deepdata: track product config and env defaults for self-contained deployment

docker/.env

@@ -0,0 +1,79 @@
+# 镜像仓库与版本
+REGISTRY=
+VERSION=latest
+
+# 数据库核心密码【必须修改】
+DB_PASSWORD=Apescale123
+
+# JWT配置 (必须 >= 32 字符，即 256 bits)
+JWT_SECRET=ApescaleSuperSecureJwtSecretKey2026v1
+DEEPDATA_JWT_ENABLE=false
+
+# 日志轮转配置
+LOG_ROTATION_MAX_SIZE=100MB
+LOG_ROTATION_BACKUP_COUNT=30
+LOG_LEVEL=INFO
+
+# 日志磁盘监控
+LOG_PVC_MONITOR_ENABLED=true
+LOG_PVC_MONITOR_PATH=/var/log/deepdata
+LOG_PVC_MONITOR_THRESHOLD=0.9
+LOG_PVC_MONITOR_INTERVAL_SECONDS=300
+LOG_PVC_MONITOR_DELETE_BATCH_SIZE=10
+LOG_PVC_MONITOR_FILE_SUFFIXES=log,out,err
+
+# Milvus向量库配置（启用milvus profile生效）
+MILVUS_URI=http://milvus:19530
+MINIO_ACCESS_KEY=minioadmin
+MINIO_SECRET_KEY=Minio@Passw0rd
+
+# LabelStudio配置
+LABEL_STUDIO_USERNAME=admin@demo.com
+LABEL_STUDIO_PASSWORD=LabelStudio@123
+LABEL_STUDIO_USER_TOKEN=50d54c9fa842a1cd8e26c55efa7113db22870c47
+LABEL_STUDIO_HOST=http://labelstudio.ailab.yilise.com
+LABEL_STUDIO_BASE_URL=http://label-studio:8000
+
+# MinerU额外启动参数
+EXTRA_ARGS=
+
+
+MINIO_ACCESS_KEY_ID=minioadmin
+MINIO_SECRET_ACCESS_KEY=Minio@Passw0rd
+AWS_REGION=us-east-1
+
+# ==========================================
+# Ray 分布式集群配置
+# ==========================================
+
+# 1. Redis 密码 (Ray Head 强依赖 Redis)
+RAY_REDIS_PASSWORD=ray_redis_secret
+RAY_REDIS_ADDRESS=deepdata-ray-redis:6379
+
+# 2. Dashboard 地址 (用于 Client 提交任务，即 job_task_scheduler.py 读取的值)
+# 注意：默认值是 K8s 的 svc，这里覆盖为 Compose 服务名
+RAY_DASHBOARD_ADDRESS=http://deepdata-ray-head:8265
+
+# 3. Head GCS 地址 (用于 Worker 节点加入集群)
+RAY_HEAD_GCS_ADDRESS=deepdata-ray-head:6379
+
+# Ray Head 端口配置
+RAY_HEAD_PORT=6379
+RAY_DASHBOARD_PORT=8265
+RAY_CLIENT_PORT=10001
+
+# Ray Worker 资源配置 (可根据服务器性能调整)
+# NUM_CPUS: 每个 Worker 容器分配的 CPU 核数
+RAY_WORKER_NUM_CPUS=4
+# NUM_GPUS: 如果不需要 GPU 则设为 0
+RAY_WORKER_NUM_GPUS=0
+
+ENABLE_RAY_EXECUTION=true
+
+# ==========================================
+# Collection Task Execution Mode
+# - local:  Backend 本地执行 (默认，兼容旧版)
+# - runtime: 提交给 Runtime -> Ray 集群执行
+# ==========================================
+COLLECTION_EXECUTION_MODE=runtime
+

