Merge pull request #335 from antgroup/dev

Merge dev branch into master branch

Author: LandJerry

.github/ISSUE_TEMPLATE/issue_template-bug.yaml

@@ -10,7 +10,7 @@ body:
   attributes:
     label: Version
     description: What is the version of your agentUniverse? | 您使用的agentUniverse版本是多少？
-    placeholder: "Example: version 0.0.13"
+    placeholder: "Example: version 0.0.15"
   validations:
     required: true
 - type: textarea

.github/ISSUE_TEMPLATE/issue_template-question.yaml

@@ -23,7 +23,7 @@ body:
   attributes:
     label: Version
     description: What is the version of your agentUniverse? | 您使用的agentUniverse版本是多少？
-    placeholder: "Example: version 0.0.13"
+    placeholder: "Example: version 0.0.15"
   validations:
     required: false
 - type: textarea

.gitignore

@@ -102,7 +102,7 @@ ipython_config.py
 #   This is especially recommended for binary packages to ensure reproducibility, and is more
 #   commonly ignored for libraries.
 #   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
+poetry.lock
 
 # pdm
 #   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
@@ -169,3 +169,7 @@ cython_debug/
 *.pyc
 __pycache__/
 /poetry.lock
+
+
+# vscode
+.vscode/launch.json

CHANGELOG.md

@@ -24,6 +24,45 @@ Note - Additional remarks regarding the version.
 ***************************************************
 
 # Version Update History
+## [0.0.15] - 2025-03-03
+### Added
+- New embedding components  
+  - Azure-OpenAI embedding component
+  - Gemini embedding component
+  - Doubao embedding component
+- New knowledge loading reader components
+  - Web page reader component based on BeautifulSoup (bs4)
+  - Image reader component based on OCR technology
+  - CSV format reader component
+- New tool plugins
+  - Arxiv paper retrieval and query tool plugin
+  - Jina AI intelligent search tool plugin
+- Added standard LLM output parser for reasoning-type models
+- Added standard logger sink for agents, LLMs, and tools
+- Added retry function annotation
+
+### Changed  
+- Improved project configuration experience, with the following key optimizations:
+  - Project configuration now supports global PACKAGE path replacement. For details, see the PACKAGE_PATH_INFO parameter in the sample project's config.toml file.
+  - Supports user-defined configuration extensions and YAML function extensions. For details, see the EXTENSION_MODULES parameter in the sample project's config.toml file.
+  - Updated custom_key.toml.sample with more detailed parameter content.
+  - Submit a set of commonly used model configuration YAML files. For details, see the llm directory in the sample project.
+  - YAML configuration now supports user-defined loading of attributes using environment variables and extension functions. For details, see the api_key comments in the llm sample of the sample project.
+  - Simplified LLM configuration. By default, it reads the global default_llm configuration. For details, see the default_llm.toml configuration in the llm sample of the sample project.
+  - Simplified component extension configuration. The module part in the component metadata can be left blank, and it will default to searching for a Python extension file with the same name in the same directory.
+- Optimized project startup process, with the following key improvements:
+  - Improved LLM component startup registration. Only LLM instances that are dependent on by components like agents and tools are started.
+  - Enhanced error info during project startup.
+- Other changes:
+  - Renamed LocalMemoryStorage to RamMemoryStorage for memory storage objects.
+
+### Note 
+- Added image_build image packaging files and tutorial documents for application projects.
+- Added CONTRIBUTING.md documentation for the project.
+- Standardized PR and ISSUE templates for the project.
+- Added a sample practice for agents based on multimodal capabilities. For details, see the examples/multimodal_app directory in the project.
+- Our project was included in the awesome-deepseek-integration list released by DeepSeek in February.
+
 ## [0.0.14] - 2025-01-26
 ### Added
 - aU Memory Component Version Update   

CHANGELOG_zh.md

@@ -24,6 +24,45 @@ Note - 对于版本的额外说明。
 ***************************************************
 
 # 版本更新记录
+## [0.0.15] - 2025-03-03
+### Added
+- embedding组件新增  
+  - 新增azure-openai embedding组件  
+  - 新增gemini embedding组件  
+  - 新增豆包embedding标准组件 
+- 知识加载reader组件新增  
+  - 新增基于bs4的网页读取组件
+  - 新增基于OCR技术的图像加载组件
+  - 新增csv格式表格加载组件
+- 工具插件新增  
+  - 新增Arxiv文献检索查询工具插件
+  - 新增Jina AI智能搜索工具插件
+- 新增reasoning类模型标准LLM输出解析器
+- 新增agent、llm、tool相关日志采集标准logger
+- 新增retry函数注解
+
+### Changed  
+- 项目配置体验优化，主要优化点如下
+  - 项目配置支持全局PACKAGE路径替换，详情见样例工程config.toml文件PACKAGE_PATH_INFO参数部分
+  - 支持用户自定义配置扩展与yaml函数扩展，详情见样例工程config.toml文件EXTENSION_MODULES参数部分
+  - custom_key.toml.sample更新，提供更详细与全面的参数内容
+  - 内置一批常用模型配置yaml，详情见样例工程llm目录
+  - yaml配置支持用户使用环境变量与扩展函数自定义加载对应属性，详情见样例工程llm样例中api_key注释说明部分
+  - llm配置简化，默认读取全局default_llm配置，详情见样例工程llm样例default_llm.toml配置内容
+  - 组件扩展配置简化，组件metadata中module部分可不填写，默认寻找同层级同名py扩展文件
+- 项目启动流程优化，主要优化点如下
+  - LLM组件启动注册优化，只启动用户在agent、tool等组件中依赖启动的LLM实例
+  - 项目启动报错提示优化
+- 其他变更
+  - 内存记忆存储对象LocalMemoryStorage更名RamMemoryStorage
+
+### Note 
+- 新增应用工程image_build镜像打包文件与教程文档
+- 新增项目贡献者开发文档
+- 规范项目PR与ISSUE模版
+- 新增基于模型多模态能力的agent样例实践，详情见项目examples/multimodal_app
+- 项目于2月收录于deepseek发布的awesome-deepseek-integration榜单
+
 ## [0.0.14] - 2025-01-26
 ### Added
 - aU记忆机制全面改版升级  

