https://help.smartchart.cn/en/docs/7.AIApplications/ Recent content on Smartchart开发手册 Hugo -- gohugo.io https://help.smartchart.cn/en/docs/7.AIApplications/AISmartDev/ Mon, 01 Jan 0001 00:00:00 +0000 https://help.smartchart.cn/en/docs/7.AIApplications/AISmartDev/ Introduction # SmartChart deeply integrates AI into all major development interfaces: dataset development, chart configuration, and template development. You can describe requirements in natural language, and AI directly generates SQL, ECharts configurations, or HTML code, greatly improving development efficiency. Use Cases # Generate SQL queries with natural language Generate ECharts chart configurations from descriptions Intelligent Q&A style data analysis Prerequisites # AI development features depend on a model data source named smtgpt. https://help.smartchart.cn/en/docs/7.AIApplications/AgentDev/ Mon, 01 Jan 0001 00:00:00 +0000 https://help.smartchart.cn/en/docs/7.AIApplications/AgentDev/ Introduction # SmartChart Agents are built on large models + tool calling mechanisms. Agents identify user intent and automatically decide which tool to invoke (SQL queries, data writes, other agents, etc.), enabling complex conversational business processes like work reporting, data entry, and approvals. Use Cases # Agent applications Agent Core Mechanism # SmartChart agents implement tool routing via the following conventions: Return Format Meaning {"tool":"local","sql":"..."} Execute local SQL query {"tool":"agent_name","msg":". https://help.smartchart.cn/en/docs/7.AIApplications/AgentOrchestration/ Mon, 01 Jan 0001 00:00:00 +0000 https://help.smartchart.cn/en/docs/7.AIApplications/AgentOrchestration/ Introduction # Agent orchestration is SmartChart’s capability for handling multi-step, multi-tool collaboration in complex AI scenarios. Through Python datasets, you can chain multiple agents, LLM calls, database queries, and data writes like writing a script, implementing complete AI business processes. Use Cases # Connecting LLM + data + charts + forms + reach Complex logic flows needed Invoice review example Key Functions # Available in Python datasets: Data Read Functions # # Get dataset via connection name and SQL ds_sql(conn_name, sql) # Read any file or webpage ds_read(file_or_url, encoding="utf-8", clean=True, max_length=None, as_base64=False, selector='') # When selector is not empty (e. https://help.smartchart.cn/en/docs/7.AIApplications/VectorDatabase/ Mon, 01 Jan 0001 00:00:00 +0000 https://help.smartchart.cn/en/docs/7.AIApplications/VectorDatabase/ Introduction # SmartChart supports vector database integration, converting text to vectors and storing them for semantic knowledge retrieval (RAG). This is the core technology for building enterprise private knowledge bases and intelligent Q&A bots. SmartChart supports PostgreSQL + pgvector, and also StarRocks vectorization (enterprise). Once configured, semantic queries in Python datasets find the most relevant knowledge fragments, then pass them to LLM for accurate answers. Use Cases # Knowledge management Vector Database Installation # Example: Installing PostgreSQL on Linux