Skip to content

LLM Flows

AI Pipes are specialized flows with persistent connections between tasks to enable low-latency LLM tasks. The pipes are persistent and multi-tenant pipes that scale and execute to suit high volume and high data requirement in real time. This is particularly useful for text-to-voice, voice-to-text and voice-to-voice LLM tasks.

AI Pipes Tasks

List of AI Pipe Tasks

NameDescription
llm-chat-pipechat with llms local or remote, using standard Open AI chat completion API
llm-pipe-requestadd a new request to the llm pipe
llm-pipe-responseget responses from the llm pipe
llm-pipe-memorymanage the memory