agentica 0.2.2__tar.gz → 0.2.5__tar.gz

{agentica-0.2.2 → agentica-0.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: agentica
-Version: 0.2.2
+Version: 0.2.5
 Summary: LLM agents
 Home-page: https://github.com/shibing624/agentica
 Author: XuMing
@@ -18,16 +18,30 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.8.0
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Requires-Dist: httpx
 Requires-Dist: loguru
-Requires-Dist: markdownify
+Requires-Dist: beautifulsoup4
 Requires-Dist: openai
 Requires-Dist: python-dotenv
 Requires-Dist: pydantic
 Requires-Dist: requests
 Requires-Dist: sqlalchemy
 Requires-Dist: scikit-learn
+Requires-Dist: markdownify
 Requires-Dist: tqdm
 Requires-Dist: rich
+Requires-Dist: pyyaml
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
 
 [**🇨🇳中文**](https://github.com/shibing624/agentica/blob/main/README.md) | [**🌐English**](https://github.com/shibing624/agentica/blob/main/README_EN.md) | [**🇯🇵日本語**](https://github.com/shibing624/agentica/blob/main/README_JP.md)
 
@@ -49,14 +63,11 @@ Requires-Dist: rich
 [![Wechat Group](https://img.shields.io/badge/wechat-group-green.svg?logo=wechat)](#Contact)
 
 
-**Agentica**: Build Smarter, Reflective, and Collaborative AI Agents with Ease!
+**Agentica**: 轻松构建智能、具备反思能力、可协作的多模态AI Agent。
 
-**Agentica**: 快速打造智能、能反思、协作的AI Agent。
 
 ## 📖 Introduction
 
-**Agentica** can build AI agent, which have the components of planning, memory, and tool use. 
-
 **Agentica** 可以构建AI Agent，包括规划、记忆和工具使用、执行等组件。
 
 #### Agent Components
@@ -79,6 +90,8 @@ Requires-Dist: rich
 - **Solver**：求解器将所有这些输出整合为最终答案
 
 ## 🔥 News
+[2024/12/29] v0.2.3版本: 支持了`ZhipuAI`的api调用，包括免费模型和工具使用，详见[Release-v0.2.3](https://github.com/shibing624/agentica/releases/tag/0.2.3)
+
 [2024/12/25] v0.2.0版本: 支持了多模态模型，输入可以是文本、图片、音频、视频，升级Assistant为Agent，Workflow支持拆解并实现复杂任务，详见[Release-v0.2.0](https://github.com/shibing624/agentica/releases/tag/0.2.0)
 
 [2024/07/02] v0.1.0版本：实现了基于LLM的Assistant，可以快速用function call搭建大语言模型助手，详见[Release-v0.1.0](https://github.com/shibing624/agentica/releases/tag/0.1.0)
@@ -89,7 +102,7 @@ Requires-Dist: rich
 
 - **Agent编排**：通过简单代码快速编排Agent，支持 Reflection(反思）、Plan and Solve(计划并执行)、RAG、Agent、Multi-Agent、Team、Workflow等功能
 - **自定义prompt**：Agent支持自定义prompt和多种工具调用（tool_calls）
-- **LLM集成**：支持OpenAI、Azure、Deepseek、Moonshot、Claude、Ollama、Together等多方大模型厂商的API
+- **LLM集成**：支持OpenAI、Azure、Deepseek、Moonshot、Anthropic、ZhipuAI、Ollama、Together等多方大模型厂商的API
 - **记忆功能**：包括短期记忆和长期记忆功能
 - **Multi-Agent协作**：支持多Agent和任务委托（Team）的团队协作。
 - **Workflow工作流**：拆解复杂任务为多个Agent，基于工作流自动化串行逐步完成任务，如投资研究、新闻文章撰写和技术教程创建
@@ -118,10 +131,10 @@ pip install .
 cp .env.example ~/.agentica/.env
 
