agentica 0.0.6__tar.gz → 0.1.1__tar.gz

{agentica-0.0.6 → agentica-0.1.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: agentica
-Version: 0.0.6
+Version: 0.1.1
 Summary: LLM agents
 Home-page: https://github.com/shibing624/agentica
 Author: XuMing
@@ -20,7 +20,7 @@ Requires-Python: >=3.8.0
 Description-Content-Type: text/markdown
 License-File: LICENSE
 
-[**🇨🇳中文**](https://github.com/shibing624/agentica/blob/main/README.md) | [**🌐English**](https://github.com/shibing624/agentica/blob/main/README_EN.md)
+[**🇨🇳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">
   <a href="https://github.com/shibing624/agentica">
@@ -47,7 +47,7 @@ License-File: LICENSE
 ## Overview
 
 #### LLM Agent
-![llm_agnet](https://github.com/shibing624/agentica/blob/main/docs/llm_agent.png)
+![llm_agnet](https://github.com/shibing624/agentica/blob/main/docs/llm_agentv2.png)
 
 - **规划（Planning）**：任务拆解、生成计划、反思
 - **记忆（Memory）**：短期记忆（prompt实现）、长期记忆（RAG实现）
@@ -63,9 +63,9 @@ License-File: LICENSE
 ## Features
 `agentica`是一个Agent构建工具，功能：
 
-- 简单代码快速编排Agent，支持RAG、Workflow、MultiAgent、MultiRole等
+- 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、Multi-Role、Workflow等功能
 - Agent支持prompt自定义，支持多种工具调用（tool_calls）
-- 支持OpenAI API和Moonshot API(kimi)调用
+- 支持OpenAI/Azure/Claude/Ollama/Together API调用
 
