diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 00000000..c3e015da
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,42 @@
+# Use an official Python runtime as a parent image
+FROM python:3.10-slim
+
+# Install build dependencies
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    && rm -rf /var/lib/apt/lists/*
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    gcc \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install Poetry
+RUN pip install poetry
+
+# Copy the project files into the container
+COPY pyproject.toml poetry.lock* README.md ./
+COPY gptme ./gptme
+COPY static ./static
+COPY media ./media
+
+# Install project dependencies including eval extras
+RUN poetry config virtualenvs.create false \
+    && poetry install --no-interaction --no-ansi -E server -E browser -E datascience
+
+# Make port 5000 available to the world outside this container
+# (assuming your Flask server runs on port 5000)
+EXPOSE 5000
+
+# Set environment variable for eval
+ENV PYTHONPATH=/app
+
+# Default command to run the server
+CMD ["poetry", "run", "gptme-server"]
+
+# Add an entry point for running evals
+ENTRYPOINT ["poetry", "run", "python", "-m", "gptme.eval.main"]
diff --git a/Makefile b/Makefile
index d174134c..5da1204e 100644
--- a/Makefile
+++ b/Makefile
@@ -14,6 +14,9 @@ SRCFILES = $(shell find ${SRCDIRS} -name '*.py' $(foreach EXCLUDE,$(EXCLUDES),-n
 build:
 	poetry install
 
+build-docker:
+	docker build -t gptme .
+
 test:
 	@# if SLOW is not set, pass `-m "not slow"` to skip slow tests
 	poetry run pytest ${SRCDIRS} -v --log-level INFO --durations=5 \
@@ -77,7 +80,7 @@ release: dist/CHANGELOG.md
 
 clean: clean-docs clean-site clean-test
 
-clean-site: 
+clean-site:
 	rm -rf site/dist
 
 clean-docs:
diff --git a/poetry.lock b/poetry.lock
index b91bcf23..00bb73cd 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.7.0 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.
 
 [[package]]
 name = "accessible-pygments"
@@ -495,17 +495,6 @@ files = [
     {file = "decorator-5.1.1.tar.gz", hash = "sha256:637996211036b6385ef91435e4fae22989472f9d571faba8927ba8253acbc330"},
 ]
 
-[[package]]
-name = "diskcache"
-version = "5.6.3"
-description = "Disk Cache -- Disk and file backed persistent cache."
-optional = true
-python-versions = ">=3"
-files = [
-    {file = "diskcache-5.6.3-py3-none-any.whl", hash = "sha256:5e31b2d5fbad117cc363ebaf6b689474db18a1f6438bc82358b024abd4c2ca19"},
-    {file = "diskcache-5.6.3.tar.gz", hash = "sha256:2c3a3fa2743d8535d832ec61c2054a1641f41775aa7c556758a109941e33e4fc"},
-]
-
 [[package]]
 name = "distro"
 version = "1.9.0"
@@ -1177,24 +1166,6 @@ files = [
     {file = "kiwisolver-1.4.5.tar.gz", hash = "sha256:e57e563a57fb22a142da34f38acc2fc1a5c864bc29ca1517a88abc963e60d6ec"},
 ]
 
-[[package]]
-name = "llama-cpp-python"
-version = "0.1.85"
-description = "A Python wrapper for llama.cpp"
-optional = true
-python-versions = ">=3.7"
-files = [
-    {file = "llama_cpp_python-0.1.85.tar.gz", hash = "sha256:9ad2269f47a5fac10e78565e0b4078ea6b8d56ddd3b78892967da4739684db2b"},
-]
-
-[package.dependencies]
-diskcache = ">=5.6.1"
-numpy = ">=1.20.0"
-typing-extensions = ">=4.5.0"
-
-[package.extras]
-server = ["fastapi (>=0.100.0)", "pydantic-settings (>=2.0.1)", "sse-starlette (>=1.6.1)", "uvicorn (>=0.22.0)"]
-
 [[package]]
 name = "markdown-it-py"
 version = "3.0.0"
@@ -1671,7 +1642,6 @@ optional = true
 python-versions = ">=3"
 files = [
     {file = "nvidia_nvjitlink_cu12-12.3.101-py3-none-manylinux1_x86_64.whl", hash = "sha256:64335a8088e2b9d196ae8665430bc6a2b7e6ef2eb877a9c735c804bd4ff6467c"},
-    {file = "nvidia_nvjitlink_cu12-12.3.101-py3-none-manylinux2014_aarch64.whl", hash = "sha256:211a63e7b30a9d62f1a853e19928fbb1a750e3f17a13a3d1f98ff0ced19478dd"},
     {file = "nvidia_nvjitlink_cu12-12.3.101-py3-none-win_amd64.whl", hash = "sha256:1b2e317e437433753530792f13eece58f0aec21a2b05903be7bffe58a606cbd1"},
 ]
 
@@ -2432,7 +2402,6 @@ files = [
     {file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"},
     {file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"},
     {file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"},
-    {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a08c6f0fe150303c1c6b71ebcd7213c2858041a7e01975da3a99aed1e7a378ef"},
     {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"},
     {file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"},
     {file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"},
@@ -3490,13 +3459,13 @@ files = [
 ]
 
 [extras]
-all = ["flask", "llama-cpp-python", "matplotlib", "numpy", "pandas", "pillow", "playwright", "torch", "transformers"]
+all = ["flask", "matplotlib", "numpy", "pandas", "pillow", "playwright", "torch", "transformers"]
 browser = ["playwright"]
 datascience = ["matplotlib", "numpy", "pandas", "pillow"]
-server = ["flask", "llama-cpp-python"]
+server = ["flask"]
 training = ["torch", "transformers"]
 
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "3a70a3cbba9b00ce58e598953c71d5af5db72087311c2750d46bba4605695742"
+content-hash = "5391ff22a43c920087bb50555c9f2060d243130d947007a37dc30e5e3a7e1bf3"
diff --git a/pyproject.toml b/pyproject.toml
index b5b8e2ec..b55470e7 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -37,7 +37,6 @@ openai = "^1.0"
 anthropic = "^0.34.0"
 
 # optionals
-llama-cpp-python = {version = "^0.1.57", optional=true}
 playwright = {version = "^1.37.0", optional=true}
 jedi = {version = "^0.19.0", optional=true}
 
@@ -74,13 +73,13 @@ types-tabulate = "^0.9.0.20240106"
 pytest-retry = "^1.6.3"
 
 [tool.poetry.extras]
-server = ["llama-cpp-python", "flask"]
+server = ["flask"]
 browser = ["playwright"]
 datascience = ["matplotlib", "pandas", "numpy", "pillow"]
 training = ["torch", "transformers"]
 all = [
     # server
-    "llama-cpp-python", "flask",
+    "flask",
     # browser
     "playwright",
     # datascience