bisheng系列（三）- 本地部署（后端 1.2版本）

一、导读

环境：Ubuntu 24.04、open Euler 23.03、Windows 11、WSL 2、Python 3.10 、bisheng 1.2.0

背景：需要bisheng二开商用，故而此处进行本地部署，便于后期调试开发

时间：20250612

说明：bisheng的1.2版本部署与1.1.1有些许不同，故另开一章

注意：本节基于下面章节的内容，如有疑问，请阅读：

bisheng系列（一）- 本地部署（Docker）

bisheng系列（二）- 本地部署（前后端）

二、停止前后端的docker

bisheng共计9个容器，需要独立代码启动前后端，则需要将前后端的容器停止

1、停止并删除所有容器

命令：

复制代码

docker-compose down

效果

复制代码

jack@Laptop-L14-gen4:~/bisheng-blog/bisheng/docker/bisheng-main/docker$ docker-compose down
Stopping bisheng-frontend  ... done
Stopping bisheng-backend   ... done
Stopping milvus-standalone ... done
Stopping bisheng-es        ... done
Stopping bisheng-office    ... done
Stopping milvus-etcd       ... done
Stopping bisheng-mysql     ... done
Stopping bisheng-redis     ... done
Stopping milvus-minio      ... done
Removing bisheng-frontend  ... done
Removing bisheng-backend   ... done
Removing milvus-standalone ... done
Removing bisheng-es        ... done
Removing bisheng-office    ... done
Removing milvus-etcd       ... done
Removing bisheng-mysql     ... done
Removing bisheng-redis     ... done
Removing milvus-minio      ... done
Removing network docker_default
jack@Laptop-L14-gen4:~/bisheng-blog/bisheng/docker/bisheng-main/docker$ docker ps -a
CONTAINER ID   IMAGE           COMMAND                  CREATED       STATUS                     PORTS                                                           NAMES
5257cf9b2426   qdrant/qdrant   "./entrypoint.sh"        3 weeks ago   Exited (255) 2 weeks ago   0.0.0.0:6333-6334->6333-6334/tcp, :::6333-6334->6333-6334/tcp   distracted_lamport
b28179c3b79b   qdrant/qdrant   "./entrypoint.sh"        3 weeks ago   Exited (255) 3 weeks ago   0.0.0.0:6333-6334->6333-6334/tcp, :::6333-6334->6333-6334/tcp   bold_beaver
b00d21f614f7   hello-world     "/hello"                 3 weeks ago   Exited (0) 3 weeks ago                                                                     objective_khayyam
114b2a816fae   ubuntu1:8080    "/bin/sh -c 'npm i &..."   7 weeks ago   Exited (255) 7 weeks ago   0.0.0.0:8080->8080/tcp, :::8080->8080/tcp                       light_house

通过上述命令说明，bisheng的9个容器停止并删除成功

2、配置docker-compse

通过编辑docker-compose.yml文件，删除前后端的启动项，修改后内容如下：

python 复制代码

services:
  mysql:
    container_name: bisheng-mysql
    image: mysql:8.0
 
    ports:
      - "3306:3306"
    environment:
      MYSQL_ROOT_PASSWORD: "1234"  # 数据库密码，如果修改需要同步修改bisheng/congfig/config.yaml配置database_url的mysql连接密码
      MYSQL_DATABASE: bisheng
      TZ: Asia/Shanghai
    volumes:
      - ${DOCKER_VOLUME_DIRECTORY:-.}/mysql/conf/my.cnf:/etc/mysql/my.cnf
      - ${DOCKER_VOLUME_DIRECTORY:-.}/mysql/data:/var/lib/mysql
    healthcheck:
      test: ["CMD-SHELL", "exit | mysql -u root -p$$MYSQL_ROOT_PASSWORD"]
      start_period: 30s
      interval: 20s
      timeout: 10s
      retries: 4
    restart: on-failure
 
  redis:
    container_name: bisheng-redis
    image: redis:7.0.4
    ports:
      - "6379:6379"
    environment:
      TZ: Asia/Shanghai
    volumes:
      - ${DOCKER_VOLUME_DIRECTORY:-.}/data/redis:/data
      - ${DOCKER_VOLUME_DIRECTORY:-.}/redis/redis.conf:/etc/redis.conf
    command: redis-server /etc/redis.conf
    healthcheck:
      test: ["CMD-SHELL", 'redis-cli ping|grep -e "PONG\|NOAUTH"']
      interval: 10s
      timeout: 5s
      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
 
  elasticsearch:
    container_name: bisheng-es
    image: docker.io/bitnami/elasticsearch:8.12.0
    user: root
    ports:
      - "9200:9200"
      - "9300:9300"
    environment:
      TZ: Asia/Shanghai
    volumes:
      - ${DOCKER_VOLUME_DIRECTORY:-.}/data/es:/bitnami/elasticsearch/data
    restart: on-failure
 