 ## Installation
 
@@ -104,27 +104,47 @@ m = Assistant(
   read_chat_history=True,
   debug_mode=True,
 )
-m.run("一句话介绍林黛玉")
-m.run("北京最近的新闻", stream=True, print_output=True)
-m.run("总结前面的问答")
+
+r = m.run("一句话介绍林黛玉")
+print(r, "".join(r))
+r = m.run("北京最近的新闻", stream=True, print_output=True)
+print(r, "".join(r))
+r = m.run("总结前面的问答", stream=False, print_output=False)
+print(r)
 ```
 
 
 ## Examples
 
-| 示例                                                                                                                                  | 描述                                                                                                                              |
-|-------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------|
-| [examples/naive_rag_demo.py](https://github.com/shibing624/agentica/blob/main/examples/naive_rag_demo.py)                         | 实现了基础版RAG，基于Txt文档回答问题                                                                                                           |
-| [examples/advanced_rag_demo.py](https://github.com/shibing624/agentica/blob/main/examples/advanced_rag_demo.py)                   | 实现了高级版RAG，基于PDF文档回答问题，新增功能：pdf文件解析、query改写，字面+语义多路召回，召回排序（rerank）                                                               |
-| [examples/python_assistant_demo.py](https://github.com/shibing624/agentica/blob/main/examples/python_assistant_demo.py)           | 实现了Code Interpreter功能，自动生成python代码，并执行                                                                                          |
-| [examples/research_demo.py](https://github.com/shibing624/agentica/blob/main/examples/research_demo.py)                           | 实现了Research功能，自动调用搜索工具，汇总信息后撰写科技报告                                                                                              |
-| [examples/run_flow_news_article_demo.py](https://github.com/shibing624/agentica/blob/main/examples/run_flow_news_article_demo.py) | 实现了写新闻稿的工作流，multi-agent的实现，定义了多个Assistant和Task，多次调用搜索工具，并生成高级排版的新闻文章                                                            |
-| [examples/run_flow_investment_demo.py](https://github.com/shibing624/agentica/blob/main/examples/run_flow_investment_demo.py)     | 实现了投资研究的工作流：股票信息收集 - 股票分析 - 撰写分析报告 - 复查报告等多个Task                                                                                |
-| [examples/crawl_webpage.py](https://github.com/shibing624/agentica/blob/main/examples/crawl_webpage.py)                           | 实现了网页分析工作流：从Url爬取融资快讯 - 分析网页内容和格式 - 提取核心信息 - 汇总保存为md文件                                                                          |
-| [examples/find_paper_from_arxiv.py](https://github.com/shibing624/agentica/blob/main/examples/find_paper_from_arxiv.py)           | 实现了论文推荐工作流：自动从arxiv搜索多组论文 - 相似论文去重 - 提取核心论文信息 - 保存为csv文件                                                                        |
-| [examples/remove_image_background.py](https://github.com/shibing624/agentica/blob/main/examples/remove_image_background.py)       | 实现了自动去除图片背景功能，包括自动通过pip安装库，调用库实现去除图片背景                                                                                          |
-| [examples/text_classification_demo.py](https://github.com/shibing624/agentica/blob/main/examples/text_classification_demo.py)     | 实现了自动训练分类模型的工作流：读取训练集文件并理解格式 - 谷歌搜索pytextclassifier库 - 爬取github页面了解pytextclassifier的调用方法 - 写代码并执行fasttext模型训练 - check训练好的模型预测结果 |
+| 示例                                                                                                                                    | 描述                                                                                                                              |
+|---------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------|
+| [examples/naive_rag_demo.py](https://github.com/shibing624/agentica/blob/main/examples/naive_rag_demo.py)                             | 实现了基础版RAG，基于Txt文档回答问题                                                                                                           |
+| [examples/advanced_rag_demo.py](https://github.com/shibing624/agentica/blob/main/examples/advanced_rag_demo.py)                       | 实现了高级版RAG，基于PDF文档回答问题，新增功能：pdf文件解析、query改写，字面+语义多路召回，召回排序（rerank）                                                               |