 cd examples
-python web_search_moonshot_demo.py
+python 12_web_search_moonshot_demo.py
 ```
 
-1. 复制[.env.example](https://github.com/shibing624/agentica/blob/main/.env.example)文件为`~/.agentica/.env`，并填写LLM api key(选填DEEPSEEK_API_KEY、MOONSHOT_API_KEY、OPENAI_API_KEY等任一个即可)。或者使用`export`命令设置环境变量：
+1. 复制[.env.example](https://github.com/shibing624/agentica/blob/main/.env.example)文件为`~/.agentica/.env`，并填写LLM api key(选填DEEPSEEK_API_KEY、MOONSHOT_API_KEY、OPENAI_API_KEY、ZHIPUAI_API_KEY等任一个即可)。或者使用`export`命令设置环境变量：
     
     ```shell
     export MOONSHOT_API_KEY=your_moonshot_api_key
@@ -133,13 +146,23 @@ python web_search_moonshot_demo.py
 自动调用google搜索工具，示例[examples/12_web_search_moonshot_demo.py](https://github.com/shibing624/agentica/blob/main/examples/12_web_search_moonshot_demo.py)
 
 ```python
-from agentica import Agent, MoonshotChat, SearchSerperTool
+from agentica import Agent, Moonshot, WeatherTool
 
