feature: 对接deer-flow

deployment/docker/datamate/.env.deer-flow.example

@@ -0,0 +1 @@
+NGINX_CONF=./backend-with-deer-flow.conf

deployment/docker/datamate/.env.example

@@ -0,0 +1 @@
+NGINX_CONF=./backend.conf

deployment/docker/datamate/backend-with-deer-flow.conf

@@ -0,0 +1,49 @@
+server {
+    listen       80;
+    server_name  0.0.0.0;
+
+    access_log /var/log/datamate/frontend/access.log main;
+    error_log /var/log/datamate/frontend/error.log notice;
+
+    client_max_body_size 1024M;
+
+    add_header Set-Cookie "NEXT_LOCALE=zh";
+
+    location /api/ {
+        proxy_pass http://datamate-backend:8080/api/;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+    }
+
+    location /chat {
+        proxy_pass http://deer-flow-frontend:3000/chat;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+    }
+
+    location /_next {
+        proxy_pass http://deer-flow-frontend:3000/_next;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+    }
+
+    location /deer-flow-backend/ {
+        proxy_pass http://deer-flow-backend:8000/api/;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+    }
+
+    location / {
+        if ($query_string ~* "_rsc=pmmii") {
+            proxy_pass http://deer-flow-frontend:3000;
+            break;
+        }
+
+        root   /opt/frontend;
+        try_files $uri $uri/ /index.html;
+    }
+}

deployment/docker/datamate/backend.conf

@@ -0,0 +1,21 @@
+server {
+    listen       80;
+    server_name  0.0.0.0;
+
+    access_log /var/log/datamate/frontend/access.log main;
+    error_log /var/log/datamate/frontend/error.log notice;
+
+    client_max_body_size 1024M;
+
+    location /api/ {
+        proxy_pass http://datamate-backend:8080/api/;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+    }
+
+    location / {
+        root   /opt/frontend;
+        try_files $uri $uri/ /index.html;
+    }
+}

deployment/docker/datamate/docker-compose.yml

@@ -5,8 +5,6 @@ services:
     image: datamate-backend
     restart: on-failure
     privileged: true
-    ports:
-      - "8080"
     volumes:
       - dataset_volume:/dataset
       - flow_volume:/flow
@@ -24,6 +22,7 @@ services:
       - "30000:80"            # nodePort → hostPort
     volumes:
       - frontend_log_volume:/var/log/datamate/frontend
+      - $NGINX_CONF:/etc/nginx/conf.d/backend.conf
     networks: [ datamate ]
     depends_on:
       - datamate-backend
@@ -35,8 +34,6 @@ services:
     restart: on-failure
     environment:
       MYSQL_ROOT_PASSWORD: password
-    ports:
-      - "3306"
     command: |
       sh -c "
         chown mysql:mysql /var/log/datamate/database &&
@@ -63,8 +60,6 @@ services:
       MYSQL_USER: "root"
       MYSQL_PASSWORD: "password"
       MYSQL_DATABASE: "datamate"
-    ports:
-      - "8081"
     command:
       - python
       - /opt/runtime/datamate/operator_runtime.py

deployment/docker/deer-flow/.env.example

@@ -0,0 +1,99 @@
+# Application Settings
+DEBUG=True
+APP_ENV=development
+
+# docker build args
+NEXT_PUBLIC_API_URL="http://localhost:30000/deer-flow-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=http://localhost:3000
+
+# 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=tvly-xxx
+# 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=<endpoint_of_self_hosted_milvus_or_zilliz_cloud>
+# MILVUS_USER=<username_of_self_hosted_milvus_or_zilliz_cloud>
+# MILVUS_PASSWORD=<password_of_self_hosted_milvus_or_zilliz_cloud>
+# 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
+
+# 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

deployment/docker/deer-flow/conf.yaml.example

@@ -0,0 +1,71 @@
+# [!NOTE]
+# Read the `docs/configuration_guide.md` carefully, and update the
+# configurations to match your specific settings and requirements.
+# - Replace `api_key` with your own credentials.
+# - Replace `base_url` and `model` name if you want to use a custom model.
+# - Set `verify_ssl` to `false` if your LLM server uses self-signed certificates
+# - A restart is required every time you change the `conf.yaml` file.
+
+BASIC_MODEL:
+  base_url: https://ark.cn-beijing.volces.com/api/v3
+  model: "doubao-1-5-pro-32k-250115"
+  api_key: xxxx
+  # max_retries: 3 # Maximum number of retries for LLM calls
+  # verify_ssl: false  # Uncomment this line to disable SSL certificate verification for self-signed certificates
+
+  # Local model configuration example:
+
+  # Ollama (Tested and supported for local development)
+  # BASIC_MODEL:
+  #   base_url: "http://localhost:11434/v1"  # Ollama OpenAI compatible endpoint
+  #   model: "qwen3:14b"  # or "llama3.2", etc.
+  #   api_key: "ollama"  # Ollama doesn't need real API key
+  #   max_retries: 3
+  #   verify_ssl: false  # Local deployment usually doesn't need SSL verification
+
+  # To use Google Ai Studio as your basic platform:
+  # BASIC_MODEL:
+  #   platform: "google_aistudio"
+  #   model: "gemini-2.5-flash"  # or "gemini-1.5-pro", "gemini-2.5-flash-exp", etc.
+  #   api_key: your_gemini_api_key  # Get from https://aistudio.google.com/app/apikey
+  #   max_retries: 3
+
+# Reasoning model is optional.
+# Uncomment the following settings if you want to use reasoning model
+# for planning.
+
+# REASONING_MODEL:
+#   base_url: https://ark.cn-beijing.volces.com/api/v3
+#   model: "doubao-1-5-thinking-pro-m-250428"
+#   api_key: xxxx
+#   max_retries: 3 # Maximum number of retries for LLM calls
+
+
+# OTHER SETTINGS:
+# Search engine configuration (Only supports Tavily currently)
+# SEARCH_ENGINE:
+#   engine: tavily
+#   # Only include results from these domains
+#   include_domains:
+#     - example.com
+#     - trusted-news.com
+#     - reliable-source.org
+#     - gov.cn
+#     - edu.cn
+#   # Exclude results from these domains
+#   exclude_domains:
+#     - example.com
+#   # Include an answer in the search results
+#   include_answer: false
+#   # Search depth: "basic" or "advanced"
+#   search_depth: "advanced"
+#   # Include raw content from pages
+#   include_raw_content: true
+#   # Include images in search results
+#   include_images: true
+#   # Include descriptions for images
+#   include_image_descriptions: true
+#   # Minimum score threshold for results (0-1)
+#   min_score_threshold: 0.0
+#   # Maximum content length per page
+#   max_content_length_per_page: 4000

deployment/docker/deer-flow/docker-compose.yml

@@ -0,0 +1,28 @@
+services:
+  deer-flow-backend:
+    image: deer-flow-backend
+    container_name: deer-flow-backend
+    env_file:
+      - .env
+    volumes:
+      - ./conf.yaml:/app/conf.yaml:ro
+    restart: unless-stopped
+    networks:
+      - datamate
+
+  deer-flow-frontend:
+    image: deer-flow-frontend
+    container_name: deer-flow-frontend
+    env_file:
+      - .env
+    depends_on:
+      - deer-flow-backend
+    restart: unless-stopped
+    networks:
+      - datamate
+
+networks:
+  datamate:
+    driver: bridge
+    name: datamate_datamate
+    external: true