWORD
        strict: false
      collection_name: haystack_documents
      embedding_dimension: 768
      similarity_function: cosine

Parameters

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
host	str	http://localhost:8529	The URL of the ArangoDB server.
database	str	haystack	The name of the database to use. Created if it does not exist.
username	Secret	Secret.from_env_var("ARANGO_USERNAME", strict=False)	The ArangoDB username. Falls back to root if the variable is not set.
password	Secret	Secret.from_env_var("ARANGO_PASSWORD")	The ArangoDB password.
collection_name	str	haystack_documents	The name of the collection to store documents in.
embedding_dimension	int	768	The dimensionality of document embeddings. Must match your embedding model's output.
recreate_collection	bool	False	Whether to drop and recreate the collection on startup.
similarity_function	str	cosine	The vector similarity function. One of cosine, dot_product, or l2.

Related Information

• ArangoEmbeddingRetriever
• Pipeline Components