In this earlier post, we created a vector store in our Oracle Database 23ai and populated it with some content from Moby Dick. Since MCP is very popular these days, I thought it might be interesting to look how to create a very simple MCP server to expose the similarity search as and MCP tool. Let's jump right into it.

In this post, I want to explore how you can use Real Application Security to provide access controls for vectors in a vector store in Oracle Database 23ai. I'm going to use the vector store we created in the last post as an example. If you want to follow along, you should follow that one first to create and populate your vector store, then come back here.

In this earlier post, we learned how to create a Vector Store in Oracle from LangChain, the hugely popular Python library for working with Generative AI and Large Language Models. We populated it with a little data and then performed some simple vector similarity searches. In this post, let's expand on that to implement basic Retrieval Augmented Generation! First, let's talk about some concepts - if you alread know this, feel free to jump ahead!

In this post, I would like to show you the basics of how to use the Oracle Vector Store support in LangChain. I am using Visual Studio Code with the Python and Jupyter extensions from Microsoft installed. I will show more detailed usage in future posts! Prefer to watch a video? Check it out here: To get started, create a new project in Visual Studio code, and then create a new Jupyter Notebook using…

Did you know that you can easily run Oracle Autonomous Database in a container on your local machine? This is a great for development. It's totally free, and you don't even need to authenticate to pull the image. It also includes Oracle REST Data Services, APEX, Database Actions and the MongoDB API, so you get a nice built-in browser-based UI to work with your database.