{ "id": 17, "title": { "en": "Text-to-SQL data expert", "de": "Text-to-SQL-Datenexperte", "zh": "Text-to-SQL 问数专家"}, "description": { "en": "Text-to-SQL data expert lets business users turn plain-English questions into fully formed SQL queries. Simply type your question (e.g., 'Show me last quarter's top 10 products by revenue') and Text-to-SQL data expert generates the exact SQL, runs it against your database, and returns the results in seconds. ", "de": "Text-to-SQL-Datenexperte ist ein KI-gestütztes Tool, mit dem Geschäftsanwender einfache englische Fragen in vollständige SQL-Abfragen umwandeln können. Geben Sie einfach Ihre Frage ein (z.B. 'Zeige mir die Top 10 Produkte des letzten Quartals nach Umsatz') und der SQL-Assistent generiert das exakte SQL, führt es gegen Ihre Datenbank aus und liefert die Ergebnisse in Sekunden.", "zh": "用户能够将简单文本问题转化为完整的SQL查询并输出结果。只需输入您的问题（例如，展示上个季度前十名按收入排序的产品），SQL助理就会生成精确的SQL语句，对其运行您的数据库，并几秒钟内返回结果。"}, "canvas_type": "Marketing", "dsl": { "components": { "Agent:WickedGoatsDivide": { "downstream": [ "ExeSQL:TiredShirtsPull" ], "obj": { "component_name": "Agent", "params": { "delay_after_error": 1, "description": "", "exception_default_value": "", "exception_goto": [], "exception_method": "", "frequencyPenaltyEnabled": false, "frequency_penalty": 0.7, "llm_id": "qwen-max@Tongyi-Qianwen", "maxTokensEnabled": false, "max_retries": 3, "max_rounds": 5, "max_tokens": 256, "mcp": [], "message_history_window_size": 12, "outputs": { "content": { "type": "string", "value": "" } }, "presencePenaltyEnabled": false, "presence_penalty": 0.4, "prompts": [ { "content": "User's query: {sys.query}\n\nSchema: {Retrieval:HappyTiesFilm@formalized_content}\n\nSamples about question to SQL: {Retrieval:SmartNewsHammer@formalized_content}\n\nDescription about meanings of tables and files: {Retrieval:SweetDancersAppear@formalized_content}", "role": "user" } ], "sys_prompt": "### ROLE\nYou are a Text-to-SQL assistant. \nGiven a relational database schema and a natural-language request, you must produce a **single, syntactically-correct MySQL query** that answers the request. \nReturn **nothing except the SQL statement itself**\u2014no code fences, no commentary, no explanations, no comments, no trailing semicolon if not required.\n\n\n### EXAMPLES \n-- Example 1 \nUser: List every product name and its unit price. \nSQL:\nSELECT name, unit_price FROM Products;\n\n-- Example 2 \nUser: Show the names and emails of customers who placed orders in January 2025. \nSQL:\nSELECT DISTINCT c.name, c.email\nFROM Customers c\nJOIN Orders o ON o.customer_id = c.id\nWHERE o.order_date BETWEEN '2025-01-01' AND '2025-01-31';\n\n-- Example 3 \nUser: How many orders have a status of \"Completed\" for each month in 2024? \nSQL:\nSELECT DATE_FORMAT(order_date, '%Y-%m') AS month,\n COUNT(*) AS completed_orders\nFROM Orders\nWHERE status = 'Completed'\n AND YEAR(order_date) = 2024\nGROUP BY month\nORDER BY month;\n\n-- Example 4 \nUser: Which products generated at least \\$10 000 in total revenue? \nSQL:\nSELECT p.id, p.name, SUM(oi.quantity * oi.unit_price) AS revenue\nFROM Products p\nJOIN OrderItems oi ON oi.product_id = p.id\nGROUP BY p.id, p.name\nHAVING revenue >= 10000\nORDER BY revenue DESC;\n\n\n### OUTPUT GUIDELINES\n1. Think through the schema and the request. \n2. Write **only** the final MySQL query. \n3. Do **not** wrap the query in