  etcd:
    container_name: milvus-etcd
    image: quay.io/coreos/etcd:v3.5.5
    environment:
      ETCD_AUTO_COMPACTION_MODE: revision
      ETCD_AUTO_COMPACTION_RETENTION: "1000"
      ETCD_QUOTA_BACKEND_BYTES: "4294967296"
      ETCD_SNAPSHOT_COUNT: "50000"
      TZ: Asia/Shanghai
    volumes:
      - ${DOCKER_VOLUME_DIRECTORY:-.}/data/milvus-etcd:/etcd
    command: etcd -advertise-client-urls=http://127.0.0.1:2379 -listen-client-urls http://0.0.0.0:2379 --data-dir /etcd
    restart: on-failure
    healthcheck:
      test: ["CMD", "etcdctl", "endpoint", "health"]
      interval: 30s
      timeout: 20s
      retries: 3
 
  minio:
    container_name: milvus-minio
    image: minio/minio:RELEASE.2023-03-20T20-16-18Z
    environment:
      MINIO_ACCESS_KEY: minioadmin
      MINIO_SECRET_KEY: minioadmin
    ports:
      - "9100:9000"
      - "9101:9001"
    volumes:
      - /etc/localtime:/etc/localtime:ro
      - ${DOCKER_VOLUME_DIRECTORY:-.}/data/milvus-minio:/minio_data
    command: minio server /minio_data --console-address ":9001"
    restart: on-failure
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:9000/minio/health/live"]
      interval: 30s
      timeout: 20s
      retries: 3
 
  milvus:
    container_name: milvus-standalone
    image: milvusdb/milvus:v2.3.3
    command: ["milvus", "run", "standalone"]
    security_opt:
    - seccomp:unconfined
    environment:
      ETCD_ENDPOINTS: etcd:2379
      MINIO_ADDRESS: minio:9000
    volumes:
      - /etc/localtime:/etc/localtime:ro
      - ${DOCKER_VOLUME_DIRECTORY:-.}/data/milvus:/var/lib/milvus
    restart: on-failure
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:9091/healthz"]
      start_period: 90s
      interval: 30s
      timeout: 20s
      retries: 3
    ports:
      - "19530:19530"
      - "9091:9091"
    depends_on:
      - etcd
      - minio

3、启动其余容器

python 复制代码

jack@Laptop-L14-gen4:~/bisheng-blog/bisheng/docker/bisheng-main/docker$ docker-compose up -d
Creating network "docker_default" with the default driver
Creating milvus-etcd    ... done
Creating bisheng-redis  ... done
Creating bisheng-mysql  ... done
Creating bisheng-office ... done
Creating milvus-minio   ... done
Creating bisheng-es     ... done
Creating milvus-standalone ... done

4、前后端代码

前后端的代码分别时：

后端：bisheng/src/backend

前端：bisheng/src/frontend

三、后端启动

通过修改部分文件，使后端可以连接到相关的容器服务

后端在open Euler 23.03启动，我使用vscode来修改相关文件

1、克隆源码

python 复制代码

git clone https://github.com/dataelement/bisheng.git

2、安装相关环境

python 复制代码

sudo yum -y install python3-pip python3-devel  gcc g++

3、安装poetry

python 复制代码

pip install poetry==1.8.2

4、项目环境

python 复制代码

# 在当前项目根目录下生成环境
poetry config virtualenvs.create true
 
# 安装环境所需的模块
poetry install

# 在openEuler环境需要该包
poetry add opencv-python-headless

安装后，看下安装过程是否存在异常，如下为正常

python 复制代码

...... 
 - Installing types-pillow (9.5.0.6)
 - Installing types-pyyaml (6.0.12.20250516)
 - Installing types-requests (2.32.0.20250515)
......
 
Writing lock file
 
Installing the current project: bisheng (1.1.1)

5、配置文件

此处配置文件特指其余七个容器的连接配置

将/bisheng/docker/bisheng/config/config.yaml 复制到指定目录下，并修改如下：

python 复制代码

# 修改后的文件内容，删除了注释的内容

database_url:
  "mysql+pymysql://root:gAAAAABlp4b4c59FeVGF_OQRVf6NOUIGdxq8246EBD-b0hdK_jVKRs1x4PoAn0A6C5S6IiFKmWn0Nm5eBUWu-7jxcqw6TiVjQA==@0.0.0.0:3306/bisheng?charset=utf8mb4"

# 缓存配置  redis://[[username]:[password]]@localhost:6379/0
# 普通模式:
redis_url: "redis://0.0.0.0:6379/1"

# celery的broken地址
celery_redis_url: "redis://0.0.0.0:6379/2"

# 知识库的milvus和es配置  支持使用 !env ${PATH} 填写环境变量的值, 若环境变量不存在则会报错
vector_stores:
  milvus:
    connection_args: '{"host":"0.0.0.0","port":"9530","user":"","password":"","secure":false}'
    is_partition: true
    partition_suffix: "1"
  elasticsearch:
    url: 'http://0.0.0.0:9200'
    ssl_verify: '{"basic_auth": ("elastic", "elastic")}'


