Merge pull request #675 from Dlouxgit/main

fix(docs): correct FastGPT image paths in chapter 5 docs

docs/chapter5/Chapter5-Building-Agents-with-Low-Code-Platforms.md

@@ -709,49 +709,49 @@ FastGPT is an open-source, LLM-based knowledge base Q&A platform and Agent build
 When you visit the FastGPT official website, the first thing you see is its concise and powerful product manifesto — "Enterprise-grade AI Productivity Engine," emphasizing the construction of secure, controllable enterprise-grade AI Agents, as shown in Figure 5.38.
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-01.png" alt="Image description" width="90%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-01.png" alt="Image description" width="90%"/>
   <p>Figure 5.38 FastGPT Official Website Homepage</p>
 </div>
 
 After logging into the platform, you can see its clear workspace layout. The left navigation bar divides core functions into four modules: Dialog Portal, Workspace, Knowledge Base, and Account. Among them, the Agent module is further divided into three types: Workflow, Dialog Agent, and Dialog Agent V2 (Beta), making it convenient for users to choose the appropriate construction mode based on their business scenarios. The main area provides a quick entry point for "Create from Template," with built-in official templates such as Sales Training Master, Document Translation Assistant, and Industry Trend Insight Briefing; below is the user's own Agent list, as shown in Figure 5.39.
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-02.png" alt="Image description" width="90%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-02.png" alt="Image description" width="90%"/>
   <p>Figure 5.39 FastGPT Platform Main Interface</p>
 </div>
 
 In terms of account and plan options, FastGPT provides a free version for individual developers to try. The free version includes 100 credits, 600 knowledge base indexes, 1 team member, 10 Agents, 3 knowledge bases, 30-day conversation record retention, 30 QPM call rate, and the ability to upload 5 files of 50MB each at a time, as shown in Figure 5.40. For small and medium-sized enterprises and teams, the platform also provides paid upgrade plans to meet higher concurrency and storage needs.
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-03.png" alt="Image description" width="90%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-03.png" alt="Image description" width="90%"/>
   <p>Figure 5.40 FastGPT Free Plan and Usage</p>
 </div>
 
 FastGPT's core competitiveness lies in its powerful knowledge base capabilities. The platform supports importing multiple file formats, including common document types such as Word, Markdown, and PDF. As shown in Figure 5.41, in the "test General Knowledge Base," we can upload multiple files such as Introduction to Deep Learning, Getting Started with Machine Learning, and Bidding Document Text. The system automatically chunks and indexes the files, and once the status shows "Ready," they can be retrieved and referenced in conversations.
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-12.png" alt="Image description" width="90%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-12.png" alt="Image description" width="90%"/>
   <p>Figure 5.41 FastGPT Knowledge Base File Management</p>
 </div>
 
 At the file processing level, FastGPT provides fine-grained parameter configuration. As shown in Figure 5.42, users can choose between "Chunk Storage" or "Q&A Pair Extraction" processing methods, set chunking conditions (such as triggering chunking when original text length exceeds 1000 characters), and enable various index enhancement options, including adding titles to indexes, automatically generating supplementary indexes, and automatic image indexing. For documents with extensive mixed text and image content (such as textbooks and research reports), the automatic image indexing feature is particularly important, as it allows the large model to understand and reference visual information in documents when answering.
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-14.png" alt="Image description" width="90%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-14.png" alt="Image description" width="90%"/>
   <p>Figure 5.42 Knowledge Base Data Processing Parameter Settings</p>
 </div>
 
 After uploading, users can view the specific content of file chunks. As shown in Figure 5.43, taking "English Grade 4 Lower Semester Full Electronic Book.pdf" as an example, the platform displays the text preview of each chunk, while the right metadata panel shows key information such as file size (62MB), original text length (37,797 characters), processing mode (chunk storage), and image indexing status. This transparent chunk display facilitates developers in debugging and optimizing the knowledge base.
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-13.png" alt="Image description" width="90%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-13.png" alt="Image description" width="90%"/>
   <p>Figure 5.43 Knowledge Base File Chunk Details and Metadata</p>
 </div>
 
 In addition to the knowledge base, FastGPT also keeps up with ecosystem trends in tool integration. The platform natively supports MCP (Model Context Protocol) tools, and users can uniformly manage various MCP services in the "My Tools" module. As shown in Figure 5.44, under the "ai Finance" folder, we have configured multiple MCP tools including Chinese Trend Aggregation, Real-time Stock MCP, QieMan Fund MCP, Minimax-MCP, and BI Chart Tool. These tools will empower the agent with the ability to call external real-time data and professional services.
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-04.png" alt="Image description" width="90%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-04.png" alt="Image description" width="90%"/>
   <p>Figure 5.44 FastGPT MCP Tool Management</p>
 </div>
 