back-ticks or markdown fences. \n4. Do **not** add explanations, comments, or additional text\u2014just the SQL.", "temperature": 0.1, "temperatureEnabled": false, "tools": [], "topPEnabled": false, "top_p": 0.3, "user_prompt": "", "visual_files_var": "" } }, "upstream": [ "Retrieval:HappyTiesFilm", "Retrieval:SmartNewsHammer", "Retrieval:SweetDancersAppear" ] }, "ExeSQL:TiredShirtsPull": { "downstream": [ "Message:ShaggyMasksAttend" ], "obj": { "component_name": "ExeSQL", "params": { "database": "", "db_type": "mysql", "host": "", "max_records": 1024, "outputs": { "formalized_content": { "type": "string", "value": "" }, "json": { "type": "Array", "value": [] } }, "password": "", "port": 3306, "sql": "{Agent:WickedGoatsDivide@content}", "username": "" } }, "upstream": [ "Agent:WickedGoatsDivide" ] }, "Message:ShaggyMasksAttend": { "downstream": [], "obj": { "component_name": "Message", "params": { "content": [ "{ExeSQL:TiredShirtsPull@formalized_content}" ] } }, "upstream": [ "ExeSQL:TiredShirtsPull" ] }, "Retrieval:HappyTiesFilm": { "downstream": [ "Agent:WickedGoatsDivide" ], "obj": { "component_name": "Retrieval", "params": { "cross_languages": [], "empty_response": "", "kb_ids": [], "keywords_similarity_weight": 0.7, "outputs": { "formalized_content": { "type": "string", "value": "" } }, "query": "{sys.query}", "rerank_id": "", "similarity_threshold": 0.2, "top_k": 1024, "top_n": 8, "use_kg": false } }, "upstream": [ "begin" ] }, "Retrieval:SmartNewsHammer": { "downstream": [ "Agent:WickedGoatsDivide" ], "obj": { "component_name": "Retrieval", "params": { "cross_languages": [], "empty_response": "", "kb_ids": [], "keywords_similarity_weight": 0.7, "outputs": { "formalized_content": { "type": "string", "value": "" } }, "query": "{sys.query}", "rerank_id": "", "similarity_threshold": 0.2, "top_k": 1024, "top_n": 8, "use_kg": false } }, "upstream": [ "begin" ] }, "Retrieval:SweetDancersAppear": { "downstream": [ "Agent:WickedGoatsDivide" ], "obj": { "component_name": "Retrieval", "params": { "cross_languages": [], "empty_response": "", "kb_ids": [], "keywords_similarity_weight": 0.7, "outputs": { "formalized_content": { "type": "string", "value": "" } }, "query": "{sys.query}", "rerank_id": "", "similarity_threshold": 0.2, "top_k": 1024, "top_n": 8, "use_kg": false } }, "upstream": [ "begin" ] }, "begin": { "downstream": [ "Retrieval:HappyTiesFilm", "Retrieval:SmartNewsHammer", "Retrieval:SweetDancersAppear" ], "obj": { "component_name": "Begin", "params": { "enablePrologue": true, "inputs": {}, "mode": "conversational", "prologue": "Hi! I'm your SQL assistant. What can I do for you?" } }, "upstream": [] } }, "globals": { "sys.conversation_turns": 0, "sys.files": [], "sys.query": "", "sys.user_id": "" }, "graph": { "edges": [ { "data": { "isHovered": false }, "id": "xy-edge__beginstart-Retrieval:HappyTiesFilmend", "source": "begin", "sourceHandle": "start", "target": "Retrieval:HappyTiesFilm", "targetHandle": "end" }, { "id": "xy-edge__beginstart-Retrieval:SmartNewsHammerend", "source": "begin", "sourceHandle": "start", "target": "Retrieval:SmartNewsHammer", "targetHandle": "end" }, { "data": { "isHovered": false }, "id": "xy-edge__beginstart-Retrieval:SweetDancersAppearend", "source": "begin", "sourceHandle": "start", "target": "Retrieval:SweetDancersAppear", "targetHandle": "end" }, { "data": { "isHovered": false }, "id": "xy-edge__Retrieval:HappyTiesFilmstart-Agent:WickedGoatsDivideend", "source": "Retrieval:HappyTiesFilm", "sourceHandle": "start", "target": "Agent:WickedGoatsDivide", "targetHandle": "end" }, { "data": { "isHovered": false }, "id": "xy-edge__Retrieval:SmartNewsHammerstart-Agent:WickedGoatsDivideend", "markerEnd": "logo", "source": "Retrieval:SmartNewsHammer", "sourceHandle": "start", "style": { "stroke": "rgba(91, 93, 106, 1)", "strokeWidth": 1 }, "target": "Agent:WickedGoatsDivide", "targetHandle": "end", "type": "buttonEdge", "zIndex": 1001 }, { "data": { "isHovered": false }, "id": "xy-edge__Retrieval:SweetDancersAppearstart-Agent:WickedGoatsDivideend", "markerEnd": "logo", "source": "Retrieval:SweetDancersAppear", "sourceHandle": "start", "style": { "stroke": "rgba(91, 93, 106, 1)", "strokeWidth": 1 }, "target": "Agent:WickedGoatsDivide", "targetHandle": "end", "type": "buttonEdge", "zIndex": 1001 }, { "data": { "isHovered": false }, "id": "xy-edge__Agent:WickedGoatsDividestart-ExeSQL:TiredShirtsPullend", "source": "Agent:WickedGoatsDivide", "sourceHandle": "start", "target": "ExeSQL:TiredShirtsPull", "targetHandle": "end" }, { "data": { "isHovered": false }, "id": "xy-edge__ExeSQL:TiredShirtsPullstart-Message:ShaggyMasksAttendend", "source": "ExeSQL:TiredShirtsPull", "sourceHandle": "start", "target": "Message:ShaggyMasksAttend", "targetHandle": "end" } ], "nodes": [ { "data": { "form": { "enablePrologue": true, "inputs": {}, "mode": "conversational", "prologue": "Hi! I'm your SQL assistant. What can I do for you?" }, "label": "Begin", "name": "begin" }, "id": "begin", "measured": { "height": 48, "width": 200 }, "position": { "x": 50, "y": 200 }, "selected": false, "sourcePosition": "left", "targetPosition": "right", "type": "beginNode" }, { "data": { "form": { "cross_languages": [], "empty_response": "", "kb_ids": [], "keywords_similarity_weight": 0.7, "outputs": { "formalized_content": { "type": "string", "value": "" } }, "query": "{sys.query}", "rerank_id": "", "similarity_threshold": 0.2, "top_k": 1024, "top_n": 8, "use_kg": false }, "label": "Retrieval", "name": "Schema" }, "dragging": false, "id": "Retrieval:HappyTiesFilm", "measured": { "height": 96, "width": 200 }, "position": { "x": 414, "y": 20.5 }, "selected": false, "sourcePosition": "right", "targetPosition": "left", "type": "retrievalNode" }, { "data": { "form": { "cross_languages": [], "empty_response": "", "kb_ids": [], "keywords_similarity_weight": 0.7, "outputs": { "formalized_content": { "type": "string", "value": "" } }, "query": "{sys.query}", "rerank_id": "", "similarity_threshold": 0.2, "top_k": 1024, "top_n": 8, "use_kg": false }, "label": "Retrieval", "name": "Question to SQL" }, "dragging": false, "id": "Retrieval:SmartNewsHammer", "measured": { "height": 96, "width": 200 }, "position": { "x": 406.5, "y": 175.5 }, "selected": false, "sourcePosition": "right", "targetPosition": "left", "type": "retrievalNode" }, { "data": { "form": { "cross_languages": [], "empty_response": "", "kb_ids": [], "keywords_similarity_weight": 0.7, "outputs": { "formalized_content": { "type": "string", "value": "" } }, "query": "{sys.query}", "rerank_id": "", "similarity_threshold": 0.2, "top_k": 1024, "top_n": 8, "use_kg": false }, "label": "Retrieval", "name": "Database Description" }, "dragging": false, "id": "Retrieval:SweetDancersAppear", "measured": { "height": 96, "width": 200 }, "position": { "x": 403.5, "y": 328 }, "selected": false, "sourcePosition": "right", "targetPosition": "left", "type": "retrievalNode" }, { "data": { "form": { "delay_after_error": 1, "description": "", "exception_default_value": "", "exception_goto": [], "exception_method": "", "frequencyPenaltyEnabled": false, "frequency_penalty": 0.7, "llm_id": "qwen-max@Tongyi-Qianwen", "maxTokensEnabled": false, "max_retries": 3, "max_rounds": 5, "max_tokens": 256, "mcp": [], "message_history_window_size": 12, "outputs": { "content": { "type": "string", "value": "" } }, "presencePenaltyEnabled": false, "presence_penalty": 0.4, "prompts": [ { "content": "User's query: {sys.query}\n\nSchema: {Retrieval:HappyTiesFilm@formalized_content}\n\nSamples about question to SQL: {Retrieval:SmartNewsHammer@formalized_content}\n\nDescription about meanings of tables and files: {Retrieval:SweetDancersAppear@formalized_content}", "role": "user" } ], "sys_prompt": "### ROLE\nYou are a Text-to-SQL assistant. \nGiven a relational database schema and a natural-language request, you must produce a **single, syntactically-correct MySQL query** that answers the request. \nReturn **nothing except the SQL statement itself**\u2014no code fences, no commentary, no explanations, no comments, no trailing semicolon if not required.\n\n\n### EXAMPLES \n-- Example 1 \nUser: List every product name and its unit price. \nSQL:\nSELECT name, unit_price FROM Products;\n\n-- Example 2 \nUser: Show the names and emails of customers who placed orders in January 2025. \nSQL:\nSELECT DISTINCT c.name, c.email\nFROM Customers c\nJOIN Orders o ON o.customer_id = c.id\nWHERE o.order_date BETWEEN '2025-01-01' AND '2025-01-31';\n\n-- Example 3 \nUser: How many orders have a status of \"Completed\" for each month in 2024? \nSQL:\nSELECT DATE_FORMAT(order_date, '%Y-%m') AS month,\n COUNT(*) AS completed_orders\nFROM Orders\nWHERE status = 'Completed'\n AND YEAR(order_date) = 2024\nGROUP BY month\nORDER BY month;\n\n-- Example 4 \nUser: Which products generated at least \\$10 000 in total revenue? \nSQL:\nSELECT p.id, p.name, SUM(oi.quantity * oi.unit_price) AS revenue\nFROM Products p\nJOIN OrderItems oi ON oi.product_id = p.id\nGROUP BY p.id, p.name\nHAVING revenue >= 10000\nORDER BY revenue DESC;\n\n\n### OUTPUT GUIDELINES\n1. Think through the schema and the request. \n2. Write **only** the final MySQL query. \n3. Do **not** wrap the query in back-ticks or markdown fences. \n4. Do **not** add explanations, comments, or additional text\u2014just the SQL.", "temperature": 0.1, "temperatureEnabled": false, "tools": [], "topPEnabled": false, "top_p": 0.3, "user_prompt": "", "visual_files_var": "" }, "label": "Agent", "name": "SQL Generator " }, "dragging": false, "id": "Agent:WickedGoatsDivide", "measured": { "height": 84, "width": 200 }, "position": { "x": 981, "y": 174 }, "selected": false, "sourcePosition": "right", "targetPosition": "left", "type": "agentNode" }, { "data": { "form": { "database": "", "db_type": "mysql", "host": "", "max_records": 1024, "outputs": { "formalized_content": { "type": "string", "value": "" }, "json": { "type": "Array", "value": [] } }, "password": "", "port": 3306, "sql": "{Agent:WickedGoatsDivide@content}", "username": "" }, "label": "ExeSQL", "name": "ExeSQL" }, "dragging": false, "id": "ExeSQL:TiredShirtsPull", "measured": { "height": 56, "width": 