From 17dfcde61501ef9c5fcd8a66491f993a3596ef1c Mon Sep 17 00:00:00 2001 From: Robey Holderith Date: Sat, 2 Mar 2024 12:43:10 -0800 Subject: [PATCH] Added admin-key param, and added endpoints to api-key description. --- examples/server/README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/examples/server/README.md b/examples/server/README.md index 397ee8252..e62b86134 100644 --- a/examples/server/README.md +++ b/examples/server/README.md @@ -43,8 +43,9 @@ see https://github.com/ggerganov/llama.cpp/issues/1437 - `--host`: Set the hostname or ip address to listen. Default `127.0.0.1`. - `--port`: Set the port to listen. Default: `8080`. - `--path`: path from which to serve static files (default examples/server/public) -- `--api-key`: Set an api key for request authorization. By default the server responds to every request. With an api key set, the requests must have the Authorization header set with the api key as Bearer token. May be used multiple times to enable multiple valid keys. +- `--api-key`: Set an api key for request authorization. By default the server responds to every request. With an api key set, the requests to `/completion`, `/infill` and `/chat/completions` must have the Authorization header set with the api key as Bearer token. May be used multiple times to enable multiple valid keys. - `--api-key-file`: path to file containing api keys delimited by new lines. If set, requests must include one of the keys for access. May be used in conjunction with `--api-key`'s. +- `--admin-key`: Set an admin key for request authorization. With an admin key set, requests to `/metrics` and `/slots` must have the Authorization header set with the api key as Bearer token. Additionally, `/health` will not show slots without the key. May be used multiple times to enable multiple valid keys. - `--embedding`: Enable embedding extraction, Default: disabled. - `-np N`, `--parallel N`: Set the number of slots for process requests (default: 1) - `-cb`, `--cont-batching`: enable continuous batching (a.k.a dynamic batching) (default: disabled)