Merge pull request #15 from wojiushixiaobai/main

perf: 优化镜像大小

.github/workflows/build-and-push-python-pg.yml

@@ -39,7 +39,7 @@ jobs:
         run: |
           DOCKER_IMAGE=ghcr.io/1panel-dev/maxkb-python-pg
           DOCKER_PLATFORMS=${{ github.event.inputs.architecture }}
-          TAG_NAME=python3.11.8-pg15.3
+          TAG_NAME=python3.11-pg15.6
           DOCKER_IMAGE_TAGS="--tag ${DOCKER_IMAGE}:${TAG_NAME} --tag ${DOCKER_IMAGE}:latest"
           echo ::set-output name=docker_image::${DOCKER_IMAGE}
           echo ::set-output name=version::${TAG_NAME}

.github/workflows/build-and-push-vector-model.yml

@@ -5,7 +5,7 @@ on:
     inputs:
       dockerImageTag:
         description: 'Docker Image Tag'
-        default: 'v1.0.0'
+        default: 'v1.0.1'
         required: true
       architecture:
         description: 'Architecture'

README.md

@@ -18,6 +18,9 @@ MaxKB 是一款基于 LLM 大语言模型的知识库问答系统。
 
 ```
 docker run -d --name=maxkb -p 8080:8080 -v ~/.maxkb:/var/lib/postgresql/data 1panel/maxkb
+
+# 用户名: admin
+# 密码: MaxKB@123..
 ```
 
 也可以通过 [1Panel 应用商店](https://apps.fit2cloud.com/1panel) 快速部署 MaxKB + Ollama + Llama 2，30 分钟内即可上线基于本地大模型的知识库问答系统，并嵌入到第三方业务系统中。

installer/Dockerfile

@@ -1,41 +1,59 @@
-FROM ghcr.io/1panel-dev/maxkb-vector-model:v1.0.0 as vector-model
+FROM ghcr.io/1panel-dev/maxkb-vector-model:v1.0.1 as vector-model
+FROM ghcr.io/1panel-dev/maxkb-python-pg:python3.11-pg15.6 as stage-build
 
-FROM node:18-alpine3.18 as web-build
+ARG DEPENDENCIES="                    \
+        python3-pip"
+
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends $DEPENDENCIES && \
+    apt-get clean all  && \
+    rm -rf /var/lib/apt/lists/*
+
+COPY . /opt/maxkb/app
+RUN mkdir -p /opt/maxkb/app /opt/maxkb/model /opt/maxkb/conf && \
+    cp -f /opt/maxkb/app/installer/config.yaml /opt/maxkb/conf && \
+    rm -rf /opt/maxkb/app/ui
+
+WORKDIR /opt/maxkb/app
+RUN python3 -m venv /opt/py3 && \
+    pip install poetry --break-system-packages && \
+    poetry config virtualenvs.create false && \
+    . /opt/py3/bin/activate && \
+    if [ "$(uname -m)" != "x86_64" ]; then sed -i '/^torch/d' pyproject.toml; fi && \
+    poetry install
+
+FROM node:18-bookworm-slim as web-build
 COPY ui ui
 RUN cd ui && \
     npm install && \
     npm run build && \
     rm -rf ./node_modules
 
-FROM ghcr.io/1panel-dev/maxkb-python-pg:python3.11.8-pg15.3
+FROM ghcr.io/1panel-dev/maxkb-python-pg:python3.11-pg15.6
-ARG DOCKER_IMAGE_TAG=dev
+ARG DOCKER_IMAGE_TAG=dev \
-ARG BUILD_AT
+    BUILD_AT \
-ARG GITHUB_COMMIT
+    GITHUB_COMMIT
+
 ENV MAXKB_VERSION ${DOCKER_IMAGE_TAG} (build at ${BUILD_AT}, commit: ${GITHUB_COMMIT})
-# 创建工作目录
+
-RUN mkdir -p /opt/maxkb/app && mkdir -p /opt/maxkb/model && mkdir -p /opt/maxkb/conf
+COPY --from=stage-build /opt/py3 /opt/py3
-# 拷贝项目
-COPY . /opt/maxkb/app
-RUN rm -rf /opt/maxkb/app/ui
-COPY installer/config.yaml /opt/maxkb/conf
-COPY --from=vector-model model /opt/maxkb/app/model
 COPY --from=web-build ui /opt/maxkb/app/ui
+COPY --from=stage-build /opt/maxkb /opt/maxkb
+COPY --from=vector-model /opt/maxkb/app/model /opt/maxkb/app/model
+
+ENV LANG=en_US.UTF-8 \
+    PATH=/opt/py3/bin:$PATH
+
 ENV POSTGRES_USER root
 ENV POSTGRES_PASSWORD Password123@postgres
-WORKDIR /opt/maxkb/app
+
 RUN mv /opt/maxkb/app/model/* /opt/maxkb/model && \
+    chmod 755 /opt/maxkb/app/installer/run-maxkb.sh && \
     cp -r /opt/maxkb/model/base/hub /opt/maxkb/model/tokenizer && \
-    apt-get update && apt-get install -y curl && \
+    cp -f /opt/maxkb/app/installer/run-maxkb.sh /usr/bin/run-maxkb.sh && \
-    pip3 install --upgrade pip && \
+    cp -f /opt/maxkb/app/installer/init.sql /docker-entrypoint-initdb.d
-    if [ "$(uname -m)" = "aarch64" ]; then sed -i '/^torch/d' pyproject.toml; fi && \
+
-    pip3 install poetry && \
-    poetry export -f requirements.txt --output requirements.txt --without-hashes && \
-    pip3 install --no-cache-dir -r requirements.txt && \
-    pip3 cache purge && \
-    rm -rf /var/lib/apt/lists/*
-# 启动命令
 EXPOSE 8080
-COPY installer/run-maxkb.sh /usr/bin/
+
-RUN chmod 755 /usr/bin/run-maxkb.sh
 ENTRYPOINT ["bash", "-c"]
 CMD [ "/usr/bin/run-maxkb.sh" ]

