https://help.smartchart.cn/en/docs/7.AIApplications/Agent/ Recent content in Agent Development Guide on Smartchart开发手册 Hugo -- gohugo.io https://help.smartchart.cn/en/docs/7.AIApplications/Agent/Bot/ Mon, 01 Jan 0001 00:00:00 +0000 https://help.smartchart.cn/en/docs/7.AIApplications/Agent/Bot/ Use Cases # Connect to DingTalk, WeCom, etc., work like openClaw but with self-control Introduction # SmartChart supports connecting agents to DingTalk, WeCom and other enterprise IM platforms as group bots providing intelligent services. When the bot receives messages, it calls SmartChart’s Python agent dataset logic, supporting tool calling (file viewing, data inquiry, record writing, etc.), using ds_tool() for multi-agent collaboration. Usage # Create dataset, type: Agent, connector: Python, name “sCraw” prompt = """$prompt""" system="""You are a professional digital assistant. https://help.smartchart.cn/en/docs/7.AIApplications/Agent/DocGeneration/ Mon, 01 Jan 0001 00:00:00 +0000 https://help.smartchart.cn/en/docs/7.AIApplications/Agent/DocGeneration/ Introduction # The document generation agent uses multi-step streaming processing to automatically generate complete Word documents (.docx) from natural language requirements. Core flow: 1) Use LLM to extract requirements and chapter structure -> 2) Generate content chapter by chapter via LLM -> 3) Save as Word document using ds_save_doc(). Supports streaming progress feedback. Use Cases # Operation documents, proposals, tender documents generation Usage # LLM connections are abstracted as data sources, see Basics -> First AI Scene https://help.smartchart.cn/en/docs/7.AIApplications/Agent/SmartQA/ Mon, 01 Jan 0001 00:00:00 +0000 https://help.smartchart.cn/en/docs/7.AIApplications/Agent/SmartQA/ Introduction # Smart Q&A is SmartChart’s Text-to-SQL implementation. Users ask questions in natural language, the system first uses a routing agent to determine which business table the question belongs to, then the askdata skill dataset auto-generates SQL and queries the database, finally presenting results visually. The entire flow is implemented through two datasets (routing agent + Q&A skill) without additional programming frameworks. Use Cases # Enter knowledge and data Q&A from homepage Usage # LLM connections are abstracted as data sources, see Basics -> First AI Scene https://help.smartchart.cn/en/docs/7.AIApplications/Agent/SmartTicket/ Mon, 01 Jan 0001 00:00:00 +0000 https://help.smartchart.cn/en/docs/7.AIApplications/Agent/SmartTicket/ Introduction # Smart ticket submission demonstrates the complete chain of “LLM + chart tool calling” in SmartChart: user uploads invoice image -> LLM recognizes and reviews content -> triggers tool call ({"tool":"VV_ReimbursementForm",...}) -> chart dataset renders reimbursement form. Datasets named with VV prefix are “Visualization Variant” datasets, specifically for rendering visual results - a SmartChart agent tool calling convention. Use Cases # Connecting LLM + data + charts + forms + reach Invoice review example Usage # Create LLM data source, using dashAI to call Alibaba DashScope dashAI supports qwen model, auto-switches to vl model for image uploads (default qwen-vl, changeable via {“vmodel”:“qwen-vl-max”}) https://help.smartchart.cn/en/docs/7.AIApplications/Agent/WebPageGeneration/ Mon, 01 Jan 0001 00:00:00 +0000 https://help.smartchart.cn/en/docs/7.AIApplications/Agent/WebPageGeneration/ Introduction # The web page generation agent provides SmartChart’s standard HTML template format to LLM, letting it directly generate visualization page code that runs in SmartChart. Ideal for rapid prototyping and users without frontend background. Generated code can be pasted directly into dashboard templates. Use Cases # SmartChart dashboard and web page development Usage # LLM connections are abstracted as data sources, see Basics -> First AI Scene Create dataset, type: Agent, connector: LLM data source, name “Web Page Generation” You can generate HTML based on the template format, filling CSS, HTML, JS in corresponding template areas.