embeddings

[kosik]

Hello, i see your example of how to generate embeddings, but it is not evident how to use the response afterwards.

Do we need to supply the response as in input parameter to generate method?
How to procced with the embeddings between LLama server restarts ?

Could you please advise on it?

https://amithkoujalgi.github.io/ollama4j/docs/apis-generate/generate-embeddings
https://ollama.com/blog/embedding-models

[AgentSchmecker]

Hi, using the embedding API of ollama does Not provide any persistent information but ist rather one entrypoint towards RAG systems.

I'll try to provide a simple RAG roundtrip in the near Future, but this does not apply directly to this library, as ist focused solely on connecting to ollama.

Greetings!