+| [examples/python_assistant_demo.py](https://github.com/shibing624/agentica/blob/main/examples/python_assistant_demo.py)               | 实现了Code Interpreter功能，自动生成python代码，并执行                                                                                          |
+| [examples/research_demo.py](https://github.com/shibing624/agentica/blob/main/examples/research_demo.py)                               | 实现了Research功能，自动调用搜索工具，汇总信息后撰写科技报告                                                                                              |
+| [examples/team_news_article_demo.py](https://github.com/shibing624/agentica/blob/main/examples/team_news_article_demo.py)             | 实现了写新闻稿的team协作，multi-role实现，委托不用角色完成各自任务：研究员检索分析文章，撰写员根据排版写文章，汇总多角色成果输出结果                                                       |
+| [examples/workflow_news_article_demo.py](https://github.com/shibing624/agentica/blob/main/examples/workflow_news_article_demo.py)     | 实现了写新闻稿的工作流，multi-agent的实现，定义了多个Assistant和Task，多次调用搜索工具，并生成高级排版的新闻文章                                                            |
+| [examples/workflow_investment_demo.py](https://github.com/shibing624/agentica/blob/main/examples/workflow_investment_demo.py)         | 实现了投资研究的工作流：股票信息收集 - 股票分析 - 撰写分析报告 - 复查报告等多个Task                                                                                |
+| [examples/crawl_webpage_demo.py](https://github.com/shibing624/agentica/blob/main/examples/crawl_webpage_demo.py)                          | 实现了网页分析工作流：从Url爬取融资快讯 - 分析网页内容和格式 - 提取核心信息 - 汇总保存为md文件                                                                          |
+| [examples/find_paper_from_arxiv_demo.py](https://github.com/shibing624/agentica/blob/main/examples/find_paper_from_arxiv_demo.py)     | 实现了论文推荐工作流：自动从arxiv搜索多组论文 - 相似论文去重 - 提取核心论文信息 - 保存为csv文件                                                                        |
+| [examples/remove_image_background_demo.py](https://github.com/shibing624/agentica/blob/main/examples/remove_image_background_demo.py) | 实现了自动去除图片背景功能，包括自动通过pip安装库，调用库实现去除图片背景                                                                                          |
+| [examples/text_classification_demo.py](https://github.com/shibing624/agentica/blob/main/examples/text_classification_demo.py)         | 实现了自动训练分类模型的工作流：读取训练集文件并理解格式 - 谷歌搜索pytextclassifier库 - 爬取github页面了解pytextclassifier的调用方法 - 写代码并执行fasttext模型训练 - check训练好的模型预测结果 |
+| [examples/llm_os_demo.py](https://github.com/shibing624/agentica/blob/main/examples/llm_os_demo.py)                                   | 实现了LLM OS的初步设计，基于LLM设计操作系统，可以通过LLM调用RAG、代码执行器、Shell等工具，并协同代码解释器、研究助手、投资助手等来解决问题。                                                |
+
+
+### LLM OS
+The LLM OS design:
+
+<img alt="LLM OS" src="https://github.com/shibing624/agentica/blob/main/docs/llmos.png" width="600" />
+
+#### Run the LLM OS App
+
+```shell
+cd examples
+streamlit run llm_os_demo.py
+```
 
+![llm_os](https://github.com/shibing624/agentica/blob/main/docs/llm_os_snap.png)
 
 ## Contact
 

{agentica-0.0.6 → agentica-0.1.1}/README.md

@@ -1,4 +1,4 @@
-[**🇨🇳中文**](https://github.com/shibing624/agentica/blob/main/README.md) | [**🌐English**](https://github.com/shibing624/agentica/blob/main/README_EN.md)
+[**🇨🇳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">
   <a href="https://github.com/shibing624/agentica">
@@ -25,7 +25,7 @@
 ## Overview
 
 #### LLM Agent
-![llm_agnet](https://github.com/shibing624/agentica/blob/main/docs/llm_agent.png)
+![llm_agnet](https://github.com/shibing624/agentica/blob/main/docs/llm_agentv2.png)
 
 - **规划（Planning）**：任务拆解、生成计划、反思
 - **记忆（Memory）**：短期记忆（prompt实现）、长期记忆（RAG实现）
@@ -41,9 +41,9 @@
 ## Features
 `agentica`是一个Agent构建工具，功能：
 
-- 简单代码快速编排Agent，支持RAG、Workflow、MultiAgent、MultiRole等
+- 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、Multi-Role、Workflow等功能
 - Agent支持prompt自定义，支持多种工具调用（tool_calls）
-- 支持OpenAI API和Moonshot API(kimi)调用
+- 支持OpenAI/Azure/Claude/Ollama/Together API调用
 
 ## Installation
 
@@ -82,27 +82,47 @@ m = Assistant(
   read_chat_history=True,
   debug_mode=True,
 )
-m.run("一句话介绍林黛玉")
-m.run("北京最近的新闻", stream=True, print_output=True)
-m.run("总结前面的问答")
+
+r = m.run("一句话介绍林黛玉")
+print(r, "".join(r))
+r = m.run("北京最近的新闻", stream=True, print_output=True)
+print(r, "".join(r))
+r = m.run("总结前面的问答", stream=False, print_output=False)
+print(r)
 ```
 