@@ -771,14 +771,14 @@ This case requires the following two types of MCP services:
 As shown in Figure 5.45, we can find the "Visual Chart MCP Server" in the MCP marketplace of the ModelScope community. This service is developed based on TypeScript, compatible with the MCP protocol, and provides capabilities for generating area charts, bar charts, pie charts, and various other charts, transforming dry data into intuitive visual results.
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-05.png" alt="Image description" width="90%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-05.png" alt="Image description" width="90%"/>
   <p>Figure 5.45 ModelScope Community Visual Chart MCP Server</p>
 </div>
 
 Additionally, as shown in Figure 5.46, the Alibaba Cloud Bailian platform also provides rich official MCP services. In the MCP management page, we can find financial MCP services such as "Today's Investment - Financial..." and "QieMan," as well as tools like real-time stock quote query and Wanxiang - Video Generation. After adding these services to FastGPT's MCP tool library, the agent can call them on demand during conversations.
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-06.png" alt="Image description" width="90%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-06.png" alt="Image description" width="90%"/>
   <p>Figure 5.46 Alibaba Cloud Bailian MCP Management</p>
 </div>
 
@@ -791,7 +791,7 @@ After completing tool configuration, enter the core workflow orchestration phase
 As shown in Figure 5.47, the complete workflow of the "Smart Investment Advisor Assistant" includes multiple processing branches: user intent recognition, knowledge base retrieval, risk questionnaire collection, MCP tool invocation, and report generation. The entire workflow presents a clear modular structure with data flowing orderly between different nodes. This visual orchestration approach allows developers to intuitively understand and debug the agent's decision paths.
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-07.png" alt="Image description" width="90%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-07.png" alt="Image description" width="90%"/>
   <p>Figure 5.47 Smart Investment Advisor Assistant Workflow Orchestration</p>
 </div>
 
@@ -840,7 +840,7 @@ At the same time, we need to configure a financial knowledge base for the assist
 After completing the workflow and prompt configuration, we can test in FastGPT's dialogue interface. As shown in Figure 5.48, the smart investment advisor assistant's opening message clearly introduces its three main features: mastery of financial investment theory, real-time market news and data, and asset allocation recommendations based on risk profile assessment. The interface also provides quick action buttons for users to trigger common tasks with one click.
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-08.png" alt="Image description" width="50%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-08.png" alt="Image description" width="50%"/>
   <p>Figure 5.48 Smart Investment Advisor Assistant Dialogue Interface</p>
 </div>
 
@@ -854,21 +854,21 @@ As shown in Figure 5.49, the report contains the following core modules:
 - **Rebalancing Strategy**: Provides recommendations for periodic portfolio rebalancing, including rebalancing cycle and trigger conditions.
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-09.png" alt="Image description" width="90%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-09.png" alt="Image description" width="90%"/>
   <p>Figure 5.49 Investment Strategy Analysis Report</p>
 </div>
 
 For real-time data query scenarios, as shown in Figure 5.50, when the user asks "Query the current stock price information of Kweichow Moutai," the agent automatically calls the MCP tool (`get_stock_quote_realtime`) to obtain real-time market data. The returned results include title, data source, key highlights (opening price, highest price, intraday price range, trading volume, total market capitalization, circulating market capitalization, etc.), as well as potential impact analysis and suggested actions. This structured, professional output reflects the practical value of Agent tool invocation capabilities.
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-10.png" alt="Image description" width="50%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-10.png" alt="Image description" width="50%"/>
   <p>Figure 5.50 Real-time Stock Quote Query</p>
 </div>
 
