# yaml-language-server: $schema=https://schema.zeabur.app/template.json apiVersion: zeabur.com/v1 kind: Template metadata: name: RAGFlow spec: description: An open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding. icon: https://avatars.githubusercontent.com/u/69962740?s=200&v=4 variables: - key: PUBLIC_DOMAIN type: DOMAIN name: Domain description: What is the domain you want for your RAGFlow? tags: - AI/ML - RAG - Knowledge Base readme: |- ## What is RAGFlow? RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding. It offers a streamlined RAG workflow that is meticulously designed for businesses of any scale. ## Features - **Deep Document Understanding**: Advanced document parsing and chunking capabilities - **Template-based Chunking**: Intelligent content segmentation - **Grounded Citations**: Trustworthy question-answering with verifiable sources - **Multiple Document Formats**: Support for PDF, DOCX, PPT, Excel, images, and more - **Compatibility**: Works with heterogeneous model ecosystems including Ollama - **Modular Architecture**: Core service with optional additional components ## Architecture This template includes: - **RAGFlow Core**: Main application service (required) - **MySQL**: Database for storing metadata and configurations (required) - **Optional Services**: Redis, MinIO, Elasticsearch, OpenSearch, and Infinity (can be deployed separately if needed) ## Environment Variables The following environment variables will be automatically configured: - `${RAGFLOW_URL}`: The URL of the RAGFlow service - `${MYSQL_CONNECTION_STRING}`: MySQL database connection string - `${REDIS_CONNECTION_STRING}`: Redis connection string - `${MINIO_ENDPOINT}`: MinIO object storage endpoint - `${ELASTICSEARCH_URL}`: Elasticsearch search engine URL - `${OPENSEARCH_URL}`: OpenSearch alternative search engine URL - `${INFINITY_URL}`: Infinity vector database URL ## Getting Started 1. After deployment, access RAGFlow through the provided URL 2. Create your first knowledge base 3. Upload documents (PDF, DOCX, images, etc.) 4. Start asking questions based on your documents ## Default Credentials - RAGFlow admin interface will be accessible without initial authentication - Database and storage credentials are automatically generated and configured services: - name: ragflow icon: https://avatars.githubusercontent.com/u/69962740?s=200&v=4 dependencies: - mysql template: PREBUILT spec: id: ragflow source: image: infiniflow/ragflow:v0.20.3-slim ports: - id: web port: 80 type: HTTP volumes: - id: logs dir: /ragflow/logs env: DOC_ENGINE: default: elasticsearch ELASTIC_PASSWORD: default: ${ZEABUR_ELASTICSEARCH_PASSWORD} ES_HOST: default: elasticsearch.zeabur.internal ES_PORT: default: "9200" HF_ENDPOINT: default: https://hf-mirror.com INFINITY_HOST: default: infinity.zeabur.internal INFINITY_HTTP_PORT: default: "23820" INFINITY_PSQL_PORT: default: "5432" INFINITY_THRIFT_PORT: default: "23817" MINIO_HOST: default: minio.zeabur.internal MINIO_PASSWORD: default: ${ZEABUR_MINIO_PASSWORD} MINIO_PORT: default: "9000" MINIO_USER: default: minio MYSQL_DBNAME: default: ${ZEABUR_MYSQL_DATABASE} MYSQL_HOST: default: ${ZEABUR_MYSQL_HOST} MYSQL_PASSWORD: default: ${ZEABUR_MYSQL_PASSWORD} MYSQL_PORT: default: ${ZEABUR_MYSQL_PORT} OPENSEARCH_HOST: default: opensearch.zeabur.internal OPENSEARCH_PASSWORD: default: ${ZEABUR_OPENSEARCH_PASSWORD} OPENSEARCH_PORT: default: "9201" REDIS_HOST: default: redis.zeabur.internal REDIS_PASSWORD: default: ${ZEABUR_REDIS_PASSWORD} REDIS_PORT: default: "6379" SVR_HTTP_PORT: default: "9380" TZ: default: Asia/Shanghai configs: - path: /etc/nginx/proxy.conf template: | proxy_set_header Host $host; proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for; proxy_set_header X-Forwarded-Proto $scheme; proxy_http_version 1.1; proxy_set_header Connection ""; proxy_buffering off; proxy_read_timeout 3600s; proxy_send_timeout 3600s; proxy_buffer_size 1024k; proxy_buffers 16 1024k; proxy_busy_buffers_size 2048k; proxy_temp_file_write_size 2048k; permission: null envsubst: null - path: /etc/nginx/conf.d/ragflow.conf template: | server { listen 80; server_name _; root /ragflow/web/dist; gzip on; gzip_min_length 1k; gzip_comp_level 9; gzip_types text/plain application/javascript application/x-javascript text/css application/xml text/javascript application/x-httpd-php image/jpeg image/gif image/png; gzip_vary on; gzip_disable "MSIE [1-6]\."; location ~ ^/(v1|api) { proxy_pass http://127.0.0.1:9380; include proxy.conf; } location / { index index.html; try_files $uri $uri/ /index.html; } # Cache-Control: max-age~@~AExpires location ~ ^/static/(css|js|media)/ { expires 10y; access_log off; } } permission: null envsubst: null - path: /etc/nginx/nginx.conf template: | user root; worker_processes auto; error_log /var/log/nginx/error.log notice; pid /var/run/nginx.pid; events { worker_connections 1024; } http { include /etc/nginx/mime.types; default_type application/octet-stream; log_format main '$remote_addr - $remote_user [$time_local] "$request" ' '$status $body_bytes_sent "$http_referer" ' '"$http_user_agent" "$http_x_forwarded_for"'; access_log /var/log/nginx/access.log main; sendfile on; keepalive_timeout 65; client_max_body_size 1024M; include /etc/nginx/conf.d/ragflow.conf; } permission: null envsubst: null - path: /ragflow/conf/service_conf.yaml template: "ragflow:\n host: 0.0.0.0\n http_port: 9380\n \nmysql:\n name: ${ZEABUR_MYSQL_DATABASE}\n user: root\n password: ${ZEABUR_MYSQL_PASSWORD}\n host: ${ZEABUR_MYSQL_HOST}\n port: ${ZEABUR_MYSQL_PORT}\n max_connections: 900\n stale_timeout: 300\n max_allowed_packet: 1073741824\n \nminio:\n user: ${MINIO_USER}\n password: ${MINIO_PASSWORD}\n host: ${MINIO_HOST}:${MINIO_PORT}\n \nes:\n hosts: http://${ES_HOST}:${ES_PORT}\n username: elastic\n password: ${ELASTIC_PASSWORD}\n \nos:\n hosts: http://${OPENSEARCH_HOST}:${OPENSEARCH_PORT}\n username: admin\n password: ${OPENSEARCH_PASSWORD}\n \ninfinity:\n uri: ${INFINITY_HOST}:${INFINITY_THRIFT_PORT}\n db_name: default_db\n \nredis:\n db: 1\n password: ${REDIS_PASSWORD}\n host: ${REDIS_HOST}:${REDIS_PORT}\n" permission: null envsubst: true - path: /ragflow/entrypoint.sh template: | #!