 
 ## Examples
 
-| 示例                                                                                                                                  | 描述                                                                                                                              |
-|-------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------|
-| [examples/naive_rag_demo.py](https://github.com/shibing624/agentica/blob/main/examples/naive_rag_demo.py)                         | 实现了基础版RAG，基于Txt文档回答问题                                                                                                           |
-| [examples/advanced_rag_demo.py](https://github.com/shibing624/agentica/blob/main/examples/advanced_rag_demo.py)                   | 实现了高级版RAG，基于PDF文档回答问题，新增功能：pdf文件解析、query改写，字面+语义多路召回，召回排序（rerank）                                                               |
-| [examples/python_assistant_demo.py](https://github.com/shibing624/agentica/blob/main/examples/python_assistant_demo.py)           | 实现了Code Interpreter功能，自动生成python代码，并执行                                                                                          |
-| [examples/research_demo.py](https://github.com/shibing624/agentica/blob/main/examples/research_demo.py)                           | 实现了Research功能，自动调用搜索工具，汇总信息后撰写科技报告                                                                                              |
-| [examples/run_flow_news_article_demo.py](https://github.com/shibing624/agentica/blob/main/examples/run_flow_news_article_demo.py) | 实现了写新闻稿的工作流，multi-agent的实现，定义了多个Assistant和Task，多次调用搜索工具，并生成高级排版的新闻文章                                                            |
-| [examples/run_flow_investment_demo.py](https://github.com/shibing624/agentica/blob/main/examples/run_flow_investment_demo.py)     | 实现了投资研究的工作流：股票信息收集 - 股票分析 - 撰写分析报告 - 复查报告等多个Task                                                                                |
-| [examples/crawl_webpage.py](https://github.com/shibing624/agentica/blob/main/examples/crawl_webpage.py)                           | 实现了网页分析工作流：从Url爬取融资快讯 - 分析网页内容和格式 - 提取核心信息 - 汇总保存为md文件                                                                          |
-| [examples/find_paper_from_arxiv.py](https://github.com/shibing624/agentica/blob/main/examples/find_paper_from_arxiv.py)           | 实现了论文推荐工作流：自动从arxiv搜索多组论文 - 相似论文去重 - 提取核心论文信息 - 保存为csv文件                                                                        |
-| [examples/remove_image_background.py](https://github.com/shibing624/agentica/blob/main/examples/remove_image_background.py)       | 实现了自动去除图片背景功能，包括自动通过pip安装库，调用库实现去除图片背景                                                                                          |
-| [examples/text_classification_demo.py](https://github.com/shibing624/agentica/blob/main/examples/text_classification_demo.py)     | 实现了自动训练分类模型的工作流：读取训练集文件并理解格式 - 谷歌搜索pytextclassifier库 - 爬取github页面了解pytextclassifier的调用方法 - 写代码并执行fasttext模型训练 - check训练好的模型预测结果 |
+| 示例                                                                                                                                    | 描述                                                                                                                              |
+|---------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------|
+| [examples/naive_rag_demo.py](https://github.com/shibing624/agentica/blob/main/examples/naive_rag_demo.py)                             | 实现了基础版RAG，基于Txt文档回答问题                                                                                                           |
+| [examples/advanced_rag_demo.py](https://github.com/shibing624/agentica/blob/main/examples/advanced_rag_demo.py)                       | 实现了高级版RAG，基于PDF文档回答问题，新增功能：pdf文件解析、query改写，字面+语义多路召回，召回排序（rerank）                                                               |
+| [examples/python_assistant_demo.py](https://github.com/shibing624/agentica/blob/main/examples/python_assistant_demo.py)               | 实现了Code Interpreter功能，自动生成python代码，并执行                                                                                          |
+| [examples/research_demo.py](https://github.com/shibing624/agentica/blob/main/examples/research_demo.py)                               | 实现了Research功能，自动调用搜索工具，汇总信息后撰写科技报告                                                                                              |
+| [examples/team_news_article_demo.py](https://github.com/shibing624/agentica/blob/main/examples/team_news_article_demo.py)             | 实现了写新闻稿的team协作，multi-role实现，委托不用角色完成各自任务：研究员检索分析文章，撰写员根据排版写文章，汇总多角色成果输出结果                                                       |
+| [examples/workflow_news_article_demo.py](https://github.com/shibing624/agentica/blob/main/examples/workflow_news_article_demo.py)     | 实现了写新闻稿的工作流，multi-agent的实现，定义了多个Assistant和Task，多次调用搜索工具，并生成高级排版的新闻文章                                                            |
+| [examples/workflow_investment_demo.py](https://github.com/shibing624/agentica/blob/main/examples/workflow_investment_demo.py)         | 实现了投资研究的工作流：股票信息收集 - 股票分析 - 撰写分析报告 - 复查报告等多个Task                                                                                |
+| [examples/crawl_webpage_demo.py](https://github.com/shibing624/agentica/blob/main/examples/crawl_webpage_demo.py)                          | 实现了网页分析工作流：从Url爬取融资快讯 - 分析网页内容和格式 - 提取核心信息 - 汇总保存为md文件                                                                          |
+| [examples/find_paper_from_arxiv_demo.py](https://github.com/shibing624/agentica/blob/main/examples/find_paper_from_arxiv_demo.py)     | 实现了论文推荐工作流：自动从arxiv搜索多组论文 - 相似论文去重 - 提取核心论文信息 - 保存为csv文件                                                                        |
+| [examples/remove_image_background_demo.py](https://github.com/shibing624/agentica/blob/main/examples/remove_image_background_demo.py) | 实现了自动去除图片背景功能，包括自动通过pip安装库，调用库实现去除图片背景                                                                                          |
+| [examples/text_classification_demo.py](https://github.com/shibing624/agentica/blob/main/examples/text_classification_demo.py)         | 实现了自动训练分类模型的工作流：读取训练集文件并理解格式 - 谷歌搜索pytextclassifier库 - 爬取github页面了解pytextclassifier的调用方法 - 写代码并执行fasttext模型训练 - check训练好的模型预测结果 |
+| [examples/llm_os_demo.py](https://github.com/shibing624/agentica/blob/main/examples/llm_os_demo.py)                                   | 实现了LLM OS的初步设计，基于LLM设计操作系统，可以通过LLM调用RAG、代码执行器、Shell等工具，并协同代码解释器、研究助手、投资助手等来解决问题。                                                |
+
+
+### LLM OS
+The LLM OS design:
+
+<img alt="LLM OS" src="https://github.com/shibing624/agentica/blob/main/docs/llmos.png" width="600" />
+
+#### Run the LLM OS App
+
+```shell
+cd examples
+streamlit run llm_os_demo.py
+```
 
