本地docker及 docker-compose版本
安裝參考：
- 實踐筆記-docker安裝及配置鏡像源
- 實踐筆記-docker-compose安裝
1.下載源碼
git clone https://github.com/infiniflow/ragflow.git
2.運行docker-compose拉取鏡像
cd ragflow/docker
docker-compose up -d
3.啟動報錯問題解決
- mysql啟動報錯：這個是由于我之前本地有個8.4版本的。直接刪除容器卷上的數據就可以了
- docker網絡問題
不知道是不是wsl的原因，docker沒有創建網絡，手動創建的網絡，幾個容器服務也是不能互通，打印ragflow-server服務的日志就可以看到了（這個以后有時間再看看咋回事，現在先把服務跑起來要緊），所以我全部切成本地網絡
切換后的docker-compose文件編排內容如下：# 查詢網絡 docker network ls # 創建網絡 docker network create ragflow # 查看網絡信息 docker network inspect ragflow # 移除網絡 docker network rm ragflow - docker-compose-all.yaml (命名隨意)
- 因為我本地之前拉取過其他版本的es、minio，所以就直接用之前拉取的鏡像
- service_conf_host.yaml.template 用本地網絡涉及到端口調整，所以我加了這個文件掛載
services:es01:container_name: ragflow-es-01profiles:- elasticsearch#這里用了我本地的esimage: docker.elastic.co/elasticsearch/elasticsearch:8.13.2volumes:- esdata01:/usr/share/elasticsearch/dataports:- ${ES_PORT}:9200env_file: .envenvironment:- node.name=es01- ELASTIC_PASSWORD=${ELASTIC_PASSWORD}- bootstrap.memory_lock=false- discovery.type=single-node- xpack.security.enabled=true- xpack.security.http.ssl.enabled=false- xpack.security.transport.ssl.enabled=false- cluster.routing.allocation.disk.watermark.low=5gb- cluster.routing.allocation.disk.watermark.high=3gb- cluster.routing.allocation.disk.watermark.flood_stage=2gb- TZ=${TIMEZONE}mem_limit: ${MEM_LIMIT}ulimits:memlock:soft: -1hard: -1healthcheck:test: ["CMD-SHELL", "curl http://localhost:9200"]interval: 10stimeout: 10sretries: 120network_mode: hostrestart: on-failuremysql:image: mysql:8.0.39container_name: ragflow-mysqlenv_file: .envenvironment:- MYSQL_ROOT_PASSWORD=${MYSQL_PASSWORD}- TZ=${TIMEZONE}command:--max_connections=1000--character-set-server=utf8mb4--collation-server=utf8mb4_unicode_ci--default-authentication-plugin=mysql_native_password--tls_version="TLSv1.2,TLSv1.3"--port=${MYSQL_PORT}--init-file /data/application/init.sqlvolumes:- mysql_data:/var/lib/mysql- ./init.sql:/data/application/init.sqlnetwork_mode: hosthealthcheck:test: ["CMD", "mysqladmin" ,"ping", "-uroot", "-p${MYSQL_PASSWORD}"]interval: 10stimeout: 10sretries: 3restart: on-failureminio:#這里用了我本地的minioimage: minio/minio:RELEASE.2023-03-20T20-16-18Zcontainer_name: ragflow-miniocommand: server --console-address ":9001" /dataports:- ${MINIO_PORT}:9000- ${MINIO_CONSOLE_PORT}:9001env_file: .envenvironment:- MINIO_ROOT_USER=${MINIO_USER}- MINIO_ROOT_PASSWORD=${MINIO_PASSWORD}- TZ=${TIMEZONE}volumes:- minio_data:/datanetwork_mode: hostrestart: on-failureredis:image: valkey/valkey:8container_name: ragflow-rediscommand: redis-server --requirepass ${REDIS_PASSWORD} --port ${REDIS_PORT} --maxmemory 128mb --maxmemory-policy allkeys-lruenv_file: .envvolumes:- redis_data:/datanetwork_mode: hostrestart: on-failureragflow:depends_on:mysql:condition: service_healthyimage: ${RAGFLOW_IMAGE}container_name: ragflow-server # ports: # - ${SVR_HTTP_PORT}:9380 # - 81:80 # - 8443:443 # - 5688:5678 # - 5689:5679volumes:- ./ragflow-logs:/ragflow/logs- ./nginx/ragflow.conf:/etc/nginx/conf.d/ragflow.conf- ./nginx/proxy.conf:/etc/nginx/proxy.conf- ./nginx/nginx.conf:/etc/nginx/nginx.conf- ../history_data_agent:/ragflow/history_data_agent#這里掛載了service_conf.yaml.template- ./service_conf_host.yaml.template:/ragflow/conf/service_conf.yaml.templateenv_file: .envenvironment:- TZ=${TIMEZONE}- HF_ENDPOINT=${HF_ENDPOINT}- MACOS=${MACOS}network_mode: hostrestart: on-failureextra_hosts:# 這里改成docker的ip- "host.docker.internal:172.17.0.1"#- "host.docker.internal:host-gateway" volumes:esdata01:driver: localinfinity_data:driver: localmysql_data:driver: localminio_data:driver: localredis_data:driver: local - service_conf_host.yaml.template
（參考原來的service_conf.yaml.template進行調整即可）ragflow:host: ${RAGFLOW_HOST:-0.0.0.0}http_port: 9380 mysql:name: '${MYSQL_DBNAME:-rag_flow}'user: '${MYSQL_USER:-root}'password: '${MYSQL_PASSWORD:-infini_rag_flow}'host: '${MYSQL_HOST:-mysql}'port: ${MYSQL_PORT:-3306}max_connections: 100stale_timeout: 30 minio:user: '${MINIO_USER:-rag_flow}'password: '${MINIO_PASSWORD:-infini_rag_flow}'host: '${MINIO_HOST:-localhost}:9000' es:hosts: 'http://${ES_HOST:-es01}:9200'username: '${ES_USER:-elastic}'password: '${ELASTIC_PASSWORD:-infini_rag_flow}' infinity:uri: '${INFINITY_HOST:-infinity}:23817'db_name: 'default_db' redis:db: 1password: '${REDIS_PASSWORD:-infini_rag_flow}'host: '${REDIS_HOST:-redis}:6379'
- ragflow.conf
這個的話，是因為我切換成本地網絡導致的，直接修改成localhost就行了。
ragflow-server打印的日志，第一二行就會有ragflow.conf報錯提醒。之前忘記截圖了。
修改完之后重啟服務就行了。
- 本次可能用到的docker命令：
# 啟動所有服務 docker-compose -f docker-compose-all.yaml up -d # 關閉所有服務 docker-compose -f docker-compose-all.yaml down # 查看所有運行容器 docker ps # 容器日志打印 docker logs -f ragflow-server # 容器日志打印最新的300行 # docker logs -f --tail 300 ragflow-server # 刪除容器 # docker rm -f ragflow-server # 啟動單個容器服務 docker-compose -f docker-compose-all.yaml up -d ragflow
4.訪問：直接localhost就可以訪問到了
- 注冊賬號：隨便注冊一個。
注冊的數據信息在數據庫里可以查看到
- 配置模型（我用的本地ollama）
ollama部署大模型的可以參考：使用Ollama在本地運行AI大模型（gemma、deepseek等）及UI整合（chatbox、Cherry Studio、Page Assist等）
- 創建知識庫
一切都正常。