-m = Agent(model=MoonshotChat(), tools=[SearchSerperTool()], add_datetime_to_instructions=True)
-r = m.run("下一届奥运会在哪里举办")
-print(r)
+m = Agent(model=Moonshot(), tools=[WeatherTool()], add_datetime_to_instructions=True)
+m.print_response("明天北京天气咋样")
 ```
 
+output:
+```markdown
+明天北京的天气预报如下：
+
+- 早晨：晴朗，气温约18°C，风速较小，约为3 km/h。
+- 中午：晴朗，气温升至23°C，风速6-7 km/h。
+- 傍晚：晴朗，气温略降至21°C，风速较大，为35-44 km/h。
+- 夜晚：晴朗转晴，气温下降至15°C，风速32-39 km/h。
+
+全天无降水，能见度良好。请注意傍晚时分的风速较大，外出时需注意安全。
+```
 
 ## ▶️ Web UI
 
@@ -204,6 +227,7 @@ bash start.sh
 | [examples/37_workflow_write_novel_demo.py](https://github.com/shibing624/agentica/blob/main/examples/37_workflow_write_novel_demo.py)                 | 实现了写小说的工作流：定小说提纲 - 搜索谷歌反思提纲 - 撰写小说内容 - 保存为md文件                                                                                    |
 | [examples/38_workflow_write_tutorial_demo.py](https://github.com/shibing624/agentica/blob/main/examples/38_workflow_write_tutorial_demo.py)           | 实现了写技术教程的工作流：定教程目录 - 反思目录内容 - 撰写教程内容 - 保存为md文件                                                                                    |
 | [examples/39_audio_multi_turn_demo.py](https://github.com/shibing624/agentica/blob/main/examples/39_audio_multi_turn_demo.py)                         | 基于openai的语音api做多轮音频对话的Demo                                                                                                        |
+| [examples/40_weather_zhipuai_demo.py](https://github.com/shibing624/agentica/blob/main/examples/40_web_search_zhipuai_demo.py)                        | 基于智谱AI的api做天气查询的Demo                                                                                                              |
 
 
 ### Self-evolving Agent
@@ -244,6 +268,63 @@ streamlit run 34_llm_os_demo.py
 
 <img alt="LLM OS" src="https://github.com/shibing624/agentica/blob/main/docs/llm_os_snap.png" width="800" />
 
+
+### 命令行模式（CLI）
+
+支持终端命令行快速搭建并体验Agent
+
+code: [cli.py](https://github.com/shibing624/agentica/blob/main/agentica/cli.py)
+
+```
+> agentica -h                                    
+usage: cli.py [-h] [--query QUERY]
+              [--model_provider {openai,azure,moonshot,zhipuai,deepseek,yi}]
+              [--model_name MODEL_NAME] [--api_base API_BASE]
+              [--api_key API_KEY] [--max_tokens MAX_TOKENS]
+              [--temperature TEMPERATURE] [--verbose VERBOSE]
+              [--tools [{search_serper,file_tool,shell_tool,yfinance_tool,web_search_pro,cogview,cogvideo,jina,wikipedia} ...]]
+
+CLI for agentica
+
+options:
+  -h, --help            show this help message and exit
+  --query QUERY         Question to ask the LLM
+  --model_provider {openai,azure,moonshot,zhipuai,deepseek,yi}
+                        LLM model provider
+  --model_name MODEL_NAME
+                        LLM model name to use, can be
+                        gpt-4o/glm-4-flash/deepseek-chat/yi-lightning/...
+  --api_base API_BASE   API base URL for the LLM
+  --api_key API_KEY     API key for the LLM
+  --max_tokens MAX_TOKENS
+                        Maximum number of tokens for the LLM
+  --temperature TEMPERATURE
+                        Temperature for the LLM
+  --verbose VERBOSE     enable verbose mode
+  --tools [{search_serper,file_tool,shell_tool,yfinance_tool,web_search_pro,cogview,cogvideo,jina,wikipedia} ...]
+                        Tools to enable
+```
+
+run：
+
+```shell
+pip install agentica -U
+# 单次调用，填入`--query`参数
+agentica --query "下一届奥运会在哪里举办" --model_provider zhipuai --model_name glm-4-flash --tools web_search_pro
+# 多次调用，多轮对话，不填`--query`参数
+agentica --model_provider zhipuai --model_name glm-4-flash --tools web_search_pro cogview --verbose 1
+```
+
+output:
+```shell
+2024-12-30 21:59:15,000 - agentica - INFO - Agentica CLI
+>>> 帮我画个大象在月球上的图
+
+> 我帮你画了一张大象在月球上的图，它看起来既滑稽又可爱。大象穿着宇航服，站在月球表面，背景是广阔的星空和地球。这张图色彩明亮，细节丰富，具有卡通风格。你可以点击下面的链接查看和下载这张图片：
+
+![大象在月球上的图](https://aigc-files.bigmodel.cn/api/cogview/20241230215915cfa22f46425e4cb0_0.png)
+```
+
 ## ☎️ Contact
 
 - Issue(建议)

agentica-0.2.2/agentica.egg-info/PKG-INFO → agentica-0.2.5/README.md

@@ -1,34 +1,3 @@
-Metadata-Version: 2.1
-Name: agentica
-Version: 0.2.2
-Summary: LLM agents
-Home-page: https://github.com/shibing624/agentica
-Author: XuMing
-Author-email: xuming624@qq.com
-License: Apache License 2.0
-Keywords: Agentica,Agent Tool,action,agent,agentica
-Classifier: Development Status :: 5 - Production/Stable
-Classifier: Intended Audience :: Developers
-Classifier: Intended Audience :: Education
-Classifier: Intended Audience :: Science/Research
-Classifier: License :: OSI Approved :: Apache Software License
-Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3
-Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Requires-Python: >=3.8.0
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: loguru
-Requires-Dist: markdownify
-Requires-Dist: openai
-Requires-Dist: python-dotenv
-Requires-Dist: pydantic
-Requires-Dist: requests
-Requires-Dist: sqlalchemy
-Requires-Dist: scikit-learn
-Requires-Dist: tqdm
-Requires-Dist: rich
-
 [**🇨🇳中文**](https://github.com/shibing624/agentica/blob/main/README.md) | [**🌐English**](https://github.com/shibing624/agentica/blob/main/README_EN.md) | [**🇯🇵日本語**](https://github.com/shibing624/agentica/blob/main/README_JP.md)
 
 <div align="center">
@@ -49,14 +18,11 @@ Requires-Dist: rich
 [![Wechat Group](https://img.shields.io/badge/wechat-group-green.svg?logo=wechat)](#Contact)
 
 
-**Agentica**: Build Smarter, Reflective, and Collaborative AI Agents with Ease!
+**Agentica**: 轻松构建智能、具备反思能力、可协作的多模态AI Agent。
 
-**Agentica**: 快速打造智能、能反思、协作的AI Agent。
 
 ## 📖 Introduction
 
-**Agentica** can build AI agent, which have the components of planning, memory, and tool use. 
-
 **Agentica** 可以构建AI Agent，包括规划、记忆和工具使用、执行等组件。
 
 #### Agent Components
@@ -79,6 +45,8 @@ Requires-Dist: rich
 - **Solver**：求解器将所有这些输出整合为最终答案
 
 ## 🔥 News
+[2024/12/29] v0.2.3版本: 支持了`ZhipuAI`的api调用，包括免费模型和工具使用，详见[Release-v0.2.3](https://github.com/shibing624/agentica/releases/tag/0.2.3)
+
 [2024/12/25] v0.2.0版本: 支持了多模态模型，输入可以是文本、图片、音频、视频，升级Assistant为Agent，Workflow支持拆解并实现复杂任务，详见[Release-v0.2.0](https://github.com/shibing624/agentica/releases/tag/0.2.0)
 
 [2024/07/02] v0.1.0版本：实现了基于LLM的Assistant，可以快速用function call搭建大语言模型助手，详见[Release-v0.1.0](https://github.com/shibing624/agentica/releases/tag/0.1.0)
@@ -89,7 +57,7 @@ Requires-Dist: rich
 
 - **Agent编排**：通过简单代码快速编排Agent，支持 Reflection(反思）、Plan and Solve(计划并执行)、RAG、Agent、Multi-Agent、Team、Workflow等功能
 - **自定义prompt**：Agent支持自定义prompt和多种工具调用（tool_calls）
-- **LLM集成**：支持OpenAI、Azure、Deepseek、Moonshot、Claude、Ollama、Together等多方大模型厂商的API
+- **LLM集成**：支持OpenAI、Azure、Deepseek、Moonshot、Anthropic、ZhipuAI、Ollama、Together等多方大模型厂商的API
 - **记忆功能**：包括短期记忆和长期记忆功能
 - **Multi-Agent协作**：支持多Agent和任务委托（Team）的团队协作。
 - **Workflow工作流**：拆解复杂任务为多个Agent，基于工作流自动化串行逐步完成任务，如投资研究、新闻文章撰写和技术教程创建
@@ -118,10 +86,10 @@ pip install .
 cp .env.example ~/.agentica/.env
 
 cd examples
-python web_search_moonshot_demo.py
+python 12_web_search_moonshot_demo.py
 ```
 
