build cpu agent ui docker image. (#1894)
This commit is contained in:
lkk
@@ -7,7 +7,7 @@ source /GenAIExamples/.github/workflows/scripts/change_color
|
||||
log_dir=/GenAIExamples/.github/workflows/scripts/codeScan
|
||||
ERROR_WARN=false
|
||||
|
||||
find . -type f \( -name "Dockerfile*" \) -print -exec hadolint --ignore DL3006 --ignore DL3007 --ignore DL3008 --ignore DL3013 {} \; > ${log_dir}/hadolint.log
|
||||
find . -type f \( -name "Dockerfile*" \) -print -exec hadolint --ignore DL3006 --ignore DL3007 --ignore DL3008 --ignore DL3013 --ignore DL3018 --ignore DL3016 {} \; > ${log_dir}/hadolint.log
|
||||
|
||||
if [[ $(grep -c "error" ${log_dir}/hadolint.log) != 0 ]]; then
|
||||
$BOLD_RED && echo "Error!! Please Click on the artifact button to download and check error details." && $RESET
|
||||
|
||||
@@ -1,49 +1,204 @@
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# Copyright (C) 2025 Intel Corporation
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
#FROM python:3.11-slim
|
||||
FROM node:22.9.0
|
||||
# syntax=docker/dockerfile:1
|
||||
# Initialize device type args
|
||||
# use build args in the docker build command with --build-arg="BUILDARG=true"
|
||||
ARG USE_CUDA=false
|
||||
ARG USE_OLLAMA=false
|
||||
# Tested with cu117 for CUDA 11 and cu121 for CUDA 12 (default)
|
||||
ARG USE_CUDA_VER=cu121
|
||||
# any sentence transformer model; models to use can be found at https://huggingface.co/models?library=sentence-transformers
|
||||
# Leaderboard: https://huggingface.co/spaces/mteb/leaderboard
|
||||
# for better performance and multilangauge support use "intfloat/multilingual-e5-large" (~2.5GB) or "intfloat/multilingual-e5-base" (~1.5GB)
|
||||
# IMPORTANT: If you change the embedding model (sentence-transformers/all-MiniLM-L6-v2) and vice versa, you aren't able to use RAG Chat with your previous documents loaded in the WebUI! You need to re-embed them.
|
||||
ARG USE_EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2
|
||||
ARG USE_RERANKING_MODEL=""
|
||||
|
||||
ENV LANG=C.UTF-8
|
||||
ARG ARCH=cpu
|
||||
# Tiktoken encoding name; models to use can be found at https://huggingface.co/models?library=tiktoken
|
||||
ARG USE_TIKTOKEN_ENCODING_NAME="cl100k_base"
|
||||
|
||||
RUN apt-get update -y && apt-get install -y --no-install-recommends --fix-missing \
|
||||
build-essential \
|
||||
libgl1-mesa-glx \
|
||||
libjemalloc-dev \
|
||||
git \
|
||||
python3-venv
|
||||
ARG BUILD_HASH=dev-build
|
||||
# Override at your own risk - non-root configurations are untested
|
||||
ARG UID=0
|
||||
ARG GID=0
|
||||
|
||||
######## WebUI frontend ########
|
||||
FROM --platform=$BUILDPLATFORM node:22-alpine3.20 AS build
|
||||
ARG BUILD_HASH
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
COPY open_webui_patches /app/patches
|
||||
ARG WEBUI_VERSION=v0.5.20
|
||||
RUN apk add --no-cache git
|
||||
|
||||
# Clone code and use patch
|
||||
RUN git config --global user.name "opea" && \
|
||||
git config --global user.email "" && \
|
||||
git clone https://github.com/open-webui/open-webui.git
|
||||
|
||||
WORKDIR /app/open-webui
|
||||
|
||||
RUN git checkout ${WEBUI_VERSION} && \
|
||||
if [ -d patches ] && [ "$(ls -A patches)" ]; then git am /app/patches/*.patch; fi
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
RUN mv open-webui/* . && rm -fr open-webui && ls -lrth /app/backend/
|
||||
|
||||
RUN npm install onnxruntime-node --onnxruntime-node-install-cuda=skip
|
||||
RUN apk update && \
|
||||
apk add --no-cache wget && \
