Oracle AI Database Powers Image Similarity Search With Vector Embeddings

Here is the link to the notebook:

https://fandf.co/4ofyvSR

This image search example is the basis for solving a ton of different useful problems:

• Manufacturing quality control • Medical diagnosis and screening • Spotting counterfeit products • Infrastructure inspection • Security and surveillance

My notebook uses LangChain and Oracle's AI Database vector store to store image embeddings.

By the way, the database is packed with AI features. Here are some of the ones that impressed me the most:

1. You can run an LLM and an Embedding model directly from your database. This is huge because you don't need to send your data anywhere else.

2. You can now run hybrid vector searches: semantic and keyword searches directly in the database.

3. There's a new concept called JSON Relational Duality views, where you can see your data in both JSON and relational form. It's cool because you can stick to a relational model while taking advantage of JSON's flexibility.

4. They built-in code generation tools you can use to write SQL code on your database.

Check the other examples in the GitHub repository above. They have a ton of interesting examples on how to use Oracle 26ai and their new functionality.

Thanks to the Oracle team for partnering with me on this post.