+![llm_os](https://github.com/shibing624/agentica/blob/main/docs/llm_os_snap.png)
 
 ## Contact
 

{agentica-0.0.6 → agentica-0.1.1}/agentica/__init__.py

@@ -8,9 +8,11 @@ from agentica.config import DOTENV_PATH, SMART_LLM, FAST_LLM  # noqa, isort: ski
 from agentica.assistant import Assistant
 from agentica.python_assistant import PythonAssistant
 from agentica.document import Document
-from agentica.documents import Documents
+from agentica.knowledge.knowledge_base import KnowledgeBase
 from agentica.llm.openai_llm import OpenAILLM
 from agentica.llm.azure_llm import AzureOpenAILLM
+from agentica.llm.together_llm import TogetherLLM
+from agentica.llm.moonshot_llm import MoonshotLLM
 from agentica.task import Task
 from agentica.workflow import Workflow
 

{agentica-0.0.6 → agentica-0.1.1}/agentica/assistant.py

@@ -29,7 +29,7 @@ from uuid import uuid4
 from pydantic import BaseModel, ConfigDict, field_validator, ValidationError
 
 from agentica.document import Document
-from agentica.documents import Documents
+from agentica.knowledge.knowledge_base import KnowledgeBase
 from agentica.llm.base import LLM
 from agentica.memory import AssistantMemory, Memory
 from agentica.message import Message
@@ -81,7 +81,7 @@ class Assistant(BaseModel):
     update_memory_after_run: bool = True
 
     # -*- Assistant Knowledge Base
-    knowledge_base: Optional[Documents] = None
+    knowledge_base: Optional[KnowledgeBase] = None
     # Enable RAG by adding references from the knowledge base to the prompt.
     add_references_to_prompt: bool = False
 
@@ -790,6 +790,7 @@ class Assistant(BaseModel):
             *,
             stream: bool = True,
             messages: Optional[List[Union[Dict, Message]]] = None,
+            print_output: bool = True,
             **kwargs: Any,
     ) -> Iterator[str]:
         logger.debug(f"*********** Assistant Run Start: {self.run_id} ***********")
@@ -865,6 +866,8 @@ class Assistant(BaseModel):
         self.llm = cast(LLM, self.llm)
         if stream and self.streamable:
             for response_chunk in self.llm.response_stream(messages=llm_messages):
+                if print_output:
+                    print_llm_stream(response_chunk)
                 llm_response += response_chunk
                 yield response_chunk
         else:
@@ -922,6 +925,8 @@ class Assistant(BaseModel):
 
