Hi great product; I was unsure where to put this but it would be cool to add base url /api key for model config in pipeline that way we can use embedding/LLms we have deployed elsewhere already for example ; we have an OpenAI api compliant LLM deployed with vllm elsewhere id like to use for embeddings, then I can do a pgml end to end rag pipe
Hi great product; I was unsure where to put this but it would be cool to add base url /api key for model config in pipeline that way we can use embedding/LLms we have deployed elsewhere already for example ; we have an OpenAI api compliant LLM deployed with vllm elsewhere id like to use for embeddings, then I can do a pgml end to end rag pipe