|
||||
wget https://github.com/microsoft/onnxruntime/releases/download/v1.20.1/onnxruntime-linux-x64-gpu-1.20.1.tgz
|
||||
|
||||
ENV APP_BUILD_HASH=${BUILD_HASH}
|
||||
RUN npm run build
|
||||
|
||||
######## WebUI backend ########
|
||||
FROM python:3.11-slim-bookworm AS base
|
||||
|
||||
# Use args
|
||||
ARG USE_CUDA
|
||||
ARG USE_OLLAMA
|
||||
ARG USE_CUDA_VER
|
||||
ARG USE_EMBEDDING_MODEL
|
||||
ARG USE_RERANKING_MODEL
|
||||
ARG UID
|
||||
ARG GID
|
||||
|
||||
## Basis ##
|
||||
ENV ENV=prod \
|
||||
PORT=8080 \
|
||||
# pass build args to the build
|
||||
USE_OLLAMA_DOCKER=${USE_OLLAMA} \
|
||||
USE_CUDA_DOCKER=${USE_CUDA} \
|
||||
USE_CUDA_DOCKER_VER=${USE_CUDA_VER} \
|
||||
USE_EMBEDDING_MODEL_DOCKER=${USE_EMBEDDING_MODEL} \
|
||||
USE_RERANKING_MODEL_DOCKER=${USE_RERANKING_MODEL}
|
||||
|
||||
## Basis URL Config ##
|
||||
ENV OLLAMA_BASE_URL="/ollama" \
|
||||
OPENAI_API_BASE_URL=""
|
||||
|
||||
## API Key and Security Config ##
|
||||
ENV OPENAI_API_KEY="" \
|
||||
WEBUI_SECRET_KEY="" \
|
||||
SCARF_NO_ANALYTICS=true \
|
||||
DO_NOT_TRACK=true \
|
||||
ANONYMIZED_TELEMETRY=false
|
||||
|
||||
#### Other models #########################################################
|
||||
## whisper TTS model settings ##
|
||||
ENV WHISPER_MODEL="base" \
|
||||
WHISPER_MODEL_DIR="/app/backend/data/cache/whisper/models"
|
||||
|
||||
## RAG Embedding model settings ##
|
||||
ENV RAG_EMBEDDING_MODEL="$USE_EMBEDDING_MODEL_DOCKER" \
|
||||
RAG_RERANKING_MODEL="$USE_RERANKING_MODEL_DOCKER" \
|
||||
SENTENCE_TRANSFORMERS_HOME="/app/backend/data/cache/embedding/models"
|
||||
|
||||
## Tiktoken model settings ##
|
||||
ENV TIKTOKEN_ENCODING_NAME="cl100k_base" \
|
||||
TIKTOKEN_CACHE_DIR="/app/backend/data/cache/tiktoken"
|
||||
|
||||
## Hugging Face download cache ##
|
||||
ENV HF_HOME="/app/backend/data/cache/embedding/models"
|
||||
|
||||
## Torch Extensions ##
|
||||
# ENV TORCH_EXTENSIONS_DIR="/.cache/torch_extensions"
|
||||
|
||||
#### Other models ##########################################################
|
||||
|
||||
COPY --from=build /app/backend /app/backend
|
||||
|
||||
WORKDIR /app/backend
|
||||
|
||||
WORKDIR /root/
|
||||
|
||||
ENV HOME=/root
|
||||
ENV VIRTUAL_ENV=$HOME/.env/open-webui
|
||||
# Create user and group if not root
|
||||
RUN if [ $UID -ne 0 ]; then \
|
||||
if [ $GID -ne 0 ]; then \
|
||||
addgroup --gid $GID app; \
|
||||
fi; \
|
||||
adduser --uid $UID --gid $GID --home $HOME --disabled-password --no-create-home app; \
|
||||
fi
|
||||
|
||||
COPY open_webui_patches /root/patches
|
||||
RUN mkdir -p $HOME/.cache/chroma
|
||||
RUN printf 00000000-0000-0000-0000-000000000000 > $HOME/.cache/chroma/telemetry_user_id
|
||||
|
||||
RUN git clone https://github.com/open-webui/open-webui.git && \
|
||||
git config --global user.name "opea" && git config --global user.email "" && \
|
||||
mkdir -p $HOME/.env && python3 -m venv $VIRTUAL_ENV && \
|
||||
$VIRTUAL_ENV/bin/python -m pip install --no-cache-dir --upgrade pip && \
|
||||
$VIRTUAL_ENV/bin/python -m pip install --no-cache-dir build
|
||||
# Make sure the user has access to the app and root directory
|
||||
RUN chown -R $UID:$GID /app $HOME
|
||||
|
||||
WORKDIR /root/open-webui
|
||||
SHELL ["/bin/bash", "-o", "pipefail", "-c"]
|
||||
|
||||
ENV PATH="$VIRTUAL_ENV/bin:$PATH"
|
||||
RUN if [ "$USE_OLLAMA" = "true" ]; then \
|
||||
apt-get update && \
|
||||
# Install pandoc and netcat
|
||||
apt-get install -y --no-install-recommends git build-essential pandoc netcat-openbsd curl && \