         # -*- Yield final response if not streaming
         if not stream:
+            if print_output:
+                print(llm_response)
             yield llm_response
 
     def run(
@@ -929,8 +934,8 @@ class Assistant(BaseModel):
             message: Optional[Union[List, Dict, str]] = None,
             *,
             stream: bool = True,
-            print_output: bool = True,
             messages: Optional[List[Union[Dict, Message]]] = None,
+            print_output: bool = True,
             **kwargs: Any,
     ) -> Union[Iterator[str], str, BaseModel]:
         # Convert response to structured output if output_model is set
@@ -959,16 +964,11 @@ class Assistant(BaseModel):
             return self.output or json_resp
         else:
             if stream and self.streamable:
-                resp = self._run(message=message, messages=messages, stream=True, **kwargs)
-                if print_output:
-                    for chunk in resp:
-                        print_llm_stream(chunk)
+                resp = self._run(message=message, messages=messages, stream=True, print_output=print_output, **kwargs)
                 return resp
             else:
-                resp = self._run(message=message, messages=messages, stream=False, **kwargs)
+                resp = self._run(message=message, messages=messages, stream=False, print_output=print_output, **kwargs)
                 resp = next(resp)
-                if print_output:
-                    print(resp)
                 return resp
 
     async def _arun(
@@ -977,6 +977,7 @@ class Assistant(BaseModel):
             *,
             stream: bool = True,
             messages: Optional[List[Union[Dict, Message]]] = None,
+            print_output: bool = True,
             **kwargs: Any,
     ) -> AsyncIterator[str]:
         logger.debug(f"*********** Run Start: {self.run_id} ***********")
@@ -1055,6 +1056,8 @@ class Assistant(BaseModel):
             response_stream = self.llm.aresponse_stream(messages=llm_messages)
             async for response_chunk in response_stream:  # type: ignore
                 llm_response += response_chunk
+                if print_output:
+                    print_llm_stream(response_chunk)
                 yield response_chunk
         else:
             llm_response = await self.llm.aresponse(messages=llm_messages)
@@ -1089,6 +1092,8 @@ class Assistant(BaseModel):
 
         # -*- Yield final response if not streaming
         if not stream:
+            if print_output:
+                print(llm_response)
             yield llm_response
 
     async def arun(
@@ -1096,8 +1101,8 @@ class Assistant(BaseModel):
             message: Optional[Union[List, Dict, str]] = None,
             *,
             stream: bool = True,
-            print_output: bool = True,
             messages: Optional[List[Union[Dict, Message]]] = None,
+            print_output: bool = True,
             **kwargs: Any,
     ) -> Union[AsyncIterator[str], str, BaseModel]:
         # Convert response to structured output if output_model is set
@@ -1127,17 +1132,11 @@ class Assistant(BaseModel):
             return self.output or json_resp
         else:
             if stream and self.streamable:
-                resp = self._arun(message=message, messages=messages, stream=True, **kwargs)
-                if print_output:
-                    async for chunk in resp:
-                        print_llm_stream(chunk)
+                resp = self._arun(message=message, messages=messages, stream=True, print_output=print_output, **kwargs)
                 return resp
             else:
-                resp = self._arun(message=message, messages=messages, stream=False, **kwargs)
-                r = await resp.__anext__()
-                if print_output:
-                    print(r)
-                return r
+                resp = self._arun(message=message, messages=messages, stream=False, print_output=print_output, **kwargs)
+                return await resp.__anext__()
 
     def chat(
             self, message: Union[List, Dict, str], stream: bool = True, **kwargs: Any
@@ -1213,13 +1212,13 @@ class Assistant(BaseModel):
     # Default Tools
     ###########################################################################
 
-    def get_chat_history(self, num_chats: Optional[int] = None) -> str:
+    def get_chat_history(self, num_chats: int = 5) -> str:
         """Use this function to get the chat history between the user and assistant.
 