-1. 复制[.env.example](https://github.com/shibing624/agentica/blob/main/.env.example)文件为`~/.agentica/.env`，并填写LLM api key(选填DEEPSEEK_API_KEY、MOONSHOT_API_KEY、OPENAI_API_KEY等任一个即可)。或者使用`export`命令设置环境变量：
+1. 复制[.env.example](https://github.com/shibing624/agentica/blob/main/.env.example)文件为`~/.agentica/.env`，并填写LLM api key(选填DEEPSEEK_API_KEY、MOONSHOT_API_KEY、OPENAI_API_KEY、ZHIPUAI_API_KEY等任一个即可)。或者使用`export`命令设置环境变量：
     
     ```shell
     export MOONSHOT_API_KEY=your_moonshot_api_key
@@ -133,13 +101,23 @@ python web_search_moonshot_demo.py
 自动调用google搜索工具，示例[examples/12_web_search_moonshot_demo.py](https://github.com/shibing624/agentica/blob/main/examples/12_web_search_moonshot_demo.py)
 
 ```python
-from agentica import Agent, MoonshotChat, SearchSerperTool
+from agentica import Agent, Moonshot, WeatherTool
 
-m = Agent(model=MoonshotChat(), tools=[SearchSerperTool()], add_datetime_to_instructions=True)
-r = m.run("下一届奥运会在哪里举办")
-print(r)
+m = Agent(model=Moonshot(), tools=[WeatherTool()], add_datetime_to_instructions=True)
+m.print_response("明天北京天气咋样")
 ```
 