 In terms of concept explanation, as shown in Figure 5.51, when the user asks "What's the difference between P/E ratio and P/B ratio," the assistant provides a systematic comparative analysis based on knowledge base and large model understanding: starting from definitions, it explains the calculation methods of P/E Ratio and P/B Ratio in detail; compares them from four dimensions (calculation basis, applicable industries, information reflected, limitations); and finally provides practical application advice on when to focus on P/E ratio versus P/B ratio. This well-structured, logically rigorous output is a typical advantage of RAG-enhanced large models in vertical domain Q&A.
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-11.png" alt="Image description" width="50%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-11.png" alt="Image description" width="50%"/>
   <p>Figure 5.51 P/E Ratio and P/B Ratio Concept Analysis</p>
 </div>
 

docs/chapter5/第五章 基于低代码平台的智能体搭建.md

@@ -712,49 +712,49 @@ FastGPT 是一个开源的、基于大语言模型的知识库问答平台与 Ag
 进入 FastGPT 官网，首先映入眼帘的是其简洁有力的产品宣言——"企业级 AI 生产力引擎"，强调构建安全、可控的企业级 AI Agent，如图5.38所示。
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-01.png" alt="图片描述" width="90%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-01.png" alt="图片描述" width="90%"/>
   <p>图 5.38 FastGPT 官网首页</p>
 </div>
 
 登录平台后，可以看到其清晰的工作台布局。左侧导航栏将核心功能划分为 对话门户、工作台、知识库和账号四大模块。其中 Agent 模块又细分为工作流、对话 Agent 和对话 Agent V2(Beta) 三种类型，方便用户根据业务场景选择合适的构建模式。主区域则提供了"从模板新建"的快捷入口，内置了销售陪练大师、文档翻译助手、行业趋势洞察简报等官方模板；下方是用户自己创建的 Agent 列表，如图5.39所示。
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-02.png" alt="图片描述" width="90%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-02.png" alt="图片描述" width="90%"/>
   <p>图 5.39 FastGPT 平台主界面</p>
 </div>
 
 在账号与套餐方面，FastGPT 提供了免费版供个人开发者体验。免费版包含 100 积分、600 条知识库索引、1 个团队成员、10 个 Agent、3 个知识库、30 天对话记录保留、30 QPM 的调用速率，以及单次可上传 5 个 50MB 文件的权限，如图5.40所示。对于中小企业和团队，平台也提供了付费升级方案以满足更高的并发和存储需求。
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-03.png" alt="图片描述" width="90%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-03.png" alt="图片描述" width="90%"/>
   <p>图 5.40 FastGPT 免费版套餐与用量</p>
 </div>
 
 FastGPT 最核心的竞争力在于其强大的知识库能力。平台支持多种文件格式的导入，包括 Word、Markdown、PDF 等常见文档类型。如图5.41所示，在"test 通用知识库"中，我们可以上传深度学习简介、机器学习入门、招标文件正文等多个文件，系统会自动对文件进行分块处理并建立索引，状态显示为"已就绪"后即可在对话中被检索引用。
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-12.png" alt="图片描述" width="90%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-12.png" alt="图片描述" width="90%"/>
   <p>图 5.41 FastGPT 知识库文件管理</p>
 </div>
 
 在文件处理层面，FastGPT 提供了精细化的参数配置。如图5.42所示，用户可以选择"分块存储"或"问答对提取"两种处理方式，设置分块条件（如原文长度大于 1000 字符时触发分块），并开启多种索引增强选项，包括将标题加入索引、自动生成补充索引以及图片自动索引等。对于包含大量图文混排内容的文档（如教材、研报），图片自动索引功能尤为重要，它能让大模型在回答时理解并引用文档中的视觉信息。
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-14.png" alt="图片描述" width="90%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-14.png" alt="图片描述" width="90%"/>
   <p>图 5.42 知识库数据处理参数设置</p>
 </div>
 
 上传完成后，用户可以查看文件被分块后的具体内容。如图5.43所示，以"英语四年级下册全册电子书.pdf"为例，平台展示了每个分块的文本预览，同时右侧元数据面板显示了文件大小（62MB）、原文长度（37797 字符）、处理模式（分块存储）、图片索引状态等关键信息。这种透明化的分块展示，方便开发者进行知识库的调试与优化。
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-13.png" alt="图片描述" width="90%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-13.png" alt="图片描述" width="90%"/>
   <p>图 5.43 知识库文件分块详情与元数据</p>
 </div>
 
 除了知识库，FastGPT 在工具集成方面也紧跟生态趋势。平台原生支持 MCP（Model Context Protocol）工具，用户可以在"我的工具"模块中统一管理各类 MCP 服务。如图5.44所示，在"ai 金融"文件夹下，我们已经配置了中文趋势聚合、实时股票 MCP、且慢基金 MCP、Minimax-MCP、BI 画图工具等多个 MCP 工具，这些工具将赋予智能体调用外部实时数据和专业服务的能力。
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-04.png" alt="图片描述" width="90%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-04.png" alt="图片描述" width="90%"/>
   <p>图 5.44 FastGPT MCP 工具管理</p>
 </div>
 