         Args:
             num_chats: The number of chats to return.
                 Each chat contains 2 messages. One from the user and one from the assistant.
-                Default: None
+                Default: 5
 
         Returns:
             str: A JSON of a list of dictionaries representing the chat history.
@@ -1227,8 +1226,8 @@ class Assistant(BaseModel):
         Example:
             - To get the last chat, use num_chats=1.
             - To get the last 5 chats, use num_chats=5.
-            - To get all chats, use num_chats=None.
-            - To get the first chat, use num_chats=None and pick the first message.
+            - To get all chats, use num_chats=-1.
+            - To get the first chat, use num_chats=-1 and pick the first message.
         """
         history: List[Dict[str, Any]] = []
         all_chats = self.memory.get_chats()
@@ -1240,9 +1239,9 @@ class Assistant(BaseModel):
             history.insert(0, chat[1].to_dict())
             history.insert(0, chat[0].to_dict())
             chats_added += 1
-            if num_chats is not None and chats_added >= num_chats:
+            if 0 < num_chats <= chats_added:
                 break
-        return json.dumps(history)
+        return json.dumps(history, ensure_ascii=False)
 
     def get_tool_call_history(self, num_calls: int = 3) -> str:
         """Use this function to get the tools called by the assistant in reverse chronological order.
@@ -1256,13 +1255,13 @@ class Assistant(BaseModel):
 
         Example:
             - To get the last tool call, use num_calls=1.
-            - To get all tool calls, use num_calls=None.
+            - To get all tool calls, use num_calls=-1.
         """
         tool_calls = self.memory.get_tool_calls(num_calls)
         if len(tool_calls) == 0:
             return ""
         logger.debug(f"tool_calls: {tool_calls}")
-        return json.dumps(tool_calls)
+        return json.dumps(tool_calls, ensure_ascii=False)
 
     def search_knowledge_base(self, query: str) -> str:
         """Use this function to search the knowledge base for information about a query.
@@ -1334,7 +1333,6 @@ class Assistant(BaseModel):
             user: str = "User",
             emoji: str = ":sunglasses:",
             stream: bool = True,
-            markdown: bool = False,
             exit_on: Optional[List[str]] = None,
             **kwargs: Any,
     ) -> None:
@@ -1342,11 +1340,11 @@ class Assistant(BaseModel):
         _exit_on = exit_on or ["exit", "quit", "bye"]
         logger.debug(f"Enable cli, exit with {_exit_on[0]}")
         if message:
-            self.run(message=message, stream=stream, markdown=markdown, **kwargs)
+            self.run(message=message, stream=stream, **kwargs)
 
         while True:
             message = Prompt.ask(f"[bold] {emoji} {user} [/bold]")
             if message in _exit_on:
                 break
 
-            self.run(message=message, stream=stream, markdown=markdown, **kwargs)
+            self.run(message=message, stream=stream, **kwargs)

{agentica-0.0.6 → agentica-0.1.1}/agentica/emb/azure_emb.py

@@ -6,17 +6,14 @@ part of the code from https://github.com/phidatahq/phidata
 """
 from os import getenv
 from typing import Optional, Dict, List, Tuple, Any
+
+from openai import AzureOpenAI as AzureOpenAIClient
+from openai.types.create_embedding_response import CreateEmbeddingResponse
 from typing_extensions import Literal
 
 from agentica.emb.base import Emb
 from agentica.utils.log import logger
 
-try:
-    from openai import AzureOpenAI as AzureOpenAIClient
-    from openai.types.create_embedding_response import CreateEmbeddingResponse
-except ImportError:
-    raise ImportError("`openai` not installed, please run `pip install openai`")
-
 
 class AzureOpenAIEmb(Emb):
     model: str = "text-embedding-ada-002"
@@ -57,7 +54,8 @@ class AzureOpenAIEmb(Emb):
             _client_params["azure_ad_token"] = self.azure_ad_token
         if self.azure_ad_token_provider:
             _client_params["azure_ad_token_provider"] = self.azure_ad_token_provider
-        return AzureOpenAIClient(**_client_params)
+        self.openai_client = AzureOpenAIClient(**_client_params)
+        return self.openai_client
 
     def _response(self, text: str) -> CreateEmbeddingResponse:
         _request_params: Dict[str, Any] = {
@@ -87,3 +85,9 @@ class AzureOpenAIEmb(Emb):
         embedding = response.data[0].embedding
         usage = response.usage
         return embedding, usage.model_dump()
+
+    def get_embeddings(self, texts: List[str]) -> List[List[float]]:
+        embeddings = []
+        for text in texts:
+            embeddings.append(self.get_embedding(text))
+        return embeddings