installer/Dockerfile-dev

@@ -1,80 +0,0 @@
-FROM debian:bookworm-slim as stage-base
-ARG DEPENDENCIES="                    \
-        python3-pip                   \
-        python3.11-mini               \
-        python3.11-venv"
-
-RUN apt-get update && \
-    apt-get install -y --no-install-recommends $DEPENDENCIES && \
-    apt-get clean all  && \
-    rm -rf /var/lib/apt/lists/*
-
-COPY . /opt/maxkb/app
-RUN mkdir -p /opt/maxkb/app /opt/maxkb/model /opt/maxkb/conf && \
-    cp -f /opt/maxkb/app/installer/config.yaml /opt/maxkb/conf && \
-    rm -rf /opt/maxkb/app/ui
-
-FROM python:3.11-slim-bookworm as vector-model
-COPY installer/install_model.py install_model.py
-RUN --mount=type=cache,target=/root/.cache \
-    pip3 install --upgrade pip setuptools && \
-    pip install pycrawlers && \
-    pip install transformers && \
-    python3 install_model.py
-
-FROM node:18-bookworm-slim as web-build
-COPY ui ui
-RUN cd ui && \
-    npm install && \
-    npm run build && \
-    rm -rf ./node_modules
-
-FROM stage-base as stage-build
-WORKDIR /opt/maxkb/app
-RUN python3 -m venv /opt/py3 && \
-    pip install poetry --break-system-packages && \
-    poetry config virtualenvs.create false && \
-    . /opt/py3/bin/activate && \
-    if [ "$(uname -m)" != "x86_64" ]; then sed -i '/^torch/d' pyproject.toml; fi && \
-    poetry install
-
-FROM postgres:15.6-bookworm
-ARG DOCKER_IMAGE_TAG=dev \
-    BUILD_AT \
-    GITHUB_COMMIT
-
-ENV MAXKB_VERSION ${DOCKER_IMAGE_TAG} (build at ${BUILD_AT}, commit: ${GITHUB_COMMIT})
-
-ARG DEPENDENCIES="                    \
-        curl                          \
-        python3.11-mini               \
-        python3.11-venv               \
-        postgresql-15-pgvector"
-
-RUN ln -sf /usr/share/zoneinfo/Asia/Shanghai /etc/localtime && \
-    echo "Asia/Shanghai" > /etc/timezone && \
-    apt-get update && apt-get install -y --no-install-recommends $DEPENDENCIES && \
-    apt-get clean all  && \
-    rm -rf /var/lib/apt/lists/*
-
-COPY --from=stage-build /opt/py3 /opt/py3
-COPY --from=stage-build /opt/maxkb /opt/maxkb
-COPY --from=vector-model model /opt/maxkb/app/model
-COPY --from=web-build ui /opt/maxkb/app/ui
-
-ENV LANG=en_US.UTF-8 \
-    PATH=/opt/py3/bin:$PATH
-
-ENV POSTGRES_USER root
-ENV POSTGRES_PASSWORD Password123@postgres
-
-RUN mv /opt/maxkb/app/model/* /opt/maxkb/model && \
-    chmod 755 /opt/maxkb/app/installer/run-maxkb.sh && \
-    cp -r /opt/maxkb/model/base/hub /opt/maxkb/model/tokenizer && \
-    cp -f /opt/maxkb/app/installer/init.sql /docker-entrypoint-initdb.d && \
-    cp -f /opt/maxkb/app/installer/run-maxkb.sh /usr/bin/run-maxkb.sh
-
-EXPOSE 8080
-
-ENTRYPOINT ["bash", "-c"]
-CMD [ "/usr/bin/run-maxkb.sh" ]

