feat/build(caddy): remove ratelimit (#178)

winstxnhdw · Jun 8, 2024 · d57ff1f · d57ff1f
1 parent 11d54d1
commit d57ff1f
Show file tree

Hide file tree

Showing 5 changed files with 2 additions and 30 deletions.
diff --git a/Caddyfile b/Caddyfile
@@ -1,5 +1,4 @@
 {
-	order rate_limit before basicauth
 	order cache before rewrite
 	cache
 }
@@ -13,14 +12,6 @@
 		}
 	}
 
-	rate_limit {
-		zone dynamic_example {
-			key {remote_host}
-			events {$EVENTS_PER_WINDOW}
-			window 60s
-		}
-	}
-
 	handle_path /api/* {
 		reverse_proxy http://localhost:{$SERVER_PORT}
 	}

diff --git a/Dockerfile b/Dockerfile
@@ -5,6 +5,5 @@ ENV OMP_NUM_THREADS 1
 ENV CT2_USE_EXPERIMENTAL_PACKED_GEMM 1
 ENV CT2_FORCE_CPU_ISA AVX512
 ENV WORKER_COUNT 2
-ENV EVENTS_PER_WINDOW 15
 
 EXPOSE $APP_PORT
diff --git a/Dockerfile.build b/Dockerfile.build
@@ -14,9 +14,7 @@ RUN poetry install --without=dev,cuda
 
 FROM caddy:builder-alpine as caddy-builder
 
-RUN xcaddy build master \
-    --with github.com/caddyserver/cache-handler \
-    --with github.com/mholt/caddy-ratelimit
+RUN xcaddy build master --with github.com/caddyserver/cache-handler
 
 
 FROM python:slim
@@ -26,7 +24,6 @@ ENV PYTHONUNBUFFERED 1
 ENV PYTHONDONTWRITEBYTECODE 1
 ENV SERVER_PORT 5000
 ENV CACHE_TIMEOUT 10s
-ENV EVENTS_PER_WINDOW 100000
 
 RUN useradd -m -u 1000 user
 

diff --git a/Dockerfile.cuda-build b/Dockerfile.cuda-build
@@ -14,9 +14,7 @@ RUN poetry install --without=dev
 
 FROM caddy:2.8.4-builder-alpine as caddy-builder
 
-RUN xcaddy build master \
-    --with github.com/caddyserver/cache-handler \
-    --with github.com/mholt/caddy-ratelimit
+RUN xcaddy build master --with github.com/caddyserver/cache-handler
 
 
 FROM python:slim
@@ -26,7 +24,6 @@ ENV PYTHONUNBUFFERED 1
 ENV PYTHONDONTWRITEBYTECODE 1
 ENV SERVER_PORT 5000
 ENV CACHE_TIMEOUT 10s
-ENV EVENTS_PER_WINDOW 100000
 ENV USE_CUDA True
 ENV LD_LIBRARY_PATH /usr/local/lib/python3.12/site-packages/nvidia/cublas/lib
 

diff --git a/README.md b/README.md
@@ -286,18 +286,6 @@ docker run --rm \
   ghcr.io/winstxnhdw/nllb-api:main
 ```
 
-### Rate Limiting
-
-You can set an IP-based rate limit on the number of requests per minute with the following environment variable.
-
-```bash
-docker run --rm \
-  -e APP_PORT=7860 \
-  -e EVENTS_PER_WINDOW=15 \
-  -p 7860:7860 \
-  ghcr.io/winstxnhdw/nllb-api:main
-```
-
 ### CUDA Support
 
 You can accelerate your inference with CUDA by building and using `Dockerfile.cuda-build` instead.