diff --git a/.streamlit/secrets.toml b/.streamlit/secrets.toml
new file mode 100644
index 000000000..7bcd79599
--- /dev/null
+++ b/.streamlit/secrets.toml
@@ -0,0 +1,2 @@
+[secrets]
+REPLICATE_API_TOKEN = ""
diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 000000000..f8881c00e
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,7 @@
+FROM python:3.9.18-slim
+WORKDIR /app
+COPY . /app/
+RUN pip install -r requirements.txt
+EXPOSE 8501
+VOLUME [ "/app" ]
+CMD ["streamlit", "run", "streamlit_app.py"]
diff --git a/README.md b/README.md
index 4792f8e69..c7b2a3b23 100644
--- a/README.md
+++ b/README.md
@@ -23,6 +23,13 @@ To use this app, you'll need to get your own [Replicate](https://replicate.com/)
 
 After signing up to Replicate, you can access your API token from [this page](https://replicate.com/account/api-tokens).
 
+## Installation with Docker
+
+```
+docker build -t llama2 .
+docker run -p 8501:8501 -v $(pwd):/app llama2
+```
+
 ## Other Llama 2 models to try
 
 As mentioned above, this chatbot implementation uses the [**Llama2-7B**](https://replicate.com/a16z-infra/llama7b-v2-chat) model that was trained on 7 billion parameters.