installer/Dockerfile-python-pg

@@ -1,176 +1,13 @@
-FROM postgres:15.3-bullseye
+FROM postgres:15.6-bookworm
 
-ENV LANG=C.UTF-8
+ARG DEPENDENCIES="                    \
+        curl                          \
+        python3.11-mini               \
+        python3.11-venv               \
+        postgresql-15-pgvector"
 
-RUN apt-get update
+RUN ln -sf /usr/share/zoneinfo/Asia/Shanghai /etc/localtime && \
-
+    echo "Asia/Shanghai" > /etc/timezone && \
-RUN apt-get install -y postgresql-15-pgvector
+    apt-get update && apt-get install -y --no-install-recommends $DEPENDENCIES && \
-
+    apt-get clean all  && \
-COPY installer/init.sql /docker-entrypoint-initdb.d
-
-RUN ln -sf /usr/share/zoneinfo/Asia/Shanghai /etc/localtime && echo "Asia/Shanghai" > /etc/timezone
-
-# ---- install python --- #
-# ---- below content is copied from https://github.com/docker-library/python/blob/master/3.11/slim-bullseye/Dockerfile --- #
-
-# ensure local python is preferred over distribution python
-ENV PATH /usr/local/bin:$PATH
-
-# http://bugs.python.org/issue19846
-# > At the moment, setting "LANG=C" on a Linux system *fundamentally breaks Python 3*, and that's not OK.
-ENV LANG C.UTF-8
-
-# runtime dependencies
-RUN set -eux; \
-	apt-get update; \
-	apt-get install -y --no-install-recommends \
-		ca-certificates \
-		netbase \
-		tzdata \
-	; \
     rm -rf /var/lib/apt/lists/*
-
-ENV GPG_KEY A035C8C19219BA821ECEA86B64E628F8D684696D
-ENV PYTHON_VERSION 3.11.8
-
-RUN set -eux; \
-	\
-	savedAptMark="$(apt-mark showmanual)"; \
-	apt-get update; \
-	apt-get install -y --no-install-recommends \
-		dpkg-dev \
-		gcc \
-		gnupg \
-		libbluetooth-dev \
-		libbz2-dev \
-		libc6-dev \
-		libdb-dev \
-		libexpat1-dev \
-		libffi-dev \
-		libgdbm-dev \
-		liblzma-dev \
-		libncursesw5-dev \
-		libreadline-dev \
-		libsqlite3-dev \
-		libssl-dev \
-		make \
-		tk-dev \
-		uuid-dev \
-		wget \
-		xz-utils \
-		zlib1g-dev \
-	; \
-	\
-	wget -O python.tar.xz "https://www.python.org/ftp/python/${PYTHON_VERSION%%[a-z]*}/Python-$PYTHON_VERSION.tar.xz"; \
-	wget -O python.tar.xz.asc "https://www.python.org/ftp/python/${PYTHON_VERSION%%[a-z]*}/Python-$PYTHON_VERSION.tar.xz.asc"; \
-	GNUPGHOME="$(mktemp -d)"; export GNUPGHOME; \
-	gpg --batch --keyserver hkps://keys.openpgp.org --recv-keys "$GPG_KEY"; \
-	gpg --batch --verify python.tar.xz.asc python.tar.xz; \
-	gpgconf --kill all; \
-	rm -rf "$GNUPGHOME" python.tar.xz.asc; \
-	mkdir -p /usr/src/python; \
-	tar --extract --directory /usr/src/python --strip-components=1 --file python.tar.xz; \
-	rm python.tar.xz; \
-	\
-	cd /usr/src/python; \
-	gnuArch="$(dpkg-architecture --query DEB_BUILD_GNU_TYPE)"; \
-	./configure \
-		--build="$gnuArch" \
-		--enable-loadable-sqlite-extensions \
-		--enable-optimizations \
-		--enable-option-checking=fatal \
-		--enable-shared \
-		--with-lto \
-		--with-system-expat \
-		--without-ensurepip \
-	; \
-	nproc="$(nproc)"; \
-	EXTRA_CFLAGS="$(dpkg-buildflags --get CFLAGS)"; \
-	LDFLAGS="$(dpkg-buildflags --get LDFLAGS)"; \
-	LDFLAGS="${LDFLAGS:--Wl},--strip-all"; \
-	make -j "$nproc" \
-		"EXTRA_CFLAGS=${EXTRA_CFLAGS:-}" \
-		"LDFLAGS=${LDFLAGS:-}" \
