Astra DB
Last updated
Last updated
The DataStax Astra DB Vector Database Connector allows you to integrate Astra DB as a vector database for storing and retrieving vectorized data in your pipelines. This guide explains the configuration options available when setting up an Astra DB vector database connector.
As of September 2024, only Astra DB serverless databases with vector search are supported by the Vectorize connector.
Name
A descriptive name to identify the connector within Vectorize
Yes
API Endpoint
The Astra DB API endpoint URL
Yes
Application Token
The Application Token for authentication
Yes
To find your Astra DB API endpoint:
Log in to your DataStax Astra account
Navigate to the dashboard for your Astra DB instance
Look for the API endpoint URL in the instance details
To generate an Application Token:
In your Astra DB dashboard, go to the "Settings" or "Security" section
Look for an option to create or manage API tokens
Generate a new Application Token
Copy the token and store it securely, as it may not be displayed again
From the main menu, click on Vector Databases
Click New Vector Database Integration
Select the DataStax Astra DB card
Fill in the required fields:
Enter a descriptive name for the connector
Paste your API Endpoint URL
Enter your Application Token
Click Create Astra DB Integration to test and save your configuration
When configuring a pipeline, you can select this Astra DB integration as the vector database output. Vectorize will then write the vectorized data to your specified Astra DB instance.
If you encounter issues while creating the integration:
Verify that your API Endpoint URL is correct and accessible
Ensure that your Application Token is valid and has the necessary permissions
Check your network settings to make sure your environment can connect to the Astra DB API
For further assistance, please refer to the documentation for contacting support
