mirror of
https://github.com/mudler/LocalAI.git
synced 2025-03-16 00:55:30 +00:00
By not closing the channel, if a server not implementing PredictStream receives a client call would hang indefinetly as would wait for resultChan to be consumed. If the prediction stream returns we close the channel now and we wait for the goroutine to finish. Signed-off-by: Ettore Di Giacinto <mudler@localai.io>