You've probably heard that there is no AI without Data, so how do you go about easily tapping into large amounts of data and getting it vectorized to build great generative AI applications?

Join DataStax and Airbyte for a 45-minute livestream where we’ll use Airbyte to ingest comics from xkcd and build a simple search engine that lets us query the entire collection and a recommendation engine that takes an xkcd comic and recommends others that folks might like!

In this 45 minute session we will demonstrate how you can:

Segment and embed data into vectors in Astra DB.

Use RAGStack for ingestion, embedding, and prompt retrieval

Bring it all together in a user-friendly chatbot

To wrap up, we’ll host a live Q&A where you can ask technical questions. If you can’t join live, register anyway! We’ll share the replay afterward.

Streamline GenAI and RAG Data Pipelines with Airbyte and DataStax Astra DB