@@ -774,14 +774,14 @@ FastGPT 最核心的竞争力在于其强大的知识库能力。平台支持多
 如图5.45所示，我们可以在魔搭社区（ModelScope）的 MCP 市场中找到"可视化图表 MCP Server"。该服务基于 TypeScript 开发，兼容 MCP 协议，提供了生成面积图、柱状图、饼图等多种图表的能力，能够将枯燥的数据转化为直观的可视化结果。
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-05.png" alt="图片描述" width="90%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-05.png" alt="图片描述" width="90%"/>
   <p>图 5.45 魔搭社区可视化图表 MCP Server</p>
 </div>
 
 另外，如图5.46所示，阿里云百炼平台也提供了丰富的官方 MCP 服务。在 MCP 管理页面中，我们可以找到"今日投资-金融实..."和"且慢"等金融类 MCP 服务，以及股票实时行情查询、万相-视频生成等工具。将这些服务添加到 FastGPT 的 MCP 工具库后，智能体便能在对话中按需调用它们。
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-06.png" alt="图片描述" width="90%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-06.png" alt="图片描述" width="90%"/>
   <p>图 5.46 阿里云百炼 MCP 管理</p>
 </div>
 
@@ -794,7 +794,7 @@ FastGPT 最核心的竞争力在于其强大的知识库能力。平台支持多
 如图5.47所示，"智能投顾助手"的完整工作流包含了多个处理分支：用户意图识别、知识库检索、风险问卷收集、MCP 工具调用、报告生成等。整个工作流呈现出清晰的模块化结构，数据在不同节点间有序流转。这种可视化的编排方式，让开发者能够直观地理解和调试智能体的决策路径。
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-07.png" alt="图片描述" width="90%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-07.png" alt="图片描述" width="90%"/>
   <p>图 5.47 智能投顾助手工作流编排</p>
 </div>
 
@@ -843,7 +843,7 @@ FastGPT 最核心的竞争力在于其强大的知识库能力。平台支持多
 完成工作流和提示词配置后，我们可以在 FastGPT 的对话界面中进行测试。如图5.48所示，智能投顾助手的开场白清晰地介绍了自身的三大功能特色：精通金融投资理论、提供实时市场新闻及数据、根据风险画像评估提供资产配置建议。界面下方还提供了快捷操作按钮，方便用户一键触发常见任务。
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-08.png" alt="图片描述" width="50%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-08.png" alt="图片描述" width="50%"/>
   <p>图 5.48 智能投顾助手对话界面</p>
 </div>
 
@@ -857,21 +857,21 @@ FastGPT 最核心的竞争力在于其强大的知识库能力。平台支持多
 - **再平衡策略**：提供定期调仓的建议方案，包括调仓周期和触发条件。
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-09.png" alt="图片描述" width="90%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-09.png" alt="图片描述" width="90%"/>
   <p>图 5.49 投资策略分析报告</p>
 </div>
 
 对于实时数据查询场景，如图5.50所示，当用户询问"查询现在贵州茅台的股价信息"时，智能体会自动调用 MCP 工具（`get_stock_quote_realtime`）获取实时行情数据。返回结果包含标题、数据来源、关键要点（开盘价、最高价、日内价格区间、成交量、总市值、流通市值等），以及潜在影响分析和建议行动。这种结构化、专业化的输出，体现了 Agent 工具调用能力的实际价值。
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-10.png" alt="图片描述" width="50%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-10.png" alt="图片描述" width="50%"/>
   <p>图 5.50 实时股票行情查询</p>
 </div>
 
 在概念解释方面，如图5.51所示，当用户询问"市盈率和市净率有什么区别"时，助手基于知识库和大模型的理解，给出了系统性的对比分析：从定义出发，详细解释了市盈率（P/E Ratio）和市净率（P/B Ratio）的计算方式；从四个维度（计算基础、适用行业、反映信息、局限性）进行对比；最后给出实际应用建议，说明何时应重点关注市盈率、何时应关注市净率。这种层次分明、逻辑严谨的输出，正是 RAG 增强后的大模型在垂直领域问答中的典型优势。
 
 <div align="center">
-  <img src="../images/5-figures/fastgpt-11.png" alt="图片描述" width="50%"/>
+  <img src="https://raw.githubusercontent.com/datawhalechina/Hello-Agents/main/docs/images/5-figures/fastgpt-11.png" alt="图片描述" width="50%"/>
   <p>图 5.51 市盈率与市净率概念解析</p>
 </div>