-		"PROFILE_TASK=${PROFILE_TASK:-}" \
-	; \
-# https://github.com/docker-library/python/issues/784
-# prevent accidental usage of a system installed libpython of the same version
-	rm python; \
-	make -j "$nproc" \
-		"EXTRA_CFLAGS=${EXTRA_CFLAGS:-}" \
-		"LDFLAGS=${LDFLAGS:--Wl},-rpath='\$\$ORIGIN/../lib'" \
-		"PROFILE_TASK=${PROFILE_TASK:-}" \
-		python \
-	; \
-	make install; \
-	\
-	cd /; \
-	rm -rf /usr/src/python; \
-	\
-	find /usr/local -depth \
-		\( \
-			\( -type d -a \( -name test -o -name tests -o -name idle_test \) \) \
-			-o \( -type f -a \( -name '*.pyc' -o -name '*.pyo' -o -name 'libpython*.a' \) \) \
-		\) -exec rm -rf '{}' + \
-	; \
-	\
-	ldconfig; \
-	\
-	apt-mark auto '.*' > /dev/null; \
-	apt-mark manual $savedAptMark; \
-	find /usr/local -type f -executable -not \( -name '*tkinter*' \) -exec ldd '{}' ';' \
-		| awk '/=>/ { so = $(NF-1); if (index(so, "/usr/local/") == 1) { next }; gsub("^/(usr/)?", "", so); printf "*%s\n", so }' \
-		| sort -u \
-		| xargs -r dpkg-query --search \
-		| cut -d: -f1 \
-		| sort -u \
-		| xargs -r apt-mark manual \
-	; \
-	apt-get purge -y --auto-remove -o APT::AutoRemove::RecommendsImportant=false; \
-	rm -rf /var/lib/apt/lists/*; \
-	\
-	python3 --version
-
-# make some useful symlinks that are expected to exist ("/usr/local/bin/python" and friends)
-RUN set -eux; \
-	for src in idle3 pydoc3 python3 python3-config; do \
-		dst="$(echo "$src" | tr -d 3)"; \
-		[ -s "/usr/local/bin/$src" ]; \
-		[ ! -e "/usr/local/bin/$dst" ]; \
-		ln -svT "$src" "/usr/local/bin/$dst"; \
-	done
-
-# if this is called "PIP_VERSION", pip explodes with "ValueError: invalid truth value '<VERSION>'"
-ENV PYTHON_PIP_VERSION 24.0
-# https://github.com/docker-library/python/issues/365
-ENV PYTHON_SETUPTOOLS_VERSION 65.5.1
-# https://github.com/pypa/get-pip
-ENV PYTHON_GET_PIP_URL https://github.com/pypa/get-pip/raw/dbf0c85f76fb6e1ab42aa672ffca6f0a675d9ee4/public/get-pip.py
-ENV PYTHON_GET_PIP_SHA256 dfe9fd5c28dc98b5ac17979a953ea550cec37ae1b47a5116007395bfacff2ab9
-
-RUN set -eux; \
-	\
-	savedAptMark="$(apt-mark showmanual)"; \
-	apt-get update; \
-	apt-get install -y --no-install-recommends wget vim; \
-	\
-	wget -O get-pip.py "$PYTHON_GET_PIP_URL"; \
-	echo "$PYTHON_GET_PIP_SHA256 *get-pip.py" | sha256sum -c -; \
-	\
-	apt-mark auto '.*' > /dev/null; \
-	[ -z "$savedAptMark" ] || apt-mark manual $savedAptMark > /dev/null; \
-	apt-get purge -y --auto-remove -o APT::AutoRemove::RecommendsImportant=false; \
-	rm -rf /var/lib/apt/lists/*; \
-	\
-	export PYTHONDONTWRITEBYTECODE=1; \
-	\
-	python get-pip.py \
-		--disable-pip-version-check \
-		--no-cache-dir \
-		--no-compile \
-		"pip==$PYTHON_PIP_VERSION" \
-		"setuptools==$PYTHON_SETUPTOOLS_VERSION" \
-	; \
-	rm -f get-pip.py; \
-	\
-	pip --version

installer/Dockerfile-vector-model

@@ -1,6 +1,10 @@
-FROM python:3.11-slim
+FROM python:3.11-slim-bookworm as vector-model
+
 COPY installer/install_model.py install_model.py
 RUN pip3 install --upgrade pip setuptools && \
     pip install pycrawlers && \
     pip install transformers && \
     python3 install_model.py
+
+FROM scratch
+COPY --from=vector-model model /opt/maxkb/app/model