+output:
+```markdown
+明天北京的天气预报如下：
+
+- 早晨：晴朗，气温约18°C，风速较小，约为3 km/h。
+- 中午：晴朗，气温升至23°C，风速6-7 km/h。
+- 傍晚：晴朗，气温略降至21°C，风速较大，为35-44 km/h。
+- 夜晚：晴朗转晴，气温下降至15°C，风速32-39 km/h。
+
+全天无降水，能见度良好。请注意傍晚时分的风速较大，外出时需注意安全。
+```
 
 ## ▶️ Web UI
 
@@ -204,6 +182,7 @@ bash start.sh
 | [examples/37_workflow_write_novel_demo.py](https://github.com/shibing624/agentica/blob/main/examples/37_workflow_write_novel_demo.py)                 | 实现了写小说的工作流：定小说提纲 - 搜索谷歌反思提纲 - 撰写小说内容 - 保存为md文件                                                                                    |
 | [examples/38_workflow_write_tutorial_demo.py](https://github.com/shibing624/agentica/blob/main/examples/38_workflow_write_tutorial_demo.py)           | 实现了写技术教程的工作流：定教程目录 - 反思目录内容 - 撰写教程内容 - 保存为md文件                                                                                    |
 | [examples/39_audio_multi_turn_demo.py](https://github.com/shibing624/agentica/blob/main/examples/39_audio_multi_turn_demo.py)                         | 基于openai的语音api做多轮音频对话的Demo                                                                                                        |
+| [examples/40_weather_zhipuai_demo.py](https://github.com/shibing624/agentica/blob/main/examples/40_web_search_zhipuai_demo.py)                        | 基于智谱AI的api做天气查询的Demo                                                                                                              |
 
 
 ### Self-evolving Agent
@@ -244,6 +223,63 @@ streamlit run 34_llm_os_demo.py
 
 <img alt="LLM OS" src="https://github.com/shibing624/agentica/blob/main/docs/llm_os_snap.png" width="800" />
 
+
+### 命令行模式（CLI）
+
+支持终端命令行快速搭建并体验Agent
+
+code: [cli.py](https://github.com/shibing624/agentica/blob/main/agentica/cli.py)
+
+```
+> agentica -h                                    
+usage: cli.py [-h] [--query QUERY]
+              [--model_provider {openai,azure,moonshot,zhipuai,deepseek,yi}]
+              [--model_name MODEL_NAME] [--api_base API_BASE]
+              [--api_key API_KEY] [--max_tokens MAX_TOKENS]
+              [--temperature TEMPERATURE] [--verbose VERBOSE]
+              [--tools [{search_serper,file_tool,shell_tool,yfinance_tool,web_search_pro,cogview,cogvideo,jina,wikipedia} ...]]
+
+CLI for agentica
+
+options:
+  -h, --help            show this help message and exit
+  --query QUERY         Question to ask the LLM
+  --model_provider {openai,azure,moonshot,zhipuai,deepseek,yi}
+                        LLM model provider
+  --model_name MODEL_NAME
+                        LLM model name to use, can be
+                        gpt-4o/glm-4-flash/deepseek-chat/yi-lightning/...
+  --api_base API_BASE   API base URL for the LLM
+  --api_key API_KEY     API key for the LLM
+  --max_tokens MAX_TOKENS
+                        Maximum number of tokens for the LLM
+  --temperature TEMPERATURE
+                        Temperature for the LLM
+  --verbose VERBOSE     enable verbose mode
+  --tools [{search_serper,file_tool,shell_tool,yfinance_tool,web_search_pro,cogview,cogvideo,jina,wikipedia} ...]
+                        Tools to enable
+```
+
+run：
+
+```shell
+pip install agentica -U
+# 单次调用，填入`--query`参数
+agentica --query "下一届奥运会在哪里举办" --model_provider zhipuai --model_name glm-4-flash --tools web_search_pro
+# 多次调用，多轮对话，不填`--query`参数
+agentica --model_provider zhipuai --model_name glm-4-flash --tools web_search_pro cogview --verbose 1
+```
+
+output:
+```shell
+2024-12-30 21:59:15,000 - agentica - INFO - Agentica CLI
+>>> 帮我画个大象在月球上的图
+
+> 我帮你画了一张大象在月球上的图，它看起来既滑稽又可爱。大象穿着宇航服，站在月球表面，背景是广阔的星空和地球。这张图色彩明亮，细节丰富，具有卡通风格。你可以点击下面的链接查看和下载这张图片：
+
+![大象在月球上的图](https://aigc-files.bigmodel.cn/api/cogview/20241230215915cfa22f46425e4cb0_0.png)
+```
+
 ## ☎️ Contact
 
