fix: add cuda dockerfile + new docker-compose profile

Dockerfile.local-cuda

@@ -0,0 +1,84 @@
+FROM nvidia/cuda:12.5.1-cudnn-devel-ubuntu22.04 as base
+
+# For tzdata
+ENV DEBIAN_FRONTEND="noninteractive" TZ="Etc/UTC"
+
+RUN apt-get update && apt-get upgrade -y \
+    && apt-get install -y git build-essential \
+    python3 python3-pip python3.11-venv gcc wget \
+    ocl-icd-opencl-dev opencl-headers clinfo \
+    libclblast-dev libopenblas-dev \
+    && mkdir -p /etc/OpenCL/vendors && echo "libnvidia-opencl.so.1" > /etc/OpenCL/vendors/nvidia.icd \
+    && ln -sf /usr/bin/python3.11 /usr/bin/python3 \
+    && python3 --version
+
+# Install poetry
+RUN pip install pipx
+RUN python3 -m pipx ensurepath
+RUN pipx install poetry==1.8.3
+ENV PATH="/root/.local/bin:$PATH"
+ENV PATH=".venv/bin/:$PATH"
+
+# Dependencies to build llama-cpp
+RUN apt update && apt install -y \
+  libopenblas-dev\
+  ninja-build\
+  build-essential\
+  pkg-config\
+  wget
+
+# https://python-poetry.org/docs/configuration/#virtualenvsin-project
+ENV POETRY_VIRTUALENVS_IN_PROJECT=true
+
+FROM base as dependencies
+WORKDIR /home/worker/app
+COPY pyproject.toml poetry.lock ./
+
+ARG POETRY_EXTRAS="ui embeddings-huggingface llms-llama-cpp vector-stores-qdrant"
+RUN poetry install --no-root --extras "${POETRY_EXTRAS}"
+
+# Enable GPU support
+ENV CUDA_DOCKER_ARCH=all
+ENV GGML_CUDA=1
+ENV TOKENIZERS_PARALLELISM=true
+RUN CMAKE_ARGS="-DGGML_CUDA=on" \
+    poetry run pip install \
+        --force-reinstall \
+        --no-cache-dir \
+        --verbose \
+        llama-cpp-python==0.2.84 \
+        numpy==1.26.0
+
+FROM base as app
+
+ENV PYTHONUNBUFFERED=1
+ENV PORT=8080
+ENV APP_ENV=prod
+ENV PYTHONPATH="$PYTHONPATH:/home/worker/app/private_gpt/"
+EXPOSE 8080
+
+# Prepare a non-root user
+# More info about how to configure UIDs and GIDs in Docker:
+# https://github.com/systemd/systemd/blob/main/docs/UIDS-GIDS.md
+
+# Define the User ID (UID) for the non-root user
+# UID 100 is chosen to avoid conflicts with existing system users
+ARG UID=1000
+
+# Define the Group ID (GID) for the non-root user
+# GID 65534 is often used for the 'nogroup' or 'nobody' group
+ARG GID=65534
+
+RUN adduser --system --gid ${GID} --uid ${UID} --home /home/worker worker
+WORKDIR /home/worker/app
+
+RUN chown worker /home/worker/app
+RUN mkdir local_data && chown worker local_data
+RUN mkdir models && chown worker models
+COPY --chown=worker --from=dependencies /home/worker/app/.venv/ .venv
+COPY --chown=worker private_gpt/ private_gpt
+COPY --chown=worker *.yaml ./
+COPY --chown=worker scripts/ scripts
+
+USER worker
+ENTRYPOINT python -m private_gpt

docker-compose.yaml

@@ -48,6 +48,26 @@ services:
     profiles:
       - llamacpp-cpu
 
+  # Private-GPT service for the local mode (with CUDA support)
+  # This service builds from a local Dockerfile and runs the application in local mode.
+  private-gpt-llamacpp-cuda:
+    image: ${PGPT_IMAGE:-zylonai/private-gpt}${PGPT_TAG:-0.6.1}-llamacpp-cuda
+    build:
+      context: .
+      dockerfile: Dockerfile.llamacpp-cuda
+    volumes:
+      - ./local_data/:/home/worker/app/local_data
+      - ./models/:/home/worker/app/models
+    entrypoint: sh -c ".venv/bin/python scripts/setup && .venv/bin/python -m private_gpt"
+    ports:
+      - "8001:8001"
+    environment:
+      PORT: 8001
+      PGPT_PROFILES: local
+      HF_TOKEN: ${HF_TOKEN}
+    profiles:
+      - llamacpp-cuda
+
   #-----------------------------------
   #---- Ollama services --------------
   #-----------------------------------

fern/docs/pages/quickstart/quickstart.mdx

@@ -82,6 +82,21 @@ HF_TOKEN=<your_hf_token> docker-compose --profile llamacpp-cpu up
 ```
 Replace `<your_hf_token>` with your actual Hugging Face token.
 
+#### 2. LlamaCPP CUDA
+
+**Description:**
+This profile runs the Private-GPT services locally using `llama-cpp` and Hugging Face models.
+
+**Requirements:**
+A **Hugging Face Token (HF_TOKEN)** is required for accessing Hugging Face models. Obtain your token following [this guide](/installation/getting-started/troubleshooting#downloading-gated-and-private-models).
+
+**Run:**
+Start the services with your Hugging Face token using pre-built images:
+```sh
+HF_TOKEN=<your_hf_token> docker-compose --profile llamacpp-cuda up
+```
+Replace `<your_hf_token>` with your actual Hugging Face token.
+
 ## Building Locally
 
 If you prefer to build Docker images locally, which is useful when making changes to the codebase or the Dockerfiles, follow these steps: