deepdata: delivery stack (docker compose, helm, CI, build scripts)

docker/deepflow/README-zh.md

@@ -0,0 +1,97 @@
+# DeepFlow 服务
+
+## 概述
+
+DeepFlow 是一个 LLM 驱动的服务，用于规划和推理任务，支持多种 LLM 提供商。
+
+## 架构
+
+```
+runtime/deepflow/
+├── conf.yaml       # DeepFlow 配置文件
+├── .env            # 环境变量
+└── (其他源代码）
+```
+
+## 配置
+
+### 基本配置 (conf.yaml)
+
+```yaml
+# 基础模型配置
+BASIC_MODEL:
+  base_url: https://api.example.com/v1
+  model: "model-name"
+  api_key: your_api_key
+  max_retries: 3
+  verify_ssl: false  # 如果使用自签名证书，设为 false
+
+# 推理模型配置（可选）
+REASONING_MODEL:
+  base_url: https://api.example.com/v1
+  model: "reasoning-model-name"
+  api_key: your_api_key
+  max_retries: 3
+
+# 搜索引擎配置（可选）
+SEARCH_ENGINE:
+  engine: tavily
+  include_domains:
+    - example.com
+    - trusted-news.com
+  exclude_domains:
+    - spam-site.com
+  search_depth: "advanced"
+  include_raw_content: true
+  include_images: true
+  include_image_descriptions: true
+  min_score_threshold: 0.0
+  max_content_length_per_page: 4000
+```
+
+## 支的 LLM 提供商
+
+#### OpenAI
+```yaml
+BASIC_MODEL:
+  base_url: https://api.openai.com/v1
+  model: "gpt-4"
+  api_key: sk-...
+```
+
+#### Ollama (本地部署）
+```yaml
+BASIC_MODEL:
+  base_url: "http://localhost:11434/v1"
+  model: "qwen2:7b"
+  api_key: "ollama"
+  verify_ssl: false
+```
+
+#### Google AI Studio
+```yaml
+BASIC_MODEL:
+  platform: "google_aistudio"
+  model: "gemini-2.5-flash"
+  api_key: your_gemini_api_key
+```
+
+## 开发
+
+### 添加新的 LLM 提供商
+1. 在 `conf.yaml` 添加新的模型配置
+2. 实现对应的 API 调用逻辑
+3. 测试连接和推理
+
+### 自定义提示词模板
+1. 创建提示词模板文件
+2. 在 `conf.yaml` 引用模板
+3. 测试提示词效果
+
+## 文档
+
+- [DeepFlow 模块说明](../../deepflow/README_zh.md)
+
+## 相关链接
+
+- [运行时 README](../README.md)

docker/deepflow/README.md

@@ -0,0 +1,97 @@
+# DeepFlow Service
+
+## Overview
+
+DeepFlow is an LLM-driven service for planning and reasoning tasks, supporting multiple LLM providers.
+
+## Architecture
+
+```
+runtime/deepflow/
+├── conf.yaml       # DeepFlow configuration file
+├── .env            # Environment variables
+└── (other source code)
+```
+
+## Configuration
+
+### Basic Configuration (conf.yaml)
+
+```yaml
+# Basic model configuration
+BASIC_MODEL:
+  base_url: https://api.example.com/v1
+  model: "model-name"
+  api_key: your_api_key
+  max_retries: 3
+  verify_ssl: false  # Set to false if using self-signed certificates
+
+# Reasoning model configuration (optional)
+REASONING_MODEL:
+  base_url: https://api.example.com/v1
+  model: "reasoning-model-name"
+  api_key: your_api_key
+  max_retries: 3
+
+# Search engine configuration (optional)
+SEARCH_ENGINE:
+  engine: tavily
+  include_domains:
+    - example.com
+    - trusted-news.com
+  exclude_domains:
+    - spam-site.com
+  search_depth: "advanced"
+  include_raw_content: true
+  include_images: true
+  include_image_descriptions: true
+  min_score_threshold: 0.0
+  max_content_length_per_page: 4000
+```
+
+## Supported LLM Providers
+
+#### OpenAI
+```yaml
+BASIC_MODEL:
+  base_url: https://api.openai.com/v1
+  model: "gpt-4"
+  api_key: sk-...
+```
+
+#### Ollama (Local Deployment)
+```yaml
+BASIC_MODEL:
+  base_url: "http://localhost:11434/v1"
+  model: "qwen2:7b"
+  api_key: "ollama"
+  verify_ssl: false
+```
+
+#### Google AI Studio
+```yaml
+BASIC_MODEL:
+  platform: "google_aistudio"
+  model: "gemini-2.5-flash"
+  api_key: your_gemini_api_key
+```
+
+## Development
+
+### Adding a New LLM Provider
+1. Add new model configuration in `conf.yaml`
+2. Implement corresponding API call logic
+3. Test connection and inference
+
+### Customizing Prompt Templates
+1. Create a prompt template file
+2. Reference the template in `conf.yaml`
+3. Test prompt effectiveness
+
+## Documentation
+
+- [DeepFlow Module README](../../deepflow/README.md)
+
+## Related Links
+
+- [Runtime README](../README.md)

docker/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