feat(deepdata): 引入修改密码、文件预览组件与清洗算子增强，deepflow 改名为 deep-flow
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）
This commit is contained in:
沃巴蒂
+69
-79
@@ -1,79 +1,69 @@
|
||||
# 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
|
||||
|
||||
# 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=true
|
||||
|
||||
# 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.ccoop.cc:18585
|
||||
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
|
||||
# ==========================================
|
||||
|
||||
RAY_REDIS_PASSWORD=ray_redis_secret
|
||||
# 内部使用的board地址
|
||||
RAY_DASHBOARD_ADDRESS=http://deepdata-ray-head:8265
|
||||
# 内部使用的GCS/head地址
|
||||
RAY_HEAD_GCS_ADDRESS=deepdata-ray-head:6379
|
||||
# 宿主机映射的head端口
|
||||
RAY_HEAD_PORT=6379
|
||||
# 宿主机映射的dashboard端口
|
||||
RAY_DASHBOARD_PORT=8267
|
||||
# 宿主机映射的client端口
|
||||
RAY_CLIENT_PORT=10002
|
||||
RAY_WORKER_NUM_CPUS=4
|
||||
RAY_WORKER_NUM_GPUS=0
|
||||
ENABLE_RAY_EXECUTION=true
|
||||
MAX_ACTOR_NUMS=40
|
||||
NUM_RAY_WORKERS=2
|
||||
RAY_WORKER_MEMORY_MB=8000
|
||||
|
||||
# ==========================================
|
||||
# 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
|
||||
|
||||
|
||||
@@ -1,97 +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)
|
||||
# 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/deep-flow/
|
||||
├── 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 官方文档](https://github.com/ModelEngine-Group/DeepFlow)
|
||||
|
||||
## 相关链接
|
||||
|
||||
- [运行时 README](../README.md)
|
||||
@@ -1,97 +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)
|
||||
# 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)
|
||||
@@ -71,13 +71,13 @@
|
||||
# max_content_length_per_page: 4000
|
||||
|
||||
sandbox:
|
||||
use: deepflow.community.aio_sandbox:AioSandboxProvider
|
||||
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
|
||||
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
|
||||
@@ -1,104 +0,0 @@
|
||||
# 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
|
||||
+592
-533
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,20 @@
|
||||
#!/bin/bash
|
||||
mkdir -p ./volumes/dataset
|
||||
mkdir -p ./volumes/flow
|
||||
mkdir -p ./volumes/logs/deepdata
|
||||
mkdir -p ./volumes/postgres/data
|
||||
mkdir -p ./volumes/ray/logs
|
||||
mkdir -p ./volumes/logs/frontend
|
||||
mkdir -p ./volumes/logs/database
|
||||
mkdir -p ./volumes/operators/upload
|
||||
mkdir -p ./volumes/operators/runtime
|
||||
mkdir -p ./volumes/operators/site-packages
|
||||
mkdir -p ./volumes/rag_storage
|
||||
mkdir -p ./volumes/logs/deep-flow
|
||||
mkdir -p ./volumes/label-studio/data
|
||||
mkdir -p ./volumes/label-studio/db
|
||||
mkdir -p ./volumes/milvus/etcd
|
||||
mkdir -p ./volumes/milvus/minio
|
||||
mkdir -p ./volumes/milvus/data
|
||||
mkdir -p ./volumes/redis/data
|
||||
echo "所有挂载目录创建完成"
|
||||
@@ -1,5 +1,6 @@
|
||||
(function () {
|
||||
const exactTextMap = new Map([
|
||||
["A full-fledged open source solution for data labeling", ""],
|
||||
["Label Studio", "Label Studio 标注平台"],
|
||||
["Projects", "项目"],
|
||||
["Project", "项目"],
|
||||
|
||||
Reference in New Issue
Block a user