为什么选用fastgpt

支持RAG，支持本地知识库训练过程和结果的可视化

version: '3.3'
services:
  # db
  pg:
    #image: pgvector/pgvector:0.7.0-pg15 # docker hub
    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/pgvector:v0.7.0 # 阿里云
    container_name: pg
    restart: always
    ports: # 生产环境建议不要暴露
      - 5432:5432
    networks:
      - fastgpt
    environment:
      # 这里的配置只有首次运行生效。修改后，重启镜像是不会生效的。需要把持久化数据删除再重启，才有效果
      - POSTGRES_USER=username
      - POSTGRES_PASSWORD=password
      - POSTGRES_DB=postgres
    volumes:
      - ./pg/data:/var/lib/postgresql/data
  mongo:
    #image: mongo:5.0.18 # dockerhub
    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/mongo:5.0.18 # 阿里云
    # image: mongo:4.4.29 # cpu不支持AVX时候使用
    container_name: mongo
    restart: always
    ports:
      - 27017:27017
    networks:
      - fastgpt
    command: mongod --keyFile /data/mongodb.key --replSet rs0
    environment:
      - MONGO_INITDB_ROOT_USERNAME=myusername
      - MONGO_INITDB_ROOT_PASSWORD=mypassword
    volumes:
      - ./mongo/data:/data/db
    entrypoint:
      - bash
      - -c
      - |
        openssl rand -base64 128 > /data/mongodb.key
        chmod 400 /data/mongodb.key
        chown 999:999 /data/mongodb.key
        echo 'const isInited = rs.status().ok === 1
        if(!isInited){
          rs.initiate({
              _id: "rs0",
              members: [
                  { _id: 0, host: "mongo:27017" }
              ]
          })
        }' > /data/initReplicaSet.js
        # 启动MongoDB服务
        exec docker-entrypoint.sh "$$@" &

        # 等待MongoDB服务启动
        until mongo -u myusername -p mypassword --authenticationDatabase admin --eval "print('waited for connection')" > /dev/null 2>&1; do
          echo "Waiting for MongoDB to start..."
          sleep 2
        done

        # 执行初始化副本集的脚本
        mongo -u myusername -p mypassword --authenticationDatabase admin /data/initReplicaSet.js

        # 等待docker-entrypoint.sh脚本执行的MongoDB服务进程
        wait $$!

  # fastgpt
  sandbox:
    container_name: sandbox
      #image: ghcr.io/labring/fastgpt-sandbox:v4.8.21 # git
    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.21 # 阿里云
    networks:
      - fastgpt
    restart: always
  fastgpt:
    container_name: fastgpt
      #image: ghcr.io/labring/fastgpt:v4.8.21 # git
    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.8.21 # 阿里云
    ports:
      - 3000:3000
    networks:
      - fastgpt
    depends_on:
      - mongo
      - pg
      - sandbox
    restart: always
    environment:
      # 前端访问地址: http://localhost:3000
      - FE_DOMAIN=http://10.0.0.110:3000;http://10.20.0.33:3000
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
      - DEFAULT_ROOT_PSW=123456
      # AI模型的API地址哦。务必加 /v1。这里默认填写了OneApi的访问地址。
      - OPENAI_BASE_URL=http://oneapi:3000/v1
      # AI模型的API Key。（这里默认填写了OneAPI的快速默认key，测试通后，务必及时修改）
      - CHAT_API_KEY=sk-123456
      # 数据库最大连接数
      - DB_MAX_LINK=30
      # 登录凭证密钥
      - TOKEN_KEY=any
      # root的密钥，常用于升级时候的初始化请求
      - ROOT_KEY=root_key
      # 文件阅读加密
      - FILE_TOKEN_KEY=filetoken
      # MongoDB 连接参数. 用户名myusername,密码mypassword。
      - MONGODB_URI=mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
      # pg 连接参数
      - PG_URL=postgresql://username:password@pg:5432/postgres
      # sandbox 地址
      - SANDBOX_URL=http://sandbox:3000
      # 日志等级: debug, info, warn, error
      - LOG_LEVEL=info
      - STORE_LOG_LEVEL=warn
      # 工作流最大运行次数
      - WORKFLOW_MAX_RUN_TIMES=1000
      # 批量执行节点，最大输入长度
      - WORKFLOW_MAX_LOOP_TIMES=100
      # 自定义跨域，不配置时，默认都允许跨域（多个域名通过逗号分割）
      - ALLOWED_ORIGINS=
      # 是否开启IP限制，默认不开启
      - USE_IP_LIMIT=false
    volumes:
      - ./config.json:/app/data/config.json

