Dockerizing Route-LLM 🚀

Dockerfile

@@ -0,0 +1,6 @@
+FROM python:3.9-slim
+WORKDIR /app
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+COPY . .
+CMD ["python", "-m", "routellm.openai_server", "--routers", "mf", "--strong-model", "gpt-4-1106-preview", "--weak-model", "anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1"]

README.md

@@ -30,6 +30,25 @@ cd RouteLLM
 pip install -e .[serve,eval]
 ```
 
+## Docker
+To run Route-LLM inside Docker:
+```
+git clone https://github.com/lm-sys/RouteLLM.git
+cd RouteLLM
+ ```
+ Add your keys and models in the **environment** section of docker-compose.yml: 
+```
+  environment:
+      - OPENAI_API_KEY=your_strong_model_key
+      - ANYSCALE_MODEL_KEY=your_weak_model_key
+  command: python -m routellm.openai_server --routers mf --strong-model openai/gpt4o --weak-model anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1
+
+```
+Now simply use the docker-compose command.
+``` 
+docker-compose up
+```
+
 ## Quickstart
 
 Let's walkthrough replacing an existing OpenAI client to route queries between LLMs instead of using only a single model.

docker-compose.yml

@@ -0,0 +1,15 @@
+version: '3.8'
+
+services:
+  routellm:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    ports: 
+      - 6060:6060
+    volumes:
+      - ./config.example.yaml:/app/config.example.yaml # Mount the config file
+    environment:
+      - OPENAI_API_KEY=your_openai_api_key  # Replace with your actual OpenAI API key
+      - GROQ_API_KEY=your_groq_api_key  # Replace with your actual GR0Q_API_KEY, ANYSCALE_API_KEY ETC.
+    command: python -m routellm.openai_server --routers mf --strong-model openai/gpt4o --weak-model groq/llama3-8b-8192