Merge branch 'release' of github.com:dataelement/bisheng into release

Author: dolphin0618

.drone.yml

@@ -40,9 +40,11 @@ steps: # 定义流水线执行步骤，这些步骤将顺序执行
     - echo $REPO
     - REPO2=$(echo $REPO | sed 's/http:\\/\\///g')
     - sed  '/apt-get/ s|$| '"$PROXY"'|' Dockerfile
+    - sed -i.bak 's/uv cache clean.*$/ /' Dockerfile
     - sed -i '6i\RUN pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple' Dockerfile
-    - sed -i '7i\RUN poetry source add --priority=supplemental foo http://'$NEXUS_PUBLIC':'$NEXUS_PUBLIC_PASSWORD'@'$REPO2'simple' Dockerfile
-    - sed -i '8i\RUN poetry source add --priority=primary qh https://pypi.tuna.tsinghua.edu.cn/simple' Dockerfile
+    - sed -i '7i\ENV UV_PIP_INDEX_URL=https://pypi.tuna.tsinghua.edu.cn/simple' Dockerfile
+    - sed -i '8i\ENV UV_DEFAULT_INDEX=https://pypi.tuna.tsinghua.edu.cn/simple' Dockerfile
+    - sed -i '9i\ENV PIP_INDEX_URL=https://pypi.tuna.tsinghua.edu.cn/simple' Dockerfile
     - cat Dockerfile
 
   - name: build_docker
@@ -56,6 +58,8 @@ steps: # 定义流水线执行步骤，这些步骤将顺序执行
         path: /var/run/docker.sock
       - name: pro-cache
         path: /root/.local/share/pypoetry
+      - name: uv-cache
+        path: /root/.cache/uv
     environment:
       http_proxy:
         from_secret: PROXY
@@ -214,8 +218,7 @@ steps: # 定义流水线执行步骤，这些步骤将顺序执行
     - REPO2=$(echo $REPO | sed 's/http:\\/\\///g')
     - sed  '/apt-get/ s|$| '"$PROXY"'|' Dockerfile
     - sed -i '6i\RUN pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple' Dockerfile
-    - sed -i '7i\RUN poetry source add --priority=supplemental foo http://'$NEXUS_PUBLIC':'$NEXUS_PUBLIC_PASSWORD'@'$REPO2'simple' Dockerfile
-    - sed -i '8i\RUN poetry source add --priority=primary qh https://pypi.tuna.tsinghua.edu.cn/simple' Dockerfile
+    - sed -i '7i\RUN export UV_PIP_INDEX_URL=https://pypi.tuna.tsinghua.edu.cn/simple' Dockerfile
     - cat Dockerfile
 
   - name: build_docker

.github/workflows/base_ci.yml

@@ -15,7 +15,7 @@ concurrency:
 
 jobs:
   build_bisheng_arm:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-22.04-arm
     # if: startsWith(github.event.ref, 'refs/tags')
     steps:
       - name: checkout
@@ -38,13 +38,15 @@ jobs:
           # DOCKERHUB_TOKEN: docker hub => Account Setting => Security 创建.
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
-          
-      # 构建 backend 并推送到 Docker hub
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v1
 
       - name: set up Docker Buildx
         uses: docker/setup-buildx-action@v3
+      
+      # because ibm-db driver not support linux arm64
+      - name: fix ibm-db lib error
+        run: |
+          # remove ibm-db lib
+          sed -i '/ibm-db*/d' ./src/backend/pyproject.toml
 
       - name: Build backend arm64 and push
         id: docker_build_backend

.github/workflows/ci.yml

@@ -83,6 +83,12 @@ jobs:
       - name: set up Docker Buildx
         uses: docker/setup-buildx-action@v3
 
+      # because ibm-db driver not support linux arm64
+      - name: fix ibm-db lib error
+        run: |
+          # remove ibm-db lib
+          sed -i '/ibm-db*/d' ./src/backend/pyproject.toml
+
       - name: Build backend and push
         id: docker_build_backend
         run: |

