diff --git a/partner-services/deepgram.mdx b/partner-services/deepgram.mdx index d18f0cd3..4960b3c0 100644 --- a/partner-services/deepgram.mdx +++ b/partner-services/deepgram.mdx @@ -60,6 +60,13 @@ cerebrium cp nova-3-general.en.streaming.123456.dg deepgram-models/nova-3-genera cerebrium cp engine.toml deepgram/engine.toml ``` + + Keep the Engine's `[server]` port set to **8055**, and the `driver_pool` URL + in `api.toml` pointing at it. Cerebrium uses this port to tell when the Engine + is ready, so requests that arrive during startup are queued instead of failing + with `503 Please try again later`. + + ```bash ### Keep in mind that all paths are in-container paths and do not need to exist @@ -84,7 +91,8 @@ server_url = ["https://license.deepgram.com"] ### The IP address to listen on. Since this is likely running in a Docker ### container, you will probably want to listen on all interfaces. host = "0.0.0.0" -### The port to listen on +### The port to listen on. On Cerebrium, keep 8055 so requests are queued while +### the Engine starts up. port = 8055 @@ -260,6 +268,8 @@ speak_streaming = true # or false ### ### Docker Compose and Podman Compose create a dedicated network that allows inter-container communication by app name. ### See [Networking in Compose](https://docs.docker.com/compose/networking/) for details. +### +### On Cerebrium, keep port 8055 here so it matches `[server]` in engine.toml. url = "https://0.0.0.0:8055/v2" ### Factor to increase the timeout by for each additional retry (for ### exponential backoff).