# 对象存储， 目前只支持minio
object_storage:
  type: minio
  minio:
    schema: false
    cert_check: false
    endpoint: '0.0.0.0:9100'
    sharepoint: '0.0.0.0:9100'
    access_key: minioadmin
    secret_key: minioadmin

environment:
  env: dev
  uns_support: ['png','jpg','jpeg','bmp','doc', 'docx', 'ppt', 'pptx', 'xls', 'xlsx', 'txt', 'md', 'html', 'pdf', 'csv', 'tiff']

# 可根据loguru的文档配置不同 handlers
logger_conf:
  # 默认输出到sys.stdout的日志级别, 大于等于此级别都会输出
  level: DEBUG
  # 默认输出格式
  format: '<level>[{time:YYYY-MM-DD HH:mm:ss.SSSSSS}] [{level.name} process-{process.id}-{thread.id} {name}:{line}]</level> - <level>trace={extra[trace_id]} {message}</level>'
  # 参考loguru.add()中的参数可以配置多个handler
  handlers:
      # 文件路径，支持插入一些系统环境变量，若环境变量不存在则置空。例如 HOSTNAME: 主机名。后端会处理环境变量的替换
    - sink: "/home/jack/bisheng_11/backend/data/bisheng.log"
      # 日志级别
      level: INFO
      # 日志格式化函数，extra内支持trace_id
      format: '<level>[{time:YYYY-MM-DD HH:mm:ss.SSSSSS}] [{level.name} process-{process.id}-{thread.id} {name}:{line}]</level> - <level>trace={extra[trace_id]} {message}</level>'
      # 每天的几点进行切割
      rotation: "00:00"
      retention: "3 Days"
      enqueue: ture
    - sink: "/home/jack/bisheng_11/backend/data/statistic.log"
      level: INFO
      # 和原生不一样，后端会将配置使用eval()执行转为函数用来过滤特定日志级别。推荐lambda
      filter: "lambda record: record['level'].name == 'INFO' and record['message'].startswith('k=s')"
      format: "[{time:YYYY-MM-DD HH:mm:ss.SSSSSS}]|{level}|BISHENG|{extra[trace_id]}||{process.id}|{thread.id}|||#EX_ERR:POS={name},line {line},ERR=500,EMSG={message}"
      rotation: "00:00"
      retention: "3 Days"
      enqueue: ture

修改目的是将链接修改为0.0.0.0:端口，由于之前使用docker配置可以连接，但是当前由于使用代码直接启动，无法识别http://mysql:3306这种链接，故而需要修改

日志路径修改是为了保证权限的问题

编辑bisheng/src/backend/bisheng/api/services/assistant_agent.py，修改文件路径

python 复制代码

# 原内容
    async def record_chat_history(self, message: List[Any]):
        # 记录助手的聊天历史
        if not os.getenv('BISHENG_RECORD_HISTORY'):
            return
        try:
            os.makedirs('/app/data/history', exist_ok=True)
            with open(f'/app/data/history/{self.assistant.id}_{time.time()}.json',
 
# 修改后
    async def record_chat_history(self, message: List[Any]):
        # 记录助手的聊天历史
        if not os.getenv('BISHENG_RECORD_HISTORY'):
            return
        try:
            os.makedirs('/home/jack/bisheng/src/backend/data/history', exist_ok=True)
            with open(f'/home/jack/bisheng/src/backend/data/history/{self.assistant.id}_{time.time()}.json',

处理fastapi_jwt_auth、langchain_openai的兼容性

python 复制代码

patch -p1 < ./bisheng/patches/fastapi_jwt_auth.patch ./.venv/lib/python3.10/site-packages/fastapi_jwt_auth/config.py

patch -p1 < ./bisheng/patches/langchain_openai.patch ./.venv/lib/python3.10/site-packages/langchain_openai/chat_models/base.py

6、启动项目

python 复制代码

uvicorn bisheng.main:app --host 0.0.0.0 --port 7860

成功如下：

python 复制代码

.
.
.
INFO:     Started server process [64315]
INFO:     Waiting for application startup.
[2025-05-19 11:25:20.152105] [2025-05-19 11:25:20.151985] [DEBUG process-64315-139958058770496 bisheng.interface.utils:91] - trace=1 Setting up LLM caching with InMemoryCache                                                                                                                              
[2025-05-19 11:25:20.153851] [2025-05-19 11:25:20.153779] [INFO process-64315-139958058770496 bisheng.interface.utils:93] - trace=1 LLM caching setup with InMemoryCache                                                                                                                                    
[2025-05-19 11:25:20.189322] [2025-05-19 11:25:20.189129] [DEBUG process-64315-139958058770496 bisheng.database.service:59] - trace=1 Creating database and tables                                                                                                                                          
[2025-05-19 11:25:20.564080] [2025-05-19 11:25:20.563913] [DEBUG process-64315-139958058770496 bisheng.database.service:79] - trace=1 Database and tables created successfully                                                                                                                              
INFO:     Application startup complete.
INFO:     Uvicorn running on http://0.0.0.0:7860 (Press CTRL+C to quit)

四、前端启动

略（参考上一节中的前端配置即可）