| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"simple_function\",\n \"description\": \"Simple function with one parameter\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"text\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"text\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nCall with hello world<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"simple_function\", \"arguments\": {\"text\": \"hello world\"}}", "rejected": "I'll call the function with hello world"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"two_param_function\",\n \"description\": \"Function with two parameters\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"name\": {\n \"type\": \"string\"\n },\n \"age\": {\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"name\",\n \"age\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nCall with name John and age 25<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"two_param_function\", \"arguments\": {\"name\": \"John\", \"age\": 25}}", "rejected": "{\"name\": \"two_param_function\", \"arguments\": {\"name\": \"John\" \"age\": 25}}"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"analyze_text\",\n \"description\": \"Analyze text content\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"content\": {\n \"type\": \"string\"\n },\n \"type\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"content\",\n \"type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze this text: The CEO said we have made tremendous progress this quarter<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_text\", \"arguments\": {\"content\": \"The CEO said we have made tremendous progress this quarter\", \"type\": \"analysis\"}}", "rejected": "I will analyze that text for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"send_message\",\n \"description\": \"Send a message\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"to\": {\n \"type\": \"string\"\n },\n \"subject\": {\n \"type\": \"string\"\n },\n \"body\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"to\",\n \"subject\",\n \"body\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSend email to john@company.com with subject Meeting Update and body The meeting has been rescheduled to tomorrow at 2 PM<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"send_message\", \"arguments\": {\"to\": \"john@company.com\", \"subject\": \"Meeting Update\", \"body\": \"The meeting has been rescheduled to tomorrow at 2 PM\"}}", "rejected": "I will send that email for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"process_query\",\n \"description\": \"Process database query\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"query\": {\n \"type\": \"string\"\n },\n \"database\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"query\",\n \"database\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nRun query SELECT name FROM users WHERE created_at > 2023-01-01 on the main database<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"process_query\", \"arguments\": {\"query\": \"SELECT name FROM users WHERE created_at > 2023-01-01\", \"database\": \"main\"}}", "rejected": "I will run that database query for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"configure_system\",\n \"description\": \"Configure system settings\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"timeout\": {\n \"type\": \"integer\"\n },\n \"enabled\": {\n \"type\": \"boolean\"\n },\n \"level\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"timeout\",\n \"enabled\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSet timeout to 30 seconds, enable the system, and set level to debug<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"configure_system\", \"arguments\": {\"timeout\": 30, \"enabled\": true, \"level\": \"debug\"}}", "rejected": "I will configure the system with those settings"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"process_files\",\n \"description\": \"Process multiple files\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"files\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"operation\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"files\",\n \"operation\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nProcess files data.csv, results.json, and report.pdf with merge operation<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"process_files\", \"arguments\": {\"files\": [\"data.csv\", \"results.json\", \"report.pdf\"], \"operation\": \"merge\"}}", "rejected": "I will process those files for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"summarize_document\",\n \"description\": \"Summarize document content\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"document_url\": {\n \"type\": \"string\"\n },\n \"summary_length\": {\n \"type\": \"string\"\n },\n \"target_audience\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"document_url\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSummarize the document at https://example.com/report.pdf for executives with brief length<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"summarize_document\", \"arguments\": {\"document_url\": \"https://example.com/report.pdf\", \"summary_length\": \"brief\", \"target_audience\": \"executive\"}}", "rejected": "I will summarize that document for executives"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"analyze_sentiment\",\n \"description\": \"Analyze text sentiment\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"text\": {\n \"type\": \"string\"\n },\n \"language\": {\n \"type\": \"string\"\n },\n \"include_emotions\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"text\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze sentiment of this text: The product was excellent and delivery was fast with emotion details in English<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_sentiment\", \"arguments\": {\"text\": \"The product was excellent and delivery was fast\", \"language\": \"en\", \"include_emotions\": true}}", "rejected": "I will analyze the sentiment of that text"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"get_weather_forecast\",\n \"description\": \"Get weather forecast\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"location\": {\n \"type\": \"string\"\n },\n \"days\": {\n \"type\": \"integer\"\n },\n \"units\": {\n \"type\": \"string\"\n },\n \"include_hourly\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"location\",\n \"days\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nGet 3-day weather forecast for New York in metric units with hourly details<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"get_weather_forecast\", \"arguments\": {\"location\": \"New York\", \"days\": 3, \"units\": \"metric\", \"include_hourly\": true}}", "rejected": "I will get the weather forecast for New York"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"convert_currency\",\n \"description\": \"Convert currency amounts\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"amount\": {\n \"type\": \"number\"\n },\n \"from_currency\": {\n \"type\": \"string\"\n },\n \"to_currency\": {\n \"type\": \"string\"\n },\n \"include_fees\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"amount\",\n \"from_currency\",\n \"to_currency\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nConvert 100 US dollars to Euros with fees included<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"convert_currency\", \"arguments\": {\"amount\": 100, \"from_currency\": \"USD\", \"to_currency\": \"EUR\", \"include_fees\": true}}", "rejected": "I will convert that currency amount