 - Issue(建议)

{agentica-0.2.2 → agentica-0.2.5}/agentica/__init__.py

@@ -14,13 +14,30 @@ from agentica.utils.log import set_log_level_to_debug, logger
 from agentica.utils.io import write_audio_to_file
 # model
 from agentica.model.openai.chat import OpenAIChat
+from agentica.model.openai.chat import OpenAIChat as OpenAILLM
+from agentica.model.openai.like import OpenAILike
 from agentica.model.azure.openai_chat import AzureOpenAIChat
-from agentica.model.moonshot import MoonshotChat
-from agentica.model.deepseek.chat import DeepSeekChat
-from agentica.model.doubao.chat import DoubaoChat
-from agentica.model.together.togetherchat import TogetherChat
-from agentica.model.xai.grok import GrokChat
-from agentica.model.yi.chat import YiChat
+from agentica.model.azure.openai_chat import AzureOpenAIChat as AzureOpenAILLM
+from agentica.model.moonshot import Moonshot
+from agentica.model.moonshot import Moonshot as MoonshotChat
+from agentica.model.moonshot import Moonshot as MoonshotLLM
+from agentica.model.deepseek.chat import DeepSeek
+from agentica.model.deepseek.chat import DeepSeek as DeepSeekChat
+from agentica.model.deepseek.chat import DeepSeek as DeepSeekLLM
+from agentica.model.doubao.chat import Doubao
+from agentica.model.doubao.chat import Doubao as DoubaoChat
+from agentica.model.together.together import Together
+from agentica.model.together.together import Together as TogetherChat
+from agentica.model.together.together import Together as TogetherLLM
+from agentica.model.xai.grok import Grok
+from agentica.model.xai.grok import Grok as GrokChat
+from agentica.model.yi.chat import Yi
+from agentica.model.yi.chat import Yi as YiChat
+from agentica.model.yi.chat import Yi as YiLLM
+from agentica.model.qwen.chat import Qwen
+from agentica.model.zhipuai.chat import ZhipuAI
+from agentica.model.zhipuai.chat import ZhipuAI as ZhipuAIChat
+from agentica.model.zhipuai.chat import ZhipuAI as ZhipuAILLM
 
 # memory
 from agentica.model.base import Model
@@ -72,6 +89,7 @@ from agentica.emb.hash_emb import HashEmb
 from agentica.emb.ollama_emb import OllamaEmb
 from agentica.emb.together_emb import TogetherEmb
 from agentica.emb.fireworks_emb import FireworksEmb
+from agentica.emb.zhipuai_emb import ZhipuAIEmb
 
 # file
 from agentica.file.base import File
@@ -94,12 +112,13 @@ from agentica.tools.search_serper_tool import SearchSerperTool
 from agentica.tools.run_python_code_tool import RunPythonCodeTool
 from agentica.tools.analyze_image_tool import AnalyzeImageTool
 from agentica.tools.calculator_tool import CalculatorTool
-from agentica.tools.create_image_tool import CreateImageTool
+from agentica.tools.dalle_tool import DalleTool
 from agentica.tools.file_tool import FileTool
 from agentica.tools.hackernews_tool import HackerNewsTool
 from agentica.tools.jina_tool import JinaTool
 from agentica.tools.shell_tool import ShellTool
 from agentica.tools.text_analysis_tool import TextAnalysisTool
+from agentica.tools.weather_tool import WeatherTool
 
