In my case I'm using [OpenAI Embedding Models](https://platform.openai.com/docs/guides/embeddings/embedding-models) for generating Vectors from text (please check the [pricings](https://openai.com/api/pricing/) first), but you could use [LangChain](https://python.langchain.com/v0.1/docs/modules/data_connection/text_embedding/) if you have enough PC resources or you're in a budget. Then I save it into my Supabase DB after installing [pgvector extension](https://supabase.com/docs/guides/database/extensions/pgvector) that not only allows you to add a Vector Column to your tables, but also adds the [ operator](https://github.com/pgvector/pgvector?tab=readme-ov-file#querying) (I'm using this one, but you should explore your options) for Cosine Distance search. Then just apply to your logic.