for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"optimize_database_query\",\n \"description\": \"Optimize database query\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"sql_query\": {\n \"type\": \"string\"\n },\n \"database_type\": {\n \"type\": \"string\"\n },\n \"performance_target\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"sql_query\",\n \"database_type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nOptimize this MySQL query for speed: SELECT id, name FROM users WHERE active = 1<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"optimize_database_query\", \"arguments\": {\"sql_query\": \"SELECT id, name FROM users WHERE active = 1\", \"database_type\": \"mysql\", \"performance_target\": \"speed\"}}", "rejected": "I will optimize that database query for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"summarize_document\",\n \"description\": \"Summarize document content\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"document_url\": {\n \"type\": \"string\"\n },\n \"summary_length\": {\n \"type\": \"string\"\n },\n \"target_audience\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"document_url\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSummarize the document at https://example.com/report.pdf for executives with brief length<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"summarize_document\", \"arguments\": {\"document_url\": \"https://example.com/report.pdf\", \"summary_length\": \"brief\", \"target_audience\": \"executive\"}}", "rejected": "I will summarize that document for executives"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"analyze_sentiment\",\n \"description\": \"Analyze text sentiment\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"text\": {\n \"type\": \"string\"\n },\n \"language\": {\n \"type\": \"string\"\n },\n \"include_emotions\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"text\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze sentiment of this text: The product was excellent and delivery was fast with emotion details in English<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_sentiment\", \"arguments\": {\"text\": \"The product was excellent and delivery was fast\", \"language\": \"en\", \"include_emotions\": true}}", "rejected": "I will analyze the sentiment of that text"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"get_weather_forecast\",\n \"description\": \"Get weather forecast\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"location\": {\n \"type\": \"string\"\n },\n \"days\": {\n \"type\": \"integer\"\n },\n \"units\": {\n \"type\": \"string\"\n },\n \"include_hourly\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"location\",\n \"days\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nGet 3-day weather forecast for New York in metric units with hourly details<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"get_weather_forecast\", \"arguments\": {\"location\": \"New York\", \"days\": 3, \"units\": \"metric\", \"include_hourly\": true}}", "rejected": "I will get the weather forecast for New York"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"convert_currency\",\n \"description\": \"Convert currency amounts\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"amount\": {\n \"type\": \"number\"\n },\n \"from_currency\": {\n \"type\": \"string\"\n },\n \"to_currency\": {\n \"type\": \"string\"\n },\n \"include_fees\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"amount\",\n \"from_currency\",\n \"to_currency\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nConvert 100 US dollars to Euros with fees included<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"convert_currency\", \"arguments\": {\"amount\": 100, \"from_currency\": \"USD\", \"to_currency\": \"EUR\", \"include_fees\": true}}", "rejected": "I will convert that currency amount for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"optimize_database_query\",\n \"description\": \"Optimize database query\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"sql_query\": {\n \"type\": \"string\"\n },\n \"database_type\": {\n \"type\": \"string\"\n },\n \"performance_target\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"sql_query\",\n \"database_type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nOptimize this MySQL query for speed: SELECT id, name FROM users WHERE active = 1<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"optimize_database_query\", \"arguments\": {\"sql_query\": \"SELECT id, name FROM users WHERE active = 1\", \"database_type\": \"mysql\", \"performance_target\": \"speed\"}}", "rejected": "I will optimize that database query for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"analyze_text\",\n \"description\": \"Analyze text content\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"content\": {\n \"type\": \"string\"\n },\n \"type\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"content\",\n \"type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze this text: The CEO said we have made tremendous progress this quarter<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_text\", \"arguments\": {\"content\": \"The CEO said we have made tremendous progress this quarter\", \"type\": \"analysis\"}}", "rejected": "I will analyze that text for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"send_message\",\n \"description\": \"Send a message\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"to\": {\n \"type\": \"string\"\n },\n \"subject\": {\n \"type\": \"string\"\n },\n \"body\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"to\",\n \"subject\",\n \"body\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSend email to john@company.com with subject Meeting Update and body The meeting has been rescheduled to tomorrow at 2 PM<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"send_message\", \"arguments\": {\"to\": \"john@company.com\", \"subject\": \"Meeting Update\", \"body\": \"The meeting has been rescheduled to tomorrow at 2 PM\"}}", "rejected": "I will send that email for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"process_query\",\n \"description\": \"Process database query\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"query\": {\n \"type\": \"string\"\n },\n \"database\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"query\",\n \"database\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nRun query SELECT name FROM users WHERE created_at > 2023-01-01 on the main database<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"process_query\", \"arguments\": {\"query\": \"SELECT name FROM users WHERE created_at > 2023-01-01\", \"database\": \"main\"}}", "rejected": "I will run that database query for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"configure_system\",\n \"description\": \"Configure system settings\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"timeout\": {\n \"type\": \"integer\"\n },\n \"enabled\": {\n \"type\": \"boolean\"\n },\n \"level\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"timeout\",\n \"enabled\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSet timeout to 30 seconds, enable the system, and set level to debug<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"configure_system\", \"arguments\": {\"timeout\": 30, \"enabled\": true, \"level\": \"debug\"}}", "rejected": "I will configure the system with those settings"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"process_files\",\n \"description\": \"Process multiple