 # agent
 from agentica.agent import Agent

{agentica-0.2.2 → agentica-0.2.5}/agentica/agent.py

@@ -7,6 +7,7 @@ part of the code from https://github.com/phidatahq/phidata
 from __future__ import annotations
 
 import json
+import os
 from datetime import datetime
 from textwrap import dedent
 from collections import defaultdict, deque
@@ -30,6 +31,7 @@ from uuid import uuid4
 from pathlib import Path
 from pydantic import BaseModel, ConfigDict, field_validator, Field, ValidationError
 
+from agentica.utils.log import logger, set_log_level_to_debug, set_log_level_to_info
 from agentica.document import Document
 from agentica.knowledge.base import Knowledge
 from agentica.model.openai import OpenAIChat
@@ -44,10 +46,11 @@ from agentica.reasoning import ReasoningStep, ReasoningSteps, NextAction
 from agentica.run_response import RunEvent, RunResponse, RunResponseExtraData
 from agentica.memory import AgentMemory, Memory, AgentRun, SessionSummary
 from agentica.storage.agent.base import AgentStorage
-from agentica.utils.log import logger, set_log_level_to_debug
-from agentica.utils.misc import get_text_from_message
+from agentica.utils.message import get_text_from_message
 from agentica.utils.timer import Timer
 from agentica.agent_session import AgentSession
+from agentica.media import AudioResponse
+from agentica.utils.string import parse_structured_output
 
 
 class Agent(BaseModel):
@@ -200,9 +203,6 @@ class Agent(BaseModel):
     add_datetime_to_instructions: bool = False
 
     # -*- User Prompt Settings
-    # User prompt: provide the user prompt as a string
-    # Note: this will ignore the message sent to the run function
-    user_prompt: Optional[Union[List, Dict, str, Callable]] = None
     # User prompt template: provide the user prompt as a PromptTemplate
     user_prompt_template: Optional[PromptTemplate] = None
     # If True, build a default user prompt using references and chat history
@@ -234,7 +234,7 @@ class Agent(BaseModel):
     team_response_separator: str = "\n"
 
     # debug_mode=True enables debug logs
-    debug_mode: bool = Field(False, validate_default=True)
+    debug_mode: bool = Field(False, validate_default=True, alias="debug")
     # monitoring=True logs Agent information
     monitoring: bool = False
 
@@ -252,6 +252,15 @@ class Agent(BaseModel):
 
     model_config = ConfigDict(arbitrary_types_allowed=True, populate_by_name=True, extra="allow")
 
+    @field_validator("debug_mode", mode="before")
+    def set_log_level(cls, v: bool) -> bool:
+        if v:
+            set_log_level_to_debug()
+            logger.debug("Debug logs enabled")
+        elif v is False:
+            set_log_level_to_info()
+        return v
+
     @field_validator("agent_id", mode="before")
     def set_agent_id(cls, v: Optional[str]) -> str:
         agent_id = v or str(uuid4())
@@ -264,13 +273,6 @@ class Agent(BaseModel):
         logger.debug(f"*********** Session ID: {session_id} ***********")
         return session_id
 
-    @field_validator("debug_mode", mode="before")
-    def set_log_level(cls, v: bool) -> bool:
-        if v:
-            set_log_level_to_debug()
-            logger.debug("Debug logs enabled")
-        return v
-
     @property
     def is_streamable(self) -> bool:
         """Determines if the response from the Model is streamable
@@ -1126,14 +1128,14 @@ class Agent(BaseModel):
     ) -> Optional[Message]:
         """Return the user message for the Agent.
 