README.md

@@ -5,7 +5,7 @@ Language version: [English](./README.md) | [中文](./README_zh.md) | [日本語
 ![](https://img.shields.io/badge/framework-agentUniverse-pink)
 ![](https://img.shields.io/badge/python-3.10%2B-blue?logo=Python)
 [![](https://img.shields.io/badge/%20license-Apache--2.0-yellow)](LICENSE)
-[![Static Badge](https://img.shields.io/badge/pypi-v0.0.13-blue?logo=pypi)](https://pypi.org/project/agentUniverse/)
+[![Static Badge](https://img.shields.io/badge/pypi-v0.0.15-blue?logo=pypi)](https://pypi.org/project/agentUniverse/)
 
 ![](docs/guidebook/_picture/logo_bar.jpg)
 ****************************************

README_jp.md

@@ -5,7 +5,7 @@
 ![](https://img.shields.io/badge/framework-agentUniverse-pink)
 ![](https://img.shields.io/badge/python-3.10%2B-blue?logo=Python)
 [![](https://img.shields.io/badge/%20license-Apache--2.0-yellow)](LICENSE)
-[![Static Badge](https://img.shields.io/badge/pypi-v0.0.13-blue?logo=pypi)](https://pypi.org/project/agentUniverse/)
+[![Static Badge](https://img.shields.io/badge/pypi-v0.0.15-blue?logo=pypi)](https://pypi.org/project/agentUniverse/)
 
 ![](docs/guidebook/_picture/logo_bar.jpg)
 ****************************************

README_zh.md

@@ -5,7 +5,7 @@
 ![](https://img.shields.io/badge/framework-agentUniverse-pink)
 ![](https://img.shields.io/badge/python-3.10%2B-blue?logo=Python)
 [![](https://img.shields.io/badge/%20license-Apache--2.0-yellow)](LICENSE)
-[![Static Badge](https://img.shields.io/badge/pypi-v0.0.13-blue?logo=pypi)](https://pypi.org/project/agentUniverse/)
+[![Static Badge](https://img.shields.io/badge/pypi-v0.0.15-blue?logo=pypi)](https://pypi.org/project/agentUniverse/)
 
 ![](docs/guidebook/_picture/logo_bar.jpg)
 ****************************************

agentuniverse/agent/action/knowledge/knowledge.py

@@ -8,6 +8,7 @@
 import os
 import re
 import traceback
+from copy import deepcopy
 from typing import Optional, Dict, List, Any
 from concurrent.futures import wait, ALL_COMPLETED
 
@@ -64,6 +65,7 @@ class Knowledge(ComponentBase):
 
         ext_info (Optional[Dict]): The extended information of the knowledge.
     """
+
     class Config:
         arbitrary_types_allowed = True
 
@@ -78,6 +80,7 @@ class Config:
     readers: Dict[str, str] = dict()
     insert_executor: Optional[ThreadPoolExecutorWithReturnValue] = None
     query_executor: Optional[ThreadPoolExecutorWithReturnValue] = None
+    tracing: Optional[bool] = None
     ext_info: Optional[Dict] = None
 
     def __init__(self, **kwargs):
@@ -263,6 +266,8 @@ def _initialize_by_component_configer(self,
             self.post_processors = knowledge_configer.post_processors
         if hasattr(knowledge_configer, "readers"):
             self.readers = knowledge_configer.readers
+        if hasattr(knowledge_configer, "tracing"):
+            self.tracing = knowledge_configer.tracing
         return self
 
     def langchain_query(self, query: str) -> str:
@@ -294,3 +299,15 @@ def as_langchain_tool(self) -> LangchainTool:
             description=self.description or '' + args_description,
             func=self.langchain_query,
         )
+
+    def create_copy(self):
+        copied = self.model_copy()
+        copied.stores = self.stores.copy()
+        copied.query_paraphrasers = self.query_paraphrasers.copy()
+        copied.insert_processors = self.insert_processors.copy()
+        copied.update_processors = self.update_processors.copy()
+        copied.post_processors = self.post_processors.copy()
+        copied.readers = deepcopy(self.readers)
+        if self.ext_info is not None:
+            copied.ext_info = deepcopy(self.ext_info)
+        return copied

agentuniverse/agent/action/knowledge/rag_router/nlu_rag_router.py

@@ -53,6 +53,3 @@ def _initialize_by_component_configer(self,
             self.agent_name = rag_router_config.agent_name
         if hasattr(rag_router_config, "store_amount"):
             self.store_amount = rag_router_config.store_amount
-
-
-