files\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"files\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"operation\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"files\",\n \"operation\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nProcess files data.csv, results.json, and report.pdf with merge operation<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"process_files\", \"arguments\": {\"files\": [\"data.csv\", \"results.json\", \"report.pdf\"], \"operation\": \"merge\"}}", "rejected": "I will process those files for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"summarize_document\",\n \"description\": \"Summarize document content\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"document_url\": {\n \"type\": \"string\"\n },\n \"summary_length\": {\n \"type\": \"string\"\n },\n \"target_audience\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"document_url\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSummarize the document at https://example.com/report.pdf for executives with brief length<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"summarize_document\", \"arguments\": {\"document_url\": \"https://example.com/report.pdf\", \"summary_length\": \"brief\", \"target_audience\": \"executive\"}}", "rejected": "I will summarize that document for executives"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"analyze_sentiment\",\n \"description\": \"Analyze text sentiment\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"text\": {\n \"type\": \"string\"\n },\n \"language\": {\n \"type\": \"string\"\n },\n \"include_emotions\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"text\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze sentiment of this text: The product was excellent and delivery was fast with emotion details in English<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_sentiment\", \"arguments\": {\"text\": \"The product was excellent and delivery was fast\", \"language\": \"en\", \"include_emotions\": true}}", "rejected": "I will analyze the sentiment of that text"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"get_weather_forecast\",\n \"description\": \"Get weather forecast\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"location\": {\n \"type\": \"string\"\n },\n \"days\": {\n \"type\": \"integer\"\n },\n \"units\": {\n \"type\": \"string\"\n },\n \"include_hourly\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"location\",\n \"days\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nGet 3-day weather forecast for New York in metric units with hourly details<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"get_weather_forecast\", \"arguments\": {\"location\": \"New York\", \"days\": 3, \"units\": \"metric\", \"include_hourly\": true}}", "rejected": "I will get the weather forecast for New York"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"convert_currency\",\n \"description\": \"Convert currency amounts\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"amount\": {\n \"type\": \"number\"\n },\n \"from_currency\": {\n \"type\": \"string\"\n },\n \"to_currency\": {\n \"type\": \"string\"\n },\n \"include_fees\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"amount\",\n \"from_currency\",\n \"to_currency\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nConvert 100 US dollars to Euros with fees included<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"convert_currency\", \"arguments\": {\"amount\": 100, \"from_currency\": \"USD\", \"to_currency\": \"EUR\", \"include_fees\": true}}", "rejected": "I will convert that currency amount for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"optimize_database_query\",\n \"description\": \"Optimize database query\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"sql_query\": {\n \"type\": \"string\"\n },\n \"database_type\": {\n \"type\": \"string\"\n },\n \"performance_target\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"sql_query\",\n \"database_type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nOptimize this MySQL query for speed: SELECT id, name FROM users WHERE active = 1<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"optimize_database_query\", \"arguments\": {\"sql_query\": \"SELECT id, name FROM users WHERE active = 1\", \"database_type\": \"mysql\", \"performance_target\": \"speed\"}}", "rejected": "I will optimize that database query for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"analyze_text\",\n \"description\": \"Analyze text content\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"content\": {\n \"type\": \"string\"\n },\n \"type\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"content\",\n \"type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze this text: The CEO said we have made tremendous progress this quarter<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_text\", \"arguments\": {\"content\": \"The CEO said we have made tremendous progress this quarter\", \"type\": \"analysis\"}}", "rejected": "I will analyze that text for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"send_message\",\n \"description\": \"Send a message\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"to\": {\n \"type\": \"string\"\n },\n \"subject\": {\n \"type\": \"string\"\n },\n \"body\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"to\",\n \"subject\",\n \"body\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSend email to john@company.com with subject Meeting Update and body The meeting has been rescheduled to tomorrow at 2 PM<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"send_message\", \"arguments\": {\"to\": \"john@company.com\", \"subject\": \"Meeting Update\", \"body\": \"The meeting has been rescheduled to tomorrow at 2 PM\"}}", "rejected": "I will send that email for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"process_query\",\n \"description\": \"Process database query\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"query\": {\n \"type\": \"string\"\n },\n \"database\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"query\",\n \"database\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nRun query SELECT name FROM users WHERE created_at > 2023-01-01 on the main database<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"process_query\", \"arguments\": {\"query\": \"SELECT name FROM users WHERE created_at > 2023-01-01\", \"database\": \"main\"}}", "rejected": "I will run that database query for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"configure_system\",\n \"description\": \"Configure system settings\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"timeout\": {\n \"type\": \"integer\"\n },\n \"enabled\": {\n \"type\": \"boolean\"\n },\n \"level\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"timeout\",\n \"enabled\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSet timeout to 30 seconds, enable the system, and set level to debug<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"configure_system\", \"arguments\": {\"timeout\": 30, \"enabled\": true, \"level\": \"debug\"}}", "rejected": "I will configure the system with those settings"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"process_files\",\n \"description\": \"Process multiple files\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"files\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"operation\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"files\",\n \"operation\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nProcess files data.csv, results.json, and report.pdf with merge