"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.",
"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.",
"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.",
"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."
"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."
