Notebook Prerequisites

Most of our example notebooks use Astra DB Serverless as the vector database and OpenAI as the LLM.

  1. Create an vector-enabled Astra DB Serverless database at For detailed instructions on database creation, see Create a serverless vector database.

  2. Create an OpenAI key at

  3. Install RAGStack with pip install ragstack-ai.

You’ll need these values for the notebooks:

Value Example Notes

Astra application token


Must have Database Administrator permissions

Astra API endpoint\

Endpoint format is https://<ASTRA_DB_ID>-<ASTRA_DB_REGION>

OpenAI key


Create an OpenAI key at

Astra collection name


Collections are where your Documents are indexed. Automatically created if it doesn’t exist.

GCP service account JSON


Credentials for GCP usage. See the GCP documentation.

LlamaIndex Cloud API key


Credentials for LlamaIndex cloud usage.

If a notebook needs additional dependencies, we’ll show you how to install them.

What’s next?

With your prerequisites set up, run the Quickstart!

Was this helpful?

Give Feedback

How can we improve the documentation?

© 2024 DataStax | Privacy policy | Terms of use

Apache, Apache Cassandra, Cassandra, Apache Tomcat, Tomcat, Apache Lucene, Apache Solr, Apache Hadoop, Hadoop, Apache Pulsar, Pulsar, Apache Spark, Spark, Apache TinkerPop, TinkerPop, Apache Kafka and Kafka are either registered trademarks or trademarks of the Apache Software Foundation or its subsidiaries in Canada, the United States and/or other countries. Kubernetes is the registered trademark of the Linux Foundation.

General Inquiries: +1 (650) 389-6000,