200 }, "position": { "x": 1211.5, "y": 212.5 }, "selected": false, "sourcePosition": "right", "targetPosition": "left", "type": "ragNode" }, { "data": { "form": { "content": [ "{ExeSQL:TiredShirtsPull@formalized_content}" ] }, "label": "Message", "name": "Message" }, "dragging": false, "id": "Message:ShaggyMasksAttend", "measured": { "height": 56, "width": 200 }, "position": { "x": 1447.3125, "y": 181.5 }, "selected": false, "sourcePosition": "right", "targetPosition": "left", "type": "messageNode" }, { "data": { "form": { "text": "Searches for relevant database creation statements.\n\nIt should label with a dataset to which the schema is dumped in. You could use \" General \" as parsing method, \" 2 \" as chunk size and \" ; \" as delimiter." }, "label": "Note", "name": "Note Schema" }, "dragHandle": ".note-drag-handle", "dragging": false, "height": 188, "id": "Note:ThickClubsFloat", "measured": { "height": 188, "width": 392 }, "position": { "x": 689, "y": -180.31251144409183 }, "resizing": false, "selected": false, "sourcePosition": "right", "targetPosition": "left", "type": "noteNode", "width": 392 }, { "data": { "form": { "text": "Searches for samples about question to SQL. \n\nYou could use \" Q&A \" as parsing method.\n\nPlease check this dataset:\nhttps://huggingface.co/datasets/InfiniFlow/text2sql" }, "label": "Note", "name": "Note: Question to SQL" }, "dragHandle": ".note-drag-handle", "dragging": false, "height": 154, "id": "Note:ElevenLionsJoke", "measured": { "height": 154, "width": 345 }, "position": { "x": 693.5, "y": 138 }, "resizing": false, "selected": false, "sourcePosition": "right", "targetPosition": "left", "type": "noteNode", "width": 345 }, { "data": { "form": { "text": "Searches for description about meanings of tables and fields.\n\nYou could use \" General \" as parsing method, \" 2 \" as chunk size and \" ### \" as delimiter." }, "label": "Note", "name": "Note: Database Description" }, "dragHandle": ".note-drag-handle", "dragging": false, "height": 158, "id": "Note:ManyRosesTrade", "measured": { "height": 158, "width": 408 }, "position": { "x": 691.5, "y": 435.69736389555317 }, "resizing": false, "selected": false, "sourcePosition": "right", "targetPosition": "left", "type": "noteNode", "width": 408 }, { "data": { "form": { "text": "The Agent learns which tables may be available based on the responses from three knowledge bases and converts the user's input into SQL statements." }, "label": "Note", "name": "Note: SQL Generator" }, "dragHandle": ".note-drag-handle", "dragging": false, "height": 132, "id": "Note:RudeHousesInvite", "measured": { "height": 132, "width": 383 }, "position": { "x": 1106.9254833678003, "y": 290.5891036507015 }, "resizing": false, "selected": false, "sourcePosition": "right", "targetPosition": "left", "type": "noteNode", "width": 383 }, { "data": { "form": { "text": "Connect to your database to execute SQL statements." }, "label": "Note", "name": "Note: SQL Executor" }, "dragHandle": ".note-drag-handle", "dragging": false, "id": "Note:HungryBatsLay", "measured": { "height": 136, "width": 255 }, "position": { "x": 1185, "y": -30 }, "selected": false, "sourcePosition": "right", "targetPosition": "left", "type": "noteNode" } ] }, "history": [], "messages": [], "path": [], "retrieval": [] }, "avatar": "data:image/jpeg;base64,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" }