.gitignore

@@ -264,4 +264,6 @@ sftp-config.json
 # Docker local files
 docker/data/*
 docker/mysql/data/*
-docker/office/bisheng/*.gz
+docker/office/bisheng/*.gz
+
+CLAUDE.md

docker/docker-compose-ft.yml

@@ -1,7 +1,8 @@
 services:
   ft_server:
     container_name: bisheng-ft-server
-    image: dataelement/bisheng-ft:v0.2.0
+    image: dataelement/bisheng-ft:v0.5.0
+    shm_size: "4g"
     ports:
       - "8000:8000"
     environment:

docker/docker-compose-office.yml

@@ -0,0 +1,14 @@
+services:
+  office:
+    container_name: bisheng-office
+    image: onlyoffice/documentserver:7.1.1
+    ports:
+      - "8701:80"
+    environment:
+      TZ: Asia/Shanghai
+      JWT_ENABLED: "false"
+    volumes:
+      - ${DOCKER_VOLUME_DIRECTORY:-.}/office/bisheng:/var/www/onlyoffice/documentserver/sdkjs-plugins/bisheng
+    command: bash -c "supervisorctl restart all"
+    restart: on-failure
+

docker/docker-compose.yml

@@ -38,22 +38,9 @@ services:
       retries: 3
     restart: on-failure
 
-  office:
-    container_name: bisheng-office
-    image: onlyoffice/documentserver:7.1.1
-    ports:
-      - "8701:80"
-    environment:
-      TZ: Asia/Shanghai
-      JWT_ENABLED: "false"
-    volumes:
-      - ${DOCKER_VOLUME_DIRECTORY:-.}/office/bisheng:/var/www/onlyoffice/documentserver/sdkjs-plugins/bisheng
-    command: bash -c "supervisorctl restart all"
-    restart: on-failure
-
   backend:
     container_name: bisheng-backend
-    image: dataelement/bisheng-backend:v2.0.3
+    image: dataelement/bisheng-backend:v2.2.0
     ports:
       - "7860:7860"
     environment:
@@ -88,12 +75,10 @@ services:
         condition: service_healthy
       redis:
         condition: service_healthy
-      office:
-        condition: service_started
 
   backend_worker:
     container_name: bisheng-backend-worker
-    image: dataelement/bisheng-backend:v2.0.3
+    image: dataelement/bisheng-backend:v2.2.0
     environment:
       TZ: Asia/Shanghai
       BS_MILVUS_CONNECTION_ARGS: '{"host":"milvus","port":"19530","user":"","password":"","secure":false}'
@@ -120,12 +105,11 @@ services:
         condition: service_healthy
       redis:
         condition: service_healthy
-      office:
-        condition: service_started
+
 
   frontend:
     container_name: bisheng-frontend
-    image: dataelement/bisheng-frontend:v2.0.3
+    image: dataelement/bisheng-frontend:v2.2.0
     ports:
       - "3001:3001"
     environment:
@@ -139,7 +123,7 @@ services:
 
   elasticsearch:
     container_name: bisheng-es
-    image: docker.io/bitnami/elasticsearch:8.12.0
+    image: docker.io/bitnamilegacy/elasticsearch:8.12.0
     user: root
     ports:
       - "9200:9200"

docker/nginx/conf.d/default.conf

@@ -21,13 +21,25 @@ server {
 	 location / {
 		root /usr/share/nginx/html/platform;
 		index index.html index.htm;
+		# 禁止浏览器缓存 index.html
+		location = /index.html {
+			add_header Cache-Control "no-store, no-cache, must-revalidate, proxy-revalidate" always;
+			add_header Pragma "no-cache" always;
+			add_header Expires 0 always;
+		}
 		try_files $uri $uri/ /index.html =404;
 		add_header X-Frame-Options SAMEORIGIN;
 	}
 
 	location /workspace/ {
 		alias /usr/share/nginx/html/client/;
 		index index.html index.htm;
+		# 禁止浏览器缓存 /workspace/index.html
+		location = /workspace/index.html {
+			add_header Cache-Control "no-store, no-cache, must-revalidate, proxy-revalidate" always;
+			add_header Pragma "no-cache" always;
+			add_header Expires 0 always;
+		}
 		try_files $uri $uri/ /workspace/index.html;
 	}
 

src/backend/Dockerfile

@@ -1,11 +1,15 @@
-FROM dataelement/bisheng-backend:base.v4
+FROM dataelement/bisheng-backend:base.v8
 