  # oneapi
  oneapi:
    container_name: oneapi
    image: ghcr.io/songquanpeng/one-api:v0.6.7
    #image: registry.cn-hangzhou.aliyuncs.com/fastgpt/one-api:v0.6.7 # 阿里云
    ports:
      - 3001:3000
    networks:
      - fastgpt
    restart: always
    environment:
      # mysql 连接参数
      - SQL_DSN=root:123456@tcp(10.0.0.110:3306)/oneapi
      # 登录凭证加密密钥
      - SESSION_SECRET=123456
      # 内存缓存
      - MEMORY_CACHE_ENABLED=true
      # 启动聚合更新，减少数据交互频率
      - BATCH_UPDATE_ENABLED=true
      # 聚合更新时长
      - BATCH_UPDATE_INTERVAL=10
      # 初始化的 root 密钥（建议部署完后更改，否则容易泄露）
      - INITIAL_ROOT_TOKEN=123456
    volumes:
      - ./oneapi:/data
networks:
  fastgpt:

为什么选用anythingllm

可以邀请用户使用，并且比openwebui速度快那么一丢丢，可以后台管理看到用户的使用情况，方便后期升级优化

为什么选用ollama

方便快捷的调用各种AI

version: '3.8'
services:
  deepseek:
    container_name: deepseek
    image: ollama/ollama:0.5.8
    volumes:
      - /usr/share/ollama/.ollama:/root/.ollama
    ports:
      - 11434:11434
    restart: unless-stopped
    environment:
      NVIDIA_VISIBLE_DEVICES: all
    deploy:
      resources:
        reservations:
          devices:
            - driver: "nvidia"
              count: "all"
              capabilities: ["gpu"]
              
  anythingllm:
    container_name: anythingllm
    image: mintplexlabs/anythingllm
    ports:
      - "3002:3001"
    cap_add:
      - SYS_ADMIN
    volumes:
      - ./anythingllm/.env:/app/server/.env
      - ./anythingllm/storage:/app/server/storage
    environment:
      STORAGE_DIR: /app/server/storage
      OLLAMA_BASE_URL: http://deepseek:11434
      NVIDIA_VISIBLE_DEVICES: all
    deploy:
      resources:
        reservations:
          devices:
            - driver: "nvidia"
              count: "all"
              capabilities: ["gpu"]

anythingllm/.env

# Auto-dump ENV from system call on 03:42:00 GMT+0000 (Coordinated Universal Time)
LLM_PROVIDER='generic-openai'
EMBEDDING_MODEL_PREF='bge-m3:latest'
LOCAL_AI_BASE_PATH='http://10.0.0.110:3000/api/v1'
LOCAL_AI_MODEL_TOKEN_LIMIT='8192'
LOCAL_AI_API_KEY='fastgpt-123456'
OLLAMA_BASE_PATH='http://deepseek:11434'
OLLAMA_MODEL_PREF='deepseek-r1_32b_max:latest'
OLLAMA_MODEL_TOKEN_LIMIT='131072'
OLLAMA_PERFORMANCE_MODE='maximum'
OLLAMA_KEEP_ALIVE_TIMEOUT='-1'
GENERIC_OPEN_AI_BASE_PATH='http://10.0.0.110:3000/api/v1'
GENERIC_OPEN_AI_MODEL_PREF='太原理工大学重庆招生负责人'
GENERIC_OPEN_AI_MODEL_TOKEN_LIMIT='8192'
GENERIC_OPEN_AI_API_KEY='fastgpt-123456'
GENERIC_OPEN_AI_MAX_TOKENS='10240'
EMBEDDING_ENGINE='native'
EMBEDDING_BASE_PATH='http://deepseek:11434'
EMBEDDING_MODEL_MAX_CHUNK_LENGTH='8192'
VECTOR_DB='lancedb'
MILVUS_ADDRESS='http://localhost:19530'
MILVUS_USERNAME='admin'
MILVUS_PASSWORD='123456'
JWT_SECRET='my-random-string-for-seeding'
STORAGE_DIR='/app/server/storage'
SERVER_PORT='3001'
SIG_KEY='passphrase'
SIG_SALT='salt'

fastgpt配置ollama模型

首先在oneapi上配置渠道

第二步在oneapi上配置令牌：选择永不过期

最后在fastgpt上配置ollama

如何在anythingllm配置fastgpt的api