|
||||
apt-get install -y --no-install-recommends gcc python3-dev && \
|
||||
# for RAG OCR
|
||||
apt-get install -y --no-install-recommends ffmpeg libsm6 libxext6 && \
|
||||
# install helper tools
|
||||
apt-get install -y --no-install-recommends curl jq && \
|
||||
# install ollama
|
||||
curl -fsSL https://ollama.com/install.sh | sh && \
|
||||
# cleanup
|
||||
rm -rf /var/lib/apt/lists/*; \
|
||||
else \
|
||||
apt-get update && \
|
||||
# Install pandoc, netcat and gcc
|
||||
apt-get install -y --no-install-recommends git build-essential pandoc gcc netcat-openbsd curl jq && \
|
||||
apt-get install -y --no-install-recommends gcc python3-dev && \
|
||||
# for RAG OCR
|
||||
apt-get install -y --no-install-recommends ffmpeg libsm6 libxext6 && \
|
||||
# cleanup
|
||||
rm -rf /var/lib/apt/lists/*; \
|
||||
fi
|
||||
|
||||
RUN git checkout v0.5.20 && \
|
||||
git am ../patches/*.patch && \
|
||||
python -m build && \
|
||||
pip install --no-cache-dir dist/open_webui-0.5.20-py3-none-any.whl
|
||||
# install python dependencies
|
||||
# COPY --chown=$UID:$GID ./backend/requirements.txt ./requirements.txt
|
||||
# RUN cp /app/backend/requirements.txt ./requirements.txt
|
||||
|
||||
ENV LANG=en_US.UTF-8
|
||||
|
||||
WORKDIR /root/
|
||||
|
||||
RUN rm -fr /root/open-webui && rm -fr /root/patches
|
||||
|
||||
# CMD ["/bin/bash"]
|
||||
ENTRYPOINT ["open-webui", "serve"]
|
||||
RUN pip3 install --no-cache-dir uv && \
|
||||
if [ "$USE_CUDA" = "true" ]; then \
|
||||
# If you use CUDA the whisper and embedding model will be downloaded on first use
|
||||
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/$USE_CUDA_DOCKER_VER --no-cache-dir && \
|
||||
uv pip install --system -r requirements.txt --no-cache-dir && \
|
||||
python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ['RAG_EMBEDDING_MODEL'], device='cpu')" && \
|
||||
python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"; \
|
||||
python -c "import os; import tiktoken; tiktoken.get_encoding(os.environ['TIKTOKEN_ENCODING_NAME'])"; \
|
||||
else \
|
||||
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir && \
|
||||
uv pip install --system -r requirements.txt --no-cache-dir && \
|
||||
python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ['RAG_EMBEDDING_MODEL'], device='cpu')" && \
|
||||
python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"; \
|
||||
python -c "import os; import tiktoken; tiktoken.get_encoding(os.environ['TIKTOKEN_ENCODING_NAME'])"; \
|
||||
fi; \
|
||||
chown -R $UID:$GID /app/backend/data/
|
||||
|
||||
|
||||
|
||||
# copy embedding weight from build
|
||||
# RUN mkdir -p /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2
|
||||
# COPY --from=build /app/onnx /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2/onnx
|
||||
|
||||
# copy built frontend files
|
||||
COPY --chown=$UID:$GID --from=build /app/build /app/build
|
||||
COPY --chown=$UID:$GID --from=build /app/CHANGELOG.md /app/CHANGELOG.md
|
||||
COPY --chown=$UID:$GID --from=build /app/package.json /app/package.json
|
||||
|
||||
# copy backend files
|
||||
# COPY --chown=$UID:$GID ./backend .
|
||||
|
||||
EXPOSE 8080
|
||||
|
||||
HEALTHCHECK CMD curl --silent --fail http://localhost:${PORT:-8080}/health | jq -ne 'input.status == true' || exit 1
|
||||
|
||||
USER $UID:$GID
|
||||
|
||||
ARG BUILD_HASH
|
||||
ENV WEBUI_BUILD_VERSION=${BUILD_HASH}
|
||||
ENV DOCKER=true
|
||||
|
||||
CMD [ "bash", "start.sh"]
|
||||
|
||||
Reference in New Issue
Block a user