-        1. If the user_prompt is provided, use that.
+        1. Get references.
         2. If the user_prompt_template is provided, build the user_message using the template.
         3. If the message is None, return None.
         4. 4. If use_default_user_message is False or If the message is not a string, return the message as is.
         5. If add_references is False or references is None, return the message as is.
         6. Build the default user message for the Agent
         """
-        # Get references from the knowledge base to use in the user message
+        # 1. Get references from the knowledge base to use in the user message
         references = None
         if self.add_references and message and isinstance(message, str):
             retrieval_timer = Timer()
@@ -1152,23 +1154,6 @@ class Agent(BaseModel):
             retrieval_timer.stop()
             logger.debug(f"Time to get references: {retrieval_timer.elapsed:.4f}s")
 
-        # 1. If the user_prompt is provided, use that.
-        if self.user_prompt is not None:
-            user_prompt_content = self.user_prompt
-            if callable(self.user_prompt):
-                user_prompt_kwargs = {"agent": self, "message": message, "references": references}
-                user_prompt_content = self.user_prompt(**user_prompt_kwargs)
-                if not isinstance(user_prompt_content, str):
-                    raise Exception("User prompt must return a string")
-            return Message(
-                role=self.user_message_role,
-                content=user_prompt_content,
-                audio=audio,
-                images=images,
-                videos=videos,
-                **kwargs,
-            )
-
         # 2. If the user_prompt_template is provided, build the user_message using the template.
         if self.user_prompt_template is not None:
             user_prompt_kwargs = {"agent": self, "message": message, "references": references}
@@ -1784,6 +1769,11 @@ class Agent(BaseModel):
             model_response = ModelResponse(content="")
             for model_response_chunk in self.model.response_stream(messages=messages_for_model):
                 if model_response_chunk.event == ModelResponseEvent.assistant_response.value:
+                    if model_response_chunk.reasoning_content is not None:
+                        model_response.content += model_response_chunk.reasoning_content
+                        self.run_response.content = model_response_chunk.reasoning_content
+                        self.run_response.created_at = model_response_chunk.created_at
+                        yield self.run_response
                     if model_response_chunk.content is not None and model_response.content is not None:
                         model_response.content += model_response_chunk.content
                         self.run_response.content = model_response_chunk.content
@@ -1991,20 +1981,9 @@ class Agent(BaseModel):
             # Otherwise convert the response to the structured format
             if isinstance(run_response.content, str):
                 try:
-                    structured_output = None
-                    try:
-                        structured_output = self.response_model.model_validate_json(run_response.content)
-                    except ValidationError as exc:
-                        logger.warning(f"Failed to convert response to pydantic model: {exc}")
-                        # Check if response starts with ```json
-                        if run_response.content.startswith("```json"):
-                            run_response.content = run_response.content.replace("```json\n", "").replace("\n```", "")
-                            try:
-                                structured_output = self.response_model.model_validate_json(run_response.content)
-                            except ValidationError as exc:
-                                logger.warning(f"Failed to convert response to pydantic model: {exc}")
+                    structured_output = parse_structured_output(run_response.content, self.response_model)
 
-                    # -*- Update Agent response
+                    # Update RunResponse
                     if structured_output is not None:
                         run_response.content = structured_output
                         run_response.content_type = self.response_model.__name__
@@ -2307,7 +2286,8 @@ class Agent(BaseModel):
                         logger.warning(f"Failed to convert response to pydantic model: {exc}")
                         # Check if response starts with ```json
                         if run_response.content.startswith("```json"):
-                            run_response.content = run_response.content.replace("```json\n", "").replace("\n```", "")
+                            run_response.content = run_response.content.replace(
+                                "```json\n", "").replace("\n```", "")
                             try:
                                 structured_output = self.response_model.model_validate_json(run_response.content)
                             except ValidationError as exc:
@@ -3089,4 +3069,3 @@ class Agent(BaseModel):
                 break
 
             self.print_response(message=message, stream=stream, markdown=markdown, **kwargs)
-