Skip to main content

GenAI

Serve and embed language, vision-language, and speech models. Use these tutorials in order.

Serve GenAI Models image Serve GenAI Models 15-20 minutes

Host multiple GenAI models behind the Neat GenAI server so a UI, service, or remote client can call LLM, VLM, and ASR endpoin...

genaiserverllmvlmasrhttp

Load a GenAI model directory, send one simple prompt, add a system prompt, then grow the same pattern into chat history and s...

genaillmchathistorystreaming

Ask repeated questions about the same image without re-encoding the image for every request.

genaivlmimagecachemultimodal

Use GenAI graph fragments when LLM, VLM, or ASR work is one stage in a larger Neat graph.

genaigraphcompositionstreamingadvanced