Merge pull request #995 from wallies/patch-1

multistage docker build

Dockerfile

@@ -1,8 +1,11 @@
 # Base image
-ARG LITELLM_BASE_IMAGE=python:3.9-slim
+ARG LITELLM_BUILD_IMAGE=python:3.9
 
-# allow users to specify, else use python 3.9-slim
-FROM $LITELLM_BASE_IMAGE
+# Runtime image
+ARG LITELLM_RUNTIME_IMAGE=python:3.9-slim
+
+# allow users to specify, else use python 3.9
+FROM $LITELLM_BUILD_IMAGE as builder
 
 # Set the working directory to /app
 WORKDIR /app
@@ -13,11 +16,23 @@ RUN apt-get update && \
     rm -rf /var/lib/apt/lists/*
 
 # Copy the current directory contents into the container at /app
-COPY . /app
+COPY requirements.txt .
 
 # Install any needed packages specified in requirements.txt
-RUN pip wheel --no-cache-dir --wheel-dir=wheels -r requirements.txt
-RUN pip install --no-cache-dir --find-links=wheels -r requirements.txt
+RUN pip install wheel && \
+    pip wheel --no-cache-dir --wheel-dir=/app/wheels -r requirements.txt
+
+###############################################################################
+FROM $LITELLM_RUNTIME_IMAGE as runtime
+
+WORKDIR /app
+
+# Copy the current directory contents into the container at /app
+COPY . .
+
+COPY --from=builder /app/wheels /app/wheels
+
+RUN pip install --no-index --find-links=/app/wheels -r requirements.txt
 
 # Trigger the Prisma CLI to be installed
 RUN prisma -v
@@ -25,7 +40,6 @@ RUN prisma -v
 EXPOSE 4000/tcp
 
 # Start the litellm proxy, using the `litellm` cli command https://docs.litellm.ai/docs/simple_proxy
-
 # Start the litellm proxy with default options
 CMD ["--port", "4000"]
 

docs/my-website/docs/proxy/deploy.md

@@ -7,12 +7,12 @@ See the latest available ghcr docker image here:
 https://github.com/berriai/litellm/pkgs/container/litellm
 
 ```shell
-docker pull ghcr.io/berriai/litellm:main-v1.10.1
+docker pull ghcr.io/berriai/litellm:main-v1.12.3
 ```
 
 ### Run the Docker Image
 ```shell
-docker run ghcr.io/berriai/litellm:main-v1.10.0
+docker run ghcr.io/berriai/litellm:main-v1.12.3
 ```
 
 #### Run the Docker Image with LiteLLM CLI args
@@ -21,12 +21,12 @@ See all supported CLI args [here](https://docs.litellm.ai/docs/proxy/cli):
 
 Here's how you can run the docker image and pass your config to `litellm`
 ```shell
-docker run ghcr.io/berriai/litellm:main-v1.10.0 --config your_config.yaml
+docker run ghcr.io/berriai/litellm:main-v1.12.3 --config your_config.yaml
 ```
 
 Here's how you can run the docker image and start litellm on port 8002 with `num_workers=8`
 ```shell
-docker run ghcr.io/berriai/litellm:main-v1.10.0 --port 8002 --num_workers 8
+docker run ghcr.io/berriai/litellm:main-v1.12.3 --port 8002 --num_workers 8
 ```
   
 #### Run the Docker Image using docker compose
@@ -42,6 +42,10 @@ Here's an example `docker-compose.yml` file
 version: "3.9"
 services:
   litellm:
+    build:
+      context: .
+        args:
+          target: runtime
     image: ghcr.io/berriai/litellm:main
     ports:
       - "8000:8000" # Map the container port to the host, change the host port if necessary