Aleksandr Chikovani
Aleksandr Chikovani
DIAL core (API) allows you to specify `max_prompt_tokens` parameters, but DIAL Chat (web UI) does not. As a user of Web UI (DIAL Chat), I want to be able to...
As an end-user of DIAL UI, I want to be able to generate a temporal API key for me to explore DIAL API and learn how to work with LLM....
(should this be created under openai-adapter?) I'd like to be able to use whisper through DIAL. API usage is first priority.
Current load balancing is using round robin strategy. I'd like to have more intelligent balancing strategies: * weights-based * latency-based (technically, it might be somehow implemented via weights controlled by...