docker/deepflow/.env

@@ -0,0 +1,104 @@
+# Application Settings
+DEBUG=True
+APP_ENV=development
+
+# docker build args
+NEXT_PUBLIC_API_URL="/deepflow-backend"
+
+AGENT_RECURSION_LIMIT=30
+
+# CORS settings
+# Comma-separated list of allowed origins for CORS requests
+# Example: ALLOWED_ORIGINS=http://localhost:3000,http://example.com
+ALLOWED_ORIGINS=*
+
+# Enable or disable MCP server configuration, the default is false.
+# Please enable this feature before securing your front-end and back-end in a managed environment.
+# Otherwise, you system could be compromised.
+ENABLE_MCP_SERVER_CONFIGURATION=true
+
+# Enable or disable PYTHON_REPL configuration, the default is false.
+# Please enable this feature before securing your in a managed environment.
+# Otherwise, you system could be compromised.
+ENABLE_PYTHON_REPL=false
+
+# Search Engine, Supported values: tavily (recommended), duckduckgo, brave_search, arxiv, searx
+SEARCH_API=tavily
+TAVILY_API_KEY=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
+# SEARX_HOST=xxx # Required only if SEARCH_API is searx.(compatible with both Searx and SearxNG)
+# BRAVE_SEARCH_API_KEY=xxx # Required only if SEARCH_API is brave_search
+# JINA_API_KEY=jina_xxx # Optional, default is None
+
+# Optional, RAG provider
+# RAG_PROVIDER=vikingdb_knowledge_base
+# VIKINGDB_KNOWLEDGE_BASE_API_URL="api-knowledgebase.mlp.cn-beijing.volces.com"
+# VIKINGDB_KNOWLEDGE_BASE_API_AK="AKxxx"
+# VIKINGDB_KNOWLEDGE_BASE_API_SK=""
+# VIKINGDB_KNOWLEDGE_BASE_RETRIEVAL_SIZE=15
+
+# RAG_PROVIDER=ragflow
+# RAGFLOW_API_URL="http://localhost:9388"
+# RAGFLOW_API_KEY="ragflow-xxx"
+# RAGFLOW_RETRIEVAL_SIZE=10
+# RAGFLOW_CROSS_LANGUAGES=English,Chinese,Spanish,French,German,Japanese,Korean # Optional. To use RAGFlow's cross-language search, please separate each language with a single comma
+
+# RAG_PROVIDER=dify
+# DIFY_API_URL="https://api.dify.ai/v1"
+# DIFY_API_KEY="dataset-xxx"
+
+# MOI is a hybrid database that mainly serves enterprise users (https://www.matrixorigin.io/matrixone-intelligence)
+# RAG_PROVIDER=moi
+# MOI_API_URL="https://cluster.matrixonecloud.cn"
+# MOI_API_KEY="xxx-xxx-xxx-xxx"
+# MOI_RETRIEVAL_SIZE=10
+# MOI_LIST_LIMIT=10
+
+# RAG_PROVIDER: milvus  (using free milvus instance on zilliz cloud: https://docs.zilliz.com/docs/quick-start )
+RAG_PROVIDER=milvus
+MILVUS_URI=http://milvus:19530
+MILVUS_USER=root
+MILVUS_PASSWORD=Milvus
+MILVUS_AUTO_LOAD_EXAMPLES=false
+MILVUS_COLLECTION=kb_deepdata
+MILVUS_EMBEDDING_PROVIDER=dashscope          # 或 dashscope，看 DeepData 侧用的哪家
+MILVUS_EMBEDDING_BASE_URL=https://dashscope.aliyuncs.com/compatible-mode/v1
+MILVUS_EMBEDDING_MODEL=text-embedding-v2
+MILVUS_EMBEDDING_API_KEY=sk-e653053a9ce049b795682194b91a56c9
+
+
+# MILVUS_EMBEDDING_PROVIDER=openai # support openai,dashscope
+# MILVUS_EMBEDDING_BASE_URL=
+# MILVUS_EMBEDDING_MODEL=
+# MILVUS_EMBEDDING_API_KEY=
+
+# RAG_PROVIDER: milvus  (using milvus lite on Mac or Linux)
+# RAG_PROVIDER=milvus
+# MILVUS_URI=./milvus_demo.db
+# MILVUS_COLLECTION=documents
+# MILVUS_EMBEDDING_PROVIDER=openai # support openai,dashscope
+# MILVUS_EMBEDDING_BASE_URL=
+# MILVUS_EMBEDDING_MODEL=
+# MILVUS_EMBEDDING_API_KEY=
+# MILVUS_AUTO_LOAD_EXAMPLES=true
+
+# Optional, volcengine TTS for generating podcast
+VOLCENGINE_TTS_APPID=xxx
+VOLCENGINE_TTS_ACCESS_TOKEN=xxx
+# VOLCENGINE_TTS_CLUSTER=volcano_tts # Optional, default is volcano_tts
+# VOLCENGINE_TTS_VOICE_TYPE=BV700_V2_streaming # Optional, default is BV700_V2_streaming
+
+# Option, for langsmith tracing and monitoring
+# LANGSMITH_TRACING=true
+# LANGSMITH_ENDPOINT="https://api.smith.langchain.com"
+# LANGSMITH_API_KEY="xxx"
+# LANGSMITH_PROJECT="xxx"
+
+# [!NOTE]
+# For model settings and other configurations, please refer to `docs/configuration_guide.md`
+
+# Option, for langgraph mongodb checkpointer
+# Enable LangGraph checkpoint saver, supports MongoDB, Postgres
+#LANGGRAPH_CHECKPOINT_SAVER=true
+# Set the database URL for saving checkpoints
+#LANGGRAPH_CHECKPOINT_DB_URL=mongodb://localhost:27017/
+#LANGGRAPH_CHECKPOINT_DB_URL=postgresql://localhost:5432/postgres