 WORKDIR /app
 
 COPY ./ ./
 
-RUN poetry config virtualenvs.create false
-RUN poetry update --without dev
+# 生成并安装依赖
+RUN uv pip compile pyproject.toml --upgrade --output-file requirements.txt && \
+    uv pip install -r requirements.txt --system --no-cache-dir && \
+    uv cache clean && \
+    rm -f requirements.txt
+
 
 # patch langchain-openai lib. remove this when langchain-openai support reasoning_content
 RUN patch -p1 < /app/bisheng/patches/langchain_openai.patch /usr/local/lib/python3.10/site-packages/langchain_openai/chat_models/base.py

src/backend/alembic.ini

@@ -0,0 +1,147 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts.
+# this is typically a path given in POSIX (e.g. forward slashes)
+# format, relative to the token %(here)s which refers to the location of this
+# ini file
+script_location = ./bisheng/core/database/alembic
+
+# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
+# Uncomment the line below if you want the files to be prepended with date and time
+# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
+# for all available tokens
+file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.  for multiple paths, the path separator
+# is defined by "path_separator" below.
+prepend_sys_path = .
+
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the tzdata library which can be installed by adding
+# `alembic[tz]` to the pip requirements.
+# string value is passed to ZoneInfo()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the "slug" field
+# truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; This defaults
+# to <script_location>/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path.
+# The path separator used here should be the separator specified by "path_separator"
+# below.
+# version_locations = %(here)s/bar:%(here)s/bat:%(here)s/alembic/versions
+
+# path_separator; This indicates what character is used to split lists of file
+# paths, including version_locations and prepend_sys_path within configparser
+# files such as alembic.ini.
+# The default rendered in new alembic.ini files is "os", which uses os.pathsep
+# to provide os-dependent path splitting.
+#
+# Note that in order to support legacy alembic.ini files, this default does NOT
+# take place if path_separator is not present in alembic.ini.  If this
+# option is omitted entirely, fallback logic is as follows:
+#
+# 1. Parsing of the version_locations option falls back to using the legacy
+#    "version_path_separator" key, which if absent then falls back to the legacy
+#    behavior of splitting on spaces and/or commas.
+# 2. Parsing of the prepend_sys_path option falls back to the legacy
+#    behavior of splitting on spaces, commas, or colons.
+#
+# Valid values for path_separator are:
+#
+# path_separator = :
+# path_separator = ;
+# path_separator = space
+# path_separator = newline
+#
+# Use os.pathsep. Default configuration used for new projects.
+path_separator = os
+
+# set to 'true' to search source files recursively
+# in each "version_locations" directory
+# new in Alembic version 1.10
+# recursive_version_locations = false
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+# database URL.  This is consumed by the user-maintained env.py script only.
+# other means of configuring database URLs may be customized within the env.py
+# file.
+# sqlalchemy.url =
+
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+# hooks = black
+# black.type = console_scripts
+# black.entrypoint = black
+# black.options = -l 79 REVISION_SCRIPT_FILENAME
+
+# lint with attempts to fix using "ruff" - use the module runner, against the "ruff" module
+# hooks = ruff
+# ruff.type = module
+# ruff.module = ruff
+# ruff.options = check --fix REVISION_SCRIPT_FILENAME
+
+# Alternatively, use the exec runner to execute a binary found on your PATH
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = ruff
+# ruff.options = check --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration.  This is also consumed by the user-maintained
+# env.py script only.
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARNING
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARNING
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S