{agentica-0.0.6 → agentica-0.1.1}/agentica/emb/base.py

@@ -12,3 +12,6 @@ class Emb(BaseModel):
 
     def get_embedding(self, text: str) -> List[float]:
         raise NotImplementedError
+
+    def get_embeddings(self, texts: List[str]) -> List[List[float]]:
+        raise NotImplementedError

{agentica-0.0.6 → agentica-0.1.1}/agentica/emb/hash_emb.py

@@ -20,3 +20,6 @@ class HashEmb(Emb):
         hash_list = list(hash_object.digest())
         float_list = [float(x) / 255.0 for x in hash_list]
         return float_list
+
+    def get_embeddings(self, texts: List[str]) -> List[List[float]]:
+        return [self.get_embedding(text) for text in texts]

{agentica-0.0.6 → agentica-0.1.1}/agentica/emb/ollama_emb.py

@@ -55,3 +55,6 @@ class OllamaEmb(Emb):
         except Exception as e:
             logger.warning(e)
             return []
+
+    def get_embeddings(self, texts: List[str]) -> List[List[float]]:
+        return [self.get_embedding(text) for text in texts]

{agentica-0.0.6 → agentica-0.1.1}/agentica/emb/openai_emb.py

@@ -7,17 +7,13 @@ part of the code from https://github.com/phidatahq/phidata
 from os import getenv
 from typing import Optional, Dict, List, Tuple, Any
 
+from openai import OpenAI as OpenAIClient
+from openai.types.create_embedding_response import CreateEmbeddingResponse
 from typing_extensions import Literal
 
 from agentica.emb.base import Emb
 from agentica.utils.log import logger
 
-try:
-    from openai import OpenAI as OpenAIClient
-    from openai.types.create_embedding_response import CreateEmbeddingResponse
-except ImportError:
-    raise ImportError("`openai` not installed, please run `pip install openai`")
-
 
 class OpenAIEmb(Emb):
     model: str = "text-embedding-ada-002"  # or text-embedding-3-small
@@ -75,3 +71,6 @@ class OpenAIEmb(Emb):
         embedding = response.data[0].embedding
         usage = response.usage
         return embedding, usage.model_dump()
+
+    def get_embeddings(self, texts: List[str]) -> List[List[float]]:
+        return [self.get_embedding(text) for text in texts]

{agentica-0.0.6 → agentica-0.1.1}/agentica/emb/text2vec_emb.py

@@ -38,3 +38,7 @@ class Text2VecEmb(Emb):
     def get_embedding(self, text: str) -> List[float]:
         # Calculate emb of the text
         return self.get_client.encode([text])[0]
+
+    def get_embeddings(self, texts: List[str]) -> List[List[float]]:
+        # Calculate emb of the texts
+        return self.get_client.encode(texts).tolist()  # type: ignore

{agentica-0.0.6 → agentica-0.1.1}/agentica/emb/word2vec_emb.py

@@ -37,3 +37,9 @@ class Word2VecEmb(Emb):
     def get_embedding(self, text: str) -> List[float]:
         # Calculate emb of the text
         return self.get_client.encode([text])[0]
+
+    def get_embeddings(self, texts: List[str]) -> List[List[float]]:
+        # Calculate emb of the texts
+        ndarr = self.get_client.encode(texts)
+        # convert numpy array to list
+        return ndarr.tolist()  # type: ignore

agentica-0.1.1/agentica/knowledge/__init__.py

@@ -0,0 +1,5 @@
+# -*- coding: utf-8 -*-
+"""
+@author:XuMing(xuming624@qq.com)
+@description: 
+"""