operation<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"process_files\", \"arguments\": {\"files\": [\"data.csv\", \"results.json\", \"report.pdf\"], \"operation\": \"merge\"}}", "rejected": "I will process those files for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"summarize_document\",\n \"description\": \"Summarize document content\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"document_url\": {\n \"type\": \"string\"\n },\n \"summary_length\": {\n \"type\": \"string\"\n },\n \"target_audience\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"document_url\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSummarize the document at https://example.com/report.pdf for executives with brief length<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"summarize_document\", \"arguments\": {\"document_url\": \"https://example.com/report.pdf\", \"summary_length\": \"brief\", \"target_audience\": \"executive\"}}", "rejected": "I will summarize that document for executives"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"analyze_sentiment\",\n \"description\": \"Analyze text sentiment\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"text\": {\n \"type\": \"string\"\n },\n \"language\": {\n \"type\": \"string\"\n },\n \"include_emotions\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"text\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze sentiment of this text: The product was excellent and delivery was fast with emotion details in English<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_sentiment\", \"arguments\": {\"text\": \"The product was excellent and delivery was fast\", \"language\": \"en\", \"include_emotions\": true}}", "rejected": "I will analyze the sentiment of that text"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"get_weather_forecast\",\n \"description\": \"Get weather forecast\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"location\": {\n \"type\": \"string\"\n },\n \"days\": {\n \"type\": \"integer\"\n },\n \"units\": {\n \"type\": \"string\"\n },\n \"include_hourly\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"location\",\n \"days\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nGet 3-day weather forecast for New York in metric units with hourly details<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"get_weather_forecast\", \"arguments\": {\"location\": \"New York\", \"days\": 3, \"units\": \"metric\", \"include_hourly\": true}}", "rejected": "I will get the weather forecast for New York"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"convert_currency\",\n \"description\": \"Convert currency amounts\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"amount\": {\n \"type\": \"number\"\n },\n \"from_currency\": {\n \"type\": \"string\"\n },\n \"to_currency\": {\n \"type\": \"string\"\n },\n \"include_fees\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"amount\",\n \"from_currency\",\n \"to_currency\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nConvert 100 US dollars to Euros with fees included<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"convert_currency\", \"arguments\": {\"amount\": 100, \"from_currency\": \"USD\", \"to_currency\": \"EUR\", \"include_fees\": true}}", "rejected": "I will convert that currency amount for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"optimize_database_query\",\n \"description\": \"Optimize database query\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"sql_query\": {\n \"type\": \"string\"\n },\n \"database_type\": {\n \"type\": \"string\"\n },\n \"performance_target\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"sql_query\",\n \"database_type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nOptimize this MySQL query for speed: SELECT id, name FROM users WHERE active = 1<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"optimize_database_query\", \"arguments\": {\"sql_query\": \"SELECT id, name FROM users WHERE active = 1\", \"database_type\": \"mysql\", \"performance_target\": \"speed\"}}", "rejected": "I will optimize that database query for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"analyze_text\",\n \"description\": \"Analyze text content\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"content\": {\n \"type\": \"string\"\n },\n \"type\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"content\",\n \"type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze this text: The CEO said we have made tremendous progress this quarter<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_text\", \"arguments\": {\"content\": \"The CEO said we have made tremendous progress this quarter\", \"type\": \"analysis\"}}", "rejected": "I will analyze that text for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"send_message\",\n \"description\": \"Send a message\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"to\": {\n \"type\": \"string\"\n },\n \"subject\": {\n \"type\": \"string\"\n },\n \"body\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"to\",\n \"subject\",\n \"body\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSend email to john@company.com with subject Meeting Update and body The meeting has been rescheduled to tomorrow at 2 PM<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"send_message\", \"arguments\": {\"to\": \"john@company.com\", \"subject\": \"Meeting Update\", \"body\": \"The meeting has been rescheduled to tomorrow at 2 PM\"}}", "rejected": "I will send that email for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"process_query\",\n \"description\": \"Process database query\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"query\": {\n \"type\": \"string\"\n },\n \"database\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"query\",\n \"database\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nRun query SELECT name FROM users WHERE created_at > 2023-01-01 on the main database<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"process_query\", \"arguments\": {\"query\": \"SELECT name FROM users WHERE created_at > 2023-01-01\", \"database\": \"main\"}}", "rejected": "I will run that database query for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"configure_system\",\n \"description\": \"Configure system settings\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"timeout\": {\n \"type\": \"integer\"\n },\n \"enabled\": {\n \"type\": \"boolean\"\n },\n \"level\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"timeout\",\n \"enabled\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSet timeout to 30 seconds, enable the system, and set level to debug<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"configure_system\", \"arguments\": {\"timeout\": 30, \"enabled\": true, \"level\": \"debug\"}}", "rejected": "I will configure the system with those settings"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"process_files\",\n \"description\": \"Process multiple files\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"files\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"operation\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"files\",\n \"operation\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nProcess files data.csv, results.json, and report.pdf with merge operation<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"process_files\", \"arguments\": {\"files\": [\"data.csv\", \"results.json\", \"report.pdf\"], \"operation\": \"merge\"}}", "rejected": "I will process those files for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"summarize_document\",\n \"description\": \"Summarize document content\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"document_url\": {\n \"type\": \"string\"\n },\n \"summary_length\": {\n \"type\": \"string\"\n },\n \"target_audience\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"document_url\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSummarize the document at https://example.com/report.pdf for executives with brief length<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"summarize_document\", \"arguments\": {\"document_url\": \"https://example.com/report.pdf\", \"summary_length\": \"brief\", \"target_audience\": \"executive\"}}", "rejected": "I will summarize that document for executives"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"analyze_sentiment\",\n \"description\": \"Analyze text sentiment\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"text\": {\n \"type\": \"string\"\n },\n \"language\": {\n \"type\": \"string\"\n },\n \"include_emotions\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"text\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze sentiment of this text: The product was excellent and delivery was fast with emotion details in English<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_sentiment\", \"arguments\": {\"text\": \"The product was excellent and delivery was fast\", \"language\": \"en\", \"include_emotions\": true}}", "rejected": "I will analyze the sentiment of that text"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"get_weather_forecast\",\n \"description\": \"Get weather forecast\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"location\": {\n \"type\": \"string\"\n },\n \"days\": {\n \"type\": \"integer\"\n },\n \"units\": {\n \"type\": \"string\"\n },\n \"include_hourly\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"location\",\n \"days\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nGet 3-day weather forecast for New York in metric units with hourly details<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"get_weather_forecast\", \"arguments\": {\"location\": \"New York\", \"days\": 3, \"units\": \"metric\", \"include_hourly\": true}}", "rejected": "I will get the weather forecast for New York"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"convert_currency\",\n \"description\": \"Convert currency amounts\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"amount\": {\n \"type\": \"number\"\n },\n \"from_currency\": {\n \"type\": \"string\"\n },\n \"to_currency\": {\n \"type\": \"string\"\n },\n \"include_fees\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"amount\",\n \"from_currency\",\n \"to_currency\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nConvert 100 US dollars to Euros with fees included<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"convert_currency\", \"arguments\": {\"amount\": 100, \"from_currency\": \"USD\", \"to_currency\": \"EUR\", \"include_fees\": true}}", "rejected": "I will convert that currency amount for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"optimize_database_query\",\n \"description\": \"Optimize database query\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"sql_query\": {\n \"type\": \"string\"\n },\n \"database_type\": {\n \"type\": \"string\"\n },\n \"performance_target\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"sql_query\",\n \"database_type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nOptimize this MySQL query for speed: SELECT id, name FROM users WHERE active = 1<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"optimize_database_query\", \"arguments\": {\"sql_query\": \"SELECT id, name FROM users WHERE active = 1\", \"database_type\": \"mysql\", \"performance_target\": \"speed\"}}", "rejected": "I will optimize that database query for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"analyze_text\",\n \"description\": \"Analyze text content\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"content\": {\n \"type\": \"string\"\n },\n \"type\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"content\",\n \"type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze this text: The CEO said we have made tremendous progress this quarter<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_text\", \"arguments\": {\"content\": \"The CEO said we have made tremendous progress this quarter\", \"type\": \"analysis\"}}", "rejected": "I will analyze that text for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"send_message\",\n \"description\": \"Send a message\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"to\": {\n \"type\": \"string\"\n },\n \"subject\": {\n \"type\": \"string\"\n },\n \"body\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"to\",\n \"subject\",\n \"body\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSend email to john@company.com with subject Meeting Update and body The meeting has been rescheduled to tomorrow at 2 PM<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"send_message\", \"arguments\": {\"to\": \"john@company.com\", \"subject\": \"Meeting Update\", \"body\": \"The meeting has been rescheduled to tomorrow at 2 PM\"}}", "rejected": "I will send that email for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"process_query\",\n \"description\": \"Process database query\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"query\": {\n \"type\": \"string\"\n },\n \"database\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"query\",\n \"database\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nRun query SELECT name FROM users WHERE created_at > 2023-01-01 on the main database<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"process_query\", \"arguments\": {\"query\": \"SELECT name FROM users WHERE created_at > 2023-01-01\", \"database\": \"main\"}}", "rejected": "I will run that database query for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"configure_system\",\n \"description\": \"Configure system settings\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"timeout\": {\n \"type\": \"integer\"\n },\n \"enabled\": {\n \"type\": \"boolean\"\n },\n \"level\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"timeout\",\n \"enabled\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSet timeout to 30 seconds, enable the system, and set level to debug<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"configure_system\", \"arguments\": {\"timeout\": 30, \"enabled\": true, \"level\": \"debug\"}}", "rejected": "I will configure the system with those settings"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"process_files\",\n \"description\": \"Process multiple files\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"files\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"operation\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"files\",\n \"operation\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nProcess files data.csv, results.json, and report.pdf with merge operation<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"process_files\", \"arguments\": {\"files\": [\"data.csv\", \"results.json\", \"report.pdf\"], \"operation\": \"merge\"}}", "rejected": "I will process those files for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"summarize_document\",\n \"description\": \"Summarize document content\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"document_url\": {\n \"type\": \"string\"\n },\n \"summary_length\": {\n \"type\": \"string\"\n },\n \"target_audience\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"document_url\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSummarize the document at https://example.com/report.pdf