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

deepflow/.dockerignore

@@ -0,0 +1,53 @@
+.env
+Dockerfile
+.dockerignore
+.git
+.gitignore
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+.venv/
+
+# Web
+node_modules
+npm-debug.log
+.next
+
+# IDE
+.idea/
+.vscode/
+*.swp
+*.swo
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Project specific
+conf.yaml
+web/
+docs/
+examples/
+assets/
+tests/
+*.log

deepflow/.env

@@ -0,0 +1,97 @@
+# 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=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=http://milvus:19530
+MILVUS_USER=root
+MILVUS_PASSWORD=Milvus
+MILVUS_AUTO_LOAD_EXAMPLES=false
+# 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

deepflow/.gitignore

@@ -14,11 +14,11 @@ static/browser_history/*.gif
 .venv
 venv/
 
-# Environment variables
-.env
+# Environment defaults are tracked for a self-contained repo
+# .env
 
-# user conf
-conf.yaml
+# Product conf is tracked
+# conf.yaml
 
 .idea/
 .langgraph_api/

deepflow/.python-version

@@ -0,0 +1 @@
+3.12

deepflow/conf.yaml

@@ -0,0 +1,84 @@
+# [!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://dashscope.aliyuncs.com/compatible-mode/v1
+    model: "qwen3.6-plus"
+    api_key: sk-e653053a9ce049b795682194b91a56c9
+    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://dashscope.aliyuncs.com/compatible-mode/v1
+    model: "qwen3.6-plus"
+    api_key: sk-e653053a9ce049b795682194b91a56c9
+    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
+
+  sandbox:
+    use: deepflow.community.aio_sandbox:AioSandboxProvider
+    image: enterprise-public-cn-beijing.cr.volces.com/vefaas-public/all-in-one-sandbox:latest
+    port: 8080
+    auto_start: true
+    replicas: 2
+    container_prefix: deepdata-deepflow-sandbox
+    # 把 DeepData 的 dataset 卷透进沙箱，Agent 写报告能直接落到 /dataset/deepflow-output
+    mounts:
+      - host_path: /var/lib/docker/volumes/deepdata-dataset-volume/_data
+        container_path: /dataset
+        read_only: false

deepflow/web/.dockerignore

@@ -0,0 +1,8 @@
+.env
+Dockerfile
+.dockerignore
+node_modules
+npm-debug.log
+README.md
+.next
+.git

deepflow/web/src/lib/utils.ts

@@ -0,0 +1,9 @@
+// Copyright (c) 2025 Bytedance Ltd. and/or its affiliates
+// SPDX-License-Identifier: MIT
+
+import { clsx, type ClassValue } from "clsx"
+import { twMerge } from "tailwind-merge"
+
+export function cn(...inputs: ClassValue[]) {
+  return twMerge(clsx(inputs))
+}

deepflow/web/src/typings/md.d.ts

@@ -0,0 +1,4 @@
+declare module "*.md" {
+  const content: string;
+  export default content;
+}