沃巴蒂
ff22ed3a8b
本次同步 09-12 至 09-28 的代码变更，主要内容： 新增功能 - 修改密码：后端新增 ChangePasswordRequest DTO 与UserController/UserService 对应接口，前端新增 ChangePasswordDialog 并在 Header 接入入口 - 文件预览组件重构：file-preview 目录拆分出 VideoPreview（支持 blobUrl 直传）、 ImagePreview、AudioPreview，index.tsx 统一调度各类型预览器 - 新增 my_ops 算子模块：markitdown_parser、mineru_pdf_parser、text_quality_evaluator - 新增 tools/minio-file-server MinIO 文件服务 功能增强 - 数据清洗：cleaning_task_service/scheduler/routes 重构， data_juicer_executor 与 wrapper 增强，OperatorTable/LogsTable/TaskDetail 同步调整 - 数据标注：annotation sync.py、project.py 接口与schema 更新 - 数据采集、算子市场、首页与菜单路由相关页面调整 - DataJuicer 算子接入（useOperatorOperations、dj_ops_schema） 结构调整 - deepflow/ 更名为 deep-flow/（419 个文件重命名） - 新增 helm 部署编排、GitHub Actions 之外的自建镜像构建脚本 未纳入本次提交 - scripts-backup/、runtime/python-executor-backup/、components_backup/（备份目录） - *.backup*、__pycache__ 产物 - zh_core_web_sm-3.8.0-py3-none-any.whl（46MB 构建产物） - DataX/（内嵌独立仓库，远程亦未收录其源码）
98 lines
2.1 KiB
Markdown
98 lines
2.1 KiB
Markdown
# DeepFlow Service
|
|
|
|
## Overview
|
|
|
|
DeepFlow is an LLM-driven service for planning and reasoning tasks, supporting multiple LLM providers.
|
|
|
|
## Architecture
|
|
|
|
```
|
|
runtime/deep-flow/
|
|
├── 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 Official Documentation](https://github.com/ModelEngine-Group/DeepFlow)
|
|
|
|
## Related Links
|
|
|
|
- [Runtime README](../README.md)
|