for executives with brief length<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"summarize_document\", \"arguments\": {\"document_url\": \"https://example.com/report.pdf\", \"summary_length\": \"brief\", \"target_audience\": \"executive\"}}", "rejected": "I will summarize that document for executives"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"analyze_sentiment\",\n \"description\": \"Analyze text sentiment\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"text\": {\n \"type\": \"string\"\n },\n \"language\": {\n \"type\": \"string\"\n },\n \"include_emotions\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"text\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze sentiment of this text: The product was excellent and delivery was fast with emotion details in English<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_sentiment\", \"arguments\": {\"text\": \"The product was excellent and delivery was fast\", \"language\": \"en\", \"include_emotions\": true}}", "rejected": "I will analyze the sentiment of that text"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"get_weather_forecast\",\n \"description\": \"Get weather forecast\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"location\": {\n \"type\": \"string\"\n },\n \"days\": {\n \"type\": \"integer\"\n },\n \"units\": {\n \"type\": \"string\"\n },\n \"include_hourly\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"location\",\n \"days\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nGet 3-day weather forecast for New York in metric units with hourly details<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"get_weather_forecast\", \"arguments\": {\"location\": \"New York\", \"days\": 3, \"units\": \"metric\", \"include_hourly\": true}}", "rejected": "I will get the weather forecast for New York"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"convert_currency\",\n \"description\": \"Convert currency amounts\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"amount\": {\n \"type\": \"number\"\n },\n \"from_currency\": {\n \"type\": \"string\"\n },\n \"to_currency\": {\n \"type\": \"string\"\n },\n \"include_fees\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"amount\",\n \"from_currency\",\n \"to_currency\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nConvert 100 US dollars to Euros with fees included<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"convert_currency\", \"arguments\": {\"amount\": 100, \"from_currency\": \"USD\", \"to_currency\": \"EUR\", \"include_fees\": true}}", "rejected": "I will convert that currency amount for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"optimize_database_query\",\n \"description\": \"Optimize database query\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"sql_query\": {\n \"type\": \"string\"\n },\n \"database_type\": {\n \"type\": \"string\"\n },\n \"performance_target\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"sql_query\",\n \"database_type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nOptimize this MySQL query for speed: SELECT id, name FROM users WHERE active = 1<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"optimize_database_query\", \"arguments\": {\"sql_query\": \"SELECT id, name FROM users WHERE active = 1\", \"database_type\": \"mysql\", \"performance_target\": \"speed\"}}", "rejected": "I will optimize that database query for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"analyze_text\",\n \"description\": \"Analyze text content\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"content\": {\n \"type\": \"string\"\n },\n \"type\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"content\",\n \"type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze this text: The CEO said we have made tremendous progress this quarter<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_text\", \"arguments\": {\"content\": \"The CEO said we have made tremendous progress this quarter\", \"type\": \"analysis\"}}", "rejected": "I will analyze that text for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"send_message\",\n \"description\": \"Send a message\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"to\": {\n \"type\": \"string\"\n },\n \"subject\": {\n \"type\": \"string\"\n },\n \"body\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"to\",\n \"subject\",\n \"body\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSend email to john@company.com with subject Meeting Update and body The meeting has been rescheduled to tomorrow at 2 PM<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"send_message\", \"arguments\": {\"to\": \"john@company.com\", \"subject\": \"Meeting Update\", \"body\": \"The meeting has been rescheduled to tomorrow at 2 PM\"}}", "rejected": "I will send that email for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"process_query\",\n \"description\": \"Process database query\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"query\": {\n \"type\": \"string\"\n },\n \"database\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"query\",\n \"database\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nRun query SELECT name FROM users WHERE created_at > 2023-01-01 on the main database<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"process_query\", \"arguments\": {\"query\": \"SELECT name FROM users WHERE created_at > 2023-01-01\", \"database\": \"main\"}}", "rejected": "I will run that database query for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"configure_system\",\n \"description\": \"Configure system settings\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"timeout\": {\n \"type\": \"integer\"\n },\n \"enabled\": {\n \"type\": \"boolean\"\n },\n \"level\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"timeout\",\n \"enabled\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSet timeout to 30 seconds, enable the system, and set level to debug<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"configure_system\", \"arguments\": {\"timeout\": 30, \"enabled\": true, \"level\": \"debug\"}}", "rejected": "I will configure the system with those settings"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"process_files\",\n \"description\": \"Process multiple files\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"files\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"operation\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"files\",\n \"operation\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nProcess files data.csv, results.json, and report.pdf with merge operation<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"process_files\", \"arguments\": {\"files\": [\"data.csv\", \"results.json\", \"report.pdf\"], \"operation\": \"merge\"}}", "rejected": "I will process those files for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"summarize_document\",\n \"description\": \"Summarize document content\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"document_url\": {\n \"type\": \"string\"\n },\n \"summary_length\": {\n \"type\": \"string\"\n },\n \"target_audience\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"document_url\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSummarize the document at https://example.com/report.pdf for executives with brief length<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"summarize_document\", \"arguments\": {\"document_url\": \"https://example.com/report.pdf\", \"summary_length\": \"brief\", \"target_audience\": \"executive\"}}", "rejected": "I will summarize that document for