pg_vectorize

Take a look at https://github.com/tembo-io/pg_vectorize. It makes it a lot easier to get started. It runs on pgvector, but as a user, its completely abstracted from you. It also provides you with a way to auto-update embeddings as you add new data or update existing source data.

check out https://github.com/tembo-io/pg_vectorize - we're taking it a little bit beyond just the storage and index. The project uses pgvector for the indices and distance operators, but also adds a simpler API, hooks into pre-trained embedding models, and helps you keep embeddings updated as data changes/grows

There is a RAG example here https://github.com/tembo-io/pg_vectorize?tab=readme-ov-file#... You can provide your own prompts by adding them to the `vectorize.prompts` table. There's an API for this in the works. It is poorly documented at the moment.

Sorry if i'm completely missing it, I noticed in the code, there is something around chat: https://github.com/tembo-io/pg_vectorize/blob/main/src/chat.... This would lead me to believe there is some way to actually use SQL for not just embeddings, but also prompting/querying the LLM... which would be crazy powerful. Are there any examples on how to do this?

pg_vectorize is a Postgres extension and provides a high level API which condenses the operations of vector search with pgvector into two function calls; one to initialize table, the other to search the table. We run a container next to Postgres that hosts many transformer models available in Hugging Face, but there is also an integration with OpenAI. The readme contains some examples and how to run this locally using docker compose.