/bin/bash set -e # Remove default nginx config rm -f /etc/nginx/conf.d/default.conf # Start nginx nginx -g "daemon on;" # Wait for nginx to start sleep 2 # Start RAGFlow cd /ragflow exec python api/ragflow_server.py permission: 493 envsubst: null domainKey: PUBLIC_DOMAIN - name: mysql icon: https://raw.githubusercontent.com/zeabur/service-icons/main/marketplace/mysql.svg template: PREBUILT spec: id: mysql source: image: mysql:8.0 ports: - id: database port: 3306 type: TCP volumes: - id: data dir: /var/lib/mysql instructions: - title: Command to connect to your MySQL content: mysqlsh --sql --host=${PORT_FORWARDED_HOSTNAME} --port=${DATABASE_PORT_FORWARDED_PORT} --user=${MYSQL_USERNAME} --password=${MYSQL_PASSWORD} --schema=${MYSQL_DATABASE} - title: MySQL username content: ${MYSQL_USERNAME} - title: MySQL password content: ${MYSQL_PASSWORD} - title: MySQL database content: ${MYSQL_DATABASE} - title: MySQL host content: ${PORT_FORWARDED_HOSTNAME} - title: MySQL port content: ${DATABASE_PORT_FORWARDED_PORT} env: MYSQL_DATABASE: default: zeabur expose: true MYSQL_HOST: default: ${CONTAINER_HOSTNAME} expose: true MYSQL_PASSWORD: default: ${MYSQL_ROOT_PASSWORD} expose: true MYSQL_PORT: default: ${DATABASE_PORT} expose: true MYSQL_ROOT_PASSWORD: default: ${PASSWORD} MYSQL_USERNAME: default: root expose: true ZEABUR_MYSQL_DATABASE: default: ${MYSQL_DATABASE} expose: true ZEABUR_MYSQL_HOST: default: ${MYSQL_HOST} expose: true ZEABUR_MYSQL_PASSWORD: default: ${MYSQL_PASSWORD} expose: true ZEABUR_MYSQL_PORT: default: ${MYSQL_PORT} expose: true configs: - path: /etc/my.cnf template: | [mysqld] default-authentication-plugin=mysql_native_password host-cache-size=0 skip-name-resolve datadir=/var/lib/mysql socket=/var/run/mysqld/mysqld.sock secure-file-priv=/var/lib/mysql-files user=mysql max_allowed_packet=10M max_connections=1000 character-set-server=utf8mb4 collation-server=utf8mb4_unicode_ci tls_version=TLSv1.2,TLSv1.3 binlog_expire_logs_seconds=604800 performance_schema=off pid-file=/var/run/mysqld/mysqld.pid [client] socket=/var/run/mysqld/mysqld.sock !includedir /etc/mysql/conf.d/ permission: null envsubst: null - path: /data/application/init.sql template: | -- RAGFlow initialization SQL CREATE DATABASE IF NOT EXISTS ragflow CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci; permission: null envsubst: null healthCheck: type: TCP port: database - name: redis icon: https://raw.githubusercontent.com/zeabur/service-icons/main/marketplace/redis.svg template: PREBUILT spec: id: redis source: image: valkey/valkey:8 command: - redis-server - --requirepass - ${REDIS_PASSWORD} - --maxmemory - 128mb - --maxmemory-policy - allkeys-lru ports: - id: database port: 6379 type: TCP volumes: - id: data dir: /data instructions: - title: Command to connect to your Redis content: redis-cli -h ${PORT_FORWARDED_HOSTNAME} -p ${DATABASE_PORT_FORWARDED_PORT} -a ${REDIS_PASSWORD} - title: Redis Connection String content: redis://:${REDIS_PASSWORD}@${PORT_FORWARDED_HOSTNAME}:${DATABASE_PORT_FORWARDED_PORT} - title: Redis password content: ${REDIS_PASSWORD} - title: Redis host content: ${PORT_FORWARDED_HOSTNAME} - title: Redis port content: ${DATABASE_PORT_FORWARDED_PORT} env: REDIS_ARGS: default: --requirepass ${REDIS_PASSWORD} REDIS_CONNECTION_STRING: default: redis://:${REDIS_PASSWORD}@${REDIS_HOST}:${REDIS_PORT} expose: true REDIS_HOST: default: ${CONTAINER_HOSTNAME} expose: true REDIS_PASSWORD: default: ${PASSWORD} expose: true REDIS_PORT: default: ${DATABASE_PORT} expose: true REDIS_URI: default: ${REDIS_CONNECTION_STRING} expose: true ZEABUR_REDIS_PASSWORD: default: ${REDIS_PASSWORD} expose: true healthCheck: type: TCP port: database - name: minio icon: https://raw.githubusercontent.com/zeabur/service-icons/main/marketplace/minio.svg template: PREBUILT spec: id: minio source: image: quay.io/minio/minio:latest command: - /bin/sh args: - -c - | minio server /data --console-address :9090 & MINIO_PID=$! while ! curl -s http://localhost:9000/minio/health/live; do echo 'Waiting for MinIO to start...' sleep 1 done sleep 5 mc alias set myminio http://localhost:9000 $MINIO_USERNAME $MINIO_PASSWORD echo "Creating bucket '$MINIO_DEFAULT_BUCKET'" mc mb myminio/$MINIO_DEFAULT_BUCKET wait $MINIO_PID ports: - id: web port: 9000 type: HTTP - id: console port: 9001 type: HTTP volumes: - id: data dir: /data instructions: - title: Go to MinIO Console content: ${MINIO_CONSOLE_URL} - title: Default Username (S3 Access Key ID) content: ${MINIO_USERNAME} - title: Default Password (S3 Secret Access Key) content: ${MINIO_PASSWORD} - title: Default Bucket content: ${MINIO_DEFAULT_BUCKET} env: MINIO_BROWSER_REDIRECT: default: "false" MINIO_CONSOLE_PORT: default: ${CONSOLE_PORT} expose: true MINIO_CONSOLE_URL: default: ${ZEABUR_CONSOLE_URL} expose: true MINIO_DEFAULT_BUCKET: default: ragflow MINIO_HOST: default: ${CONTAINER_HOSTNAME} MINIO_PASSWORD: default: ${MINIO_ROOT_PASSWORD} expose: true MINIO_ROOT_PASSWORD: default: ${PASSWORD} MINIO_ROOT_USER: default: minio MINIO_S3_PORT: default: ${WEB_PORT} MINIO_USERNAME: default: ${MINIO_ROOT_USER} expose: true ZEABUR_MINIO_PASSWORD: default: ${MINIO_ROOT_PASSWORD} expose: true - name: elasticsearch icon: https://cdn.worldvectorlogo.com/logos/elasticsearch.svg template: PREBUILT spec: id: elasticsearch source: image: docker.elastic.co/elasticsearch/elasticsearch:8.19.3 runAsUserID: 1000 ports: - id: http port: 9200 type: HTTP volumes: - id: certs dir: /usr/share/elasticsearch/config/certs - id: esdata dir: /usr/share/elasticsearch/data env: ELASTIC_PASSWORD: default: ${PASSWORD} ES_PORT: default: "9200" MEM_LIMIT: default: "1073741824" ZEABUR_ELASTICSEARCH_PASSWORD: default: ${ELASTIC_PASSWORD} expose: true action.destructive_requires_name: default: "false" bootstrap.memory_lock: default: "true" cluster.routing.allocation.disk.watermark.flood_stage: default: 2gb cluster.routing.allocation.disk.watermark.high: default: 3gb cluster.routing.allocation.disk.watermark.low: default: 5gb discovery.type: default: single-node node.name: default: elasticsearch xpack.license.self_generated.type: default: basic xpack.ml.use_auto_machine_memory_percent: default: "true" xpack.security.enabled: default: "true" xpack.security.http.ssl.enabled: default: "false" xpack.security.transport.ssl.enabled: default: "false" - name: infinity icon: https://avatars.githubusercontent.com/u/69962740?s=200&v=4 template: PREBUILT spec: id: infinity source: image: infiniflow/infinity:v0.6.0-dev5 ports: - id: thrift port: 23817 type: TCP - id: http port: 23820 type: HTTP - id: psql port: 5432 type: TCP volumes: - id: infinity-data dir: /var/infinity env: MEM_LIMIT: default: "1073741824" TZ: default: Asia/Shanghai configs: - path: /infinity_conf.toml template: | [general] version = "0.6.0-dev5" timezone = "Asia/Shanghai" [network] server_address = "0.0.0.0" postgres_port = 5432 http_port = 23820 sdk_port = 23817 [log] log_filename = "infinity.log" log_dir = "/var/infinity/log" log_to_stdout = true log_level = "info" [storage] data_dir = "/var/infinity/data" default_row_size = 8192 permission: null envsubst: null - name: opensearch icon: https://avatars.githubusercontent.com/u/80134844?s=200&v=4 template: PREBUILT spec: id: opensearch source: image: opensearchproject/opensearch:2.19.1 runAsUserID: 1000 ports: - id: http port: 9201 type: HTTP volumes: - id: osdata dir: /usr/share/opensearch/data env: MEM_LIMIT: default: "1073741824" OPENSEARCH_INITIAL_ADMIN_PASSWORD: default: ${PASSWORD} OPENSEARCH_PASSWORD: default: ${PASSWORD} expose: true TZ: default: Asia/Shanghai ZEABUR_OPENSEARCH_PASSWORD: default: ${OPENSEARCH_PASSWORD} expose: true bootstrap.memory_lock: default: "false" cluster.routing.allocation.disk.watermark.flood_stage: default: 2gb cluster.routing.allocation.disk.watermark.high: default: 3gb cluster.routing.allocation.disk.watermark.low: default: 5gb discovery.type: default: single-node http.port: default: "9201" node.name: default: opensearch plugins.security.disabled: default: "false" plugins.security.ssl.http.enabled: default: "false" plugins.security.ssl.transport.enabled: default: "true" localization: zh-CN: description: 基于深度文档理解的开源 RAG（检索增强生成）引擎，提供精简的 RAG 工作流程，专为各种规模的企业设计。 readme: |- ## 什么是 RAGFlow？ RAGFlow 是一个基于深度文档理解的开源 RAG（检索增强生成）引擎，提供精简的 RAG 工作流程，专为各种规模的企业设计。 ## 功能特色 - **深度文档理解**：先进的文档解析和分块功能 - **基于模板的分块**：智能内容分段 - **可信引用**：具有可验证来源的可信问答 - **多种文档格式**：支持 PDF、DOCX、PPT、Excel、图片等格式 - **兼容性**：与包括 Ollama 在内的异构模型生态系统兼容 - **模块化架构**：核心服务与可选附加组件 ## 架构 本模板包含： - **RAGFlow 核心**：主要应用服务（必需） - **MySQL**：用于存储元数据和配置的数据库（必需） - **可选服务**：Redis、MinIO、Elasticsearch、OpenSearch 和 Infinity（可根据需要单独部署） ## 环境变量 部署完成后，以下环境变量将自动配置： - `${RAGFLOW_URL}`：RAGFlow 服务的 URL - `${MYSQL_CONNECTION_STRING}`：MySQL 数据库连接字符串 - `${REDIS_CONNECTION_STRING}`：Redis 连接字符串 - `${MINIO_ENDPOINT}`：MinIO 对象存储端点 - `${ELASTICSEARCH_URL}`：Elasticsearch 搜索引擎 URL - `${OPENSEARCH_URL}`：OpenSearch 替代搜索引擎 URL - `${INFINITY_URL}`：Infinity 向量数据库 URL ## 开始使用 1. 部署完成后，通过提供的 URL 访问 RAGFlow 2. 创建您的第一个知识库 3. 上传文档（PDF、DOCX、图片等） 4. 开始基于您的文档进行问答 ## 默认凭证 - RAGFlow 管理界面无需初始认证即可访问 - 数据库和存储凭证将自动生成和配置 zh-TW: description: 基於深度文檔理解的開源 RAG（檢索增強生成）引擎，提供精簡的 RAG 工作流程，專為各種規模的企業設計。 readme: |- ## 什麼是 RAGFlow？ RAGFlow 是一個基於深度文檔理解的開源 RAG（檢索增強生成）引擎，提供精簡的 RAG 工作流程，專為各種規模的企業設計。 ## 功能特色 - **深度文檔理解**：先進的文檔解析和分塊功能 - **基於模板的分塊**：智慧內容分段 - **可信引用**：具有可驗證來源的可信問答 - **多種文檔格式**：支援 PDF、DOCX、PPT、Excel、圖片等格式 - **相容性**：與包括 Ollama 在內的異構模型生態系統兼容 - **模組化架構**：核心服務與可選附加元件 ## 架構 本模板包含： - **RAGFlow 核心**：主要應用服務（必需） - **MySQL**：用於存儲元數據和配置的資料庫（必需） - **可選服務**：Redis、MinIO、Elasticsearch、OpenSearch 和 Infinity（可根據需要單獨部署） ## 環境變數 部署完成後，以下環境變數將自動配置： - `${RAGFLOW_URL}`：RAGFlow 服務的 URL - `${MYSQL_CONNECTION_STRING}`：MySQL 資料庫連接字串 - `${REDIS_CONNECTION_STRING}`：Redis 連接字串 - `${MINIO_ENDPOINT}`：MinIO 物件存儲端點 - `${ELASTICSEARCH_URL}`：Elasticsearch 搜尋引擎 URL - `${OPENSEARCH_URL}`：OpenSearch 替代搜尋引擎 URL - `${INFINITY_URL}`：Infinity 向量資料庫 URL ## 開始使用 1. 部署完成後，透過提供的 URL 存取 RAGFlow 2. 建立您的第一個知識庫 3. 上傳文檔（PDF、DOCX、圖片等） 4. 開始基於您的文檔進行問答 ## 預設憑證 - RAGFlow 管理介面無需初始認證即可存取 - 資料庫和存儲憑證將自動產生和配置