executives"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"analyze_sentiment\",\n \"description\": \"Analyze text sentiment\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"text\": {\n \"type\": \"string\"\n },\n \"language\": {\n \"type\": \"string\"\n },\n \"include_emotions\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"text\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze sentiment of this text: The product was excellent and delivery was fast with emotion details in English<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_sentiment\", \"arguments\": {\"text\": \"The product was excellent and delivery was fast\", \"language\": \"en\", \"include_emotions\": true}}", "rejected": "I will analyze the sentiment of that text"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"get_weather_forecast\",\n \"description\": \"Get weather forecast\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"location\": {\n \"type\": \"string\"\n },\n \"days\": {\n \"type\": \"integer\"\n },\n \"units\": {\n \"type\": \"string\"\n },\n \"include_hourly\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"location\",\n \"days\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nGet 3-day weather forecast for New York in metric units with hourly details<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"get_weather_forecast\", \"arguments\": {\"location\": \"New York\", \"days\": 3, \"units\": \"metric\", \"include_hourly\": true}}", "rejected": "I will get the weather forecast for New York"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"convert_currency\",\n \"description\": \"Convert currency amounts\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"amount\": {\n \"type\": \"number\"\n },\n \"from_currency\": {\n \"type\": \"string\"\n },\n \"to_currency\": {\n \"type\": \"string\"\n },\n \"include_fees\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"amount\",\n \"from_currency\",\n \"to_currency\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nConvert 100 US dollars to Euros with fees included<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"convert_currency\", \"arguments\": {\"amount\": 100, \"from_currency\": \"USD\", \"to_currency\": \"EUR\", \"include_fees\": true}}", "rejected": "I will convert that currency amount for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"optimize_database_query\",\n \"description\": \"Optimize database query\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"sql_query\": {\n \"type\": \"string\"\n },\n \"database_type\": {\n \"type\": \"string\"\n },\n \"performance_target\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"sql_query\",\n \"database_type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nOptimize this MySQL query for speed: SELECT id, name FROM users WHERE active = 1<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"optimize_database_query\", \"arguments\": {\"sql_query\": \"SELECT id, name FROM users WHERE active = 1\", \"database_type\": \"mysql\", \"performance_target\": \"speed\"}}", "rejected": "I will optimize that database query for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"analyze_text\",\n \"description\": \"Analyze text content\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"content\": {\n \"type\": \"string\"\n },\n \"type\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"content\",\n \"type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze this text: The CEO said we have made tremendous progress this quarter<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_text\", \"arguments\": {\"content\": \"The CEO said we have made tremendous progress this quarter\", \"type\": \"analysis\"}}", "rejected": "I will analyze that text for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"send_message\",\n \"description\": \"Send a message\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"to\": {\n \"type\": \"string\"\n },\n \"subject\": {\n \"type\": \"string\"\n },\n \"body\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"to\",\n \"subject\",\n \"body\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSend email to john@company.com with subject Meeting Update and body The meeting has been rescheduled to tomorrow at 2 PM<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"send_message\", \"arguments\": {\"to\": \"john@company.com\", \"subject\": \"Meeting Update\", \"body\": \"The meeting has been rescheduled to tomorrow at 2 PM\"}}", "rejected": "I will send that email for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"process_query\",\n \"description\": \"Process database query\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"query\": {\n \"type\": \"string\"\n },\n \"database\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"query\",\n \"database\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nRun query SELECT name FROM users WHERE created_at > 2023-01-01 on the main database<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"process_query\", \"arguments\": {\"query\": \"SELECT name FROM users WHERE created_at > 2023-01-01\", \"database\": \"main\"}}", "rejected": "I will run that database query for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"configure_system\",\n \"description\": \"Configure system settings\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"timeout\": {\n \"type\": \"integer\"\n },\n \"enabled\": {\n \"type\": \"boolean\"\n },\n \"level\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"timeout\",\n \"enabled\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSet timeout to 30 seconds, enable the system, and set level to debug<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"configure_system\", \"arguments\": {\"timeout\": 30, \"enabled\": true, \"level\": \"debug\"}}", "rejected": "I will configure the system with those settings"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"process_files\",\n \"description\": \"Process multiple files\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"files\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"operation\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"files\",\n \"operation\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nProcess files data.csv, results.json, and report.pdf with merge operation<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"process_files\", \"arguments\": {\"files\": [\"data.csv\", \"results.json\", \"report.pdf\"], \"operation\": \"merge\"}}", "rejected": "I will process those files for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"summarize_document\",\n \"description\": \"Summarize document content\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"document_url\": {\n \"type\": \"string\"\n },\n \"summary_length\": {\n \"type\": \"string\"\n },\n \"target_audience\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"document_url\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSummarize the document at https://example.com/report.pdf for executives with brief length<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"summarize_document\", \"arguments\": {\"document_url\": \"https://example.com/report.pdf\", \"summary_length\": \"brief\", \"target_audience\": \"executive\"}}", "rejected": "I will summarize that document for executives"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"analyze_sentiment\",\n \"description\": \"Analyze text sentiment\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"text\": {\n \"type\": \"string\"\n },\n \"language\": {\n \"type\": \"string\"\n },\n \"include_emotions\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"text\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze sentiment of this text: The product was excellent and delivery was fast with emotion details in English<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_sentiment\", \"arguments\": {\"text\": \"The product was excellent and delivery was fast\", \"language\": \"en\", \"include_emotions\": true}}", "rejected": "I will analyze the sentiment of that text"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"get_weather_forecast\",\n \"description\": \"Get weather forecast\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"location\": {\n \"type\": \"string\"\n },\n \"days\": {\n \"type\": \"integer\"\n },\n \"units\": {\n \"type\": \"string\"\n },\n \"include_hourly\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"location\",\n \"days\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nGet 3-day weather forecast for New York in metric units with hourly details<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"get_weather_forecast\", \"arguments\": {\"location\": \"New York\", \"days\": 3, \"units\": \"metric\", \"include_hourly\": true}}", "rejected": "I will get the weather forecast for New York"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"convert_currency\",\n \"description\": \"Convert currency amounts\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"amount\": {\n \"type\": \"number\"\n },\n \"from_currency\": {\n \"type\": \"string\"\n },\n \"to_currency\": {\n \"type\": \"string\"\n },\n \"include_fees\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"amount\",\n \"from_currency\",\n \"to_currency\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nConvert 100 US dollars to Euros with fees included<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"convert_currency\", \"arguments\": {\"amount\": 100, \"from_currency\": \"USD\", \"to_currency\": \"EUR\", \"include_fees\": true}}", "rejected": "I will convert that currency amount for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"optimize_database_query\",\n \"description\": \"Optimize database query\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"sql_query\": {\n \"type\": \"string\"\n },\n \"database_type\": {\n \"type\": \"string\"\n },\n \"performance_target\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"sql_query\",\n \"database_type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nOptimize this MySQL query for speed: SELECT id, name FROM users WHERE active = 1<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"optimize_database_query\", \"arguments\": {\"sql_query\": \"SELECT id, name FROM users WHERE active = 1\", \"database_type\": \"mysql\", \"performance_target\": \"speed\"}}", "rejected": "I will optimize that database query for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"analyze_text\",\n \"description\": \"Analyze text content\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"content\": {\n \"type\": \"string\"\n },\n \"type\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"content\",\n \"type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze this text: The CEO said we have made tremendous progress this quarter<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_text\", \"arguments\": {\"content\": \"The CEO said we have made tremendous progress this quarter\", \"type\": \"analysis\"}}", "rejected": "I will analyze that text for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"send_message\",\n \"description\": \"Send a message\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"to\": {\n \"type\": \"string\"\n },\n \"subject\": {\n \"type\": \"string\"\n },\n \"body\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"to\",\n \"subject\",\n \"body\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSend email to john@company.com with subject Meeting Update and body The meeting has been rescheduled to tomorrow at 2 PM<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"send_message\", \"arguments\": {\"to\": \"john@company.com\", \"subject\": \"Meeting Update\", \"body\": \"The meeting has been rescheduled to tomorrow at 2 PM\"}}", "rejected": "I will send that email for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"process_query\",\n \"description\": \"Process database query\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"query\": {\n \"type\": \"string\"\n },\n \"database\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"query\",\n \"database\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nRun query SELECT name FROM users WHERE created_at > 2023-01-01 on the main database<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"process_query\", \"arguments\": {\"query\": \"SELECT name FROM users WHERE created_at > 2023-01-01\", \"database\": \"main\"}}", "rejected": "I will run that database query for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"configure_system\",\n \"description\": \"Configure system settings\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"timeout\": {\n \"type\": \"integer\"\n },\n \"enabled\": {\n \"type\": \"boolean\"\n },\n \"level\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"timeout\",\n \"enabled\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSet timeout to 30 seconds, enable the system, and set level to debug<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"configure_system\", \"arguments\": {\"timeout\": 30, \"enabled\": true, \"level\": \"debug\"}}", "rejected": "I will configure the system with those settings"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"process_files\",\n \"description\": \"Process multiple files\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"files\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"operation\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"files\",\n \"operation\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nProcess files data.csv, results.json, and report.pdf with merge operation<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"process_files\", \"arguments\": {\"files\": [\"data.csv\", \"results.json\", \"report.pdf\"], \"operation\": \"merge\"}}", "rejected": "I will process those files for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"summarize_document\",\n \"description\": \"Summarize document content\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"document_url\": {\n \"type\": \"string\"\n },\n \"summary_length\": {\n \"type\": \"string\"\n },\n \"target_audience\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"document_url\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSummarize the document at https://example.com/report.pdf for executives with brief length<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"summarize_document\", \"arguments\": {\"document_url\": \"https://example.com/report.pdf\", \"summary_length\": \"brief\", \"target_audience\": \"executive\"}}", "rejected": "I will summarize that document for executives"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"analyze_sentiment\",\n \"description\": \"Analyze text sentiment\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"text\": {\n \"type\": \"string\"\n },\n \"language\": {\n \"type\": \"string\"\n },\n \"include_emotions\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"text\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze sentiment of this text: The product was excellent and delivery was fast with emotion details in English<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_sentiment\", \"arguments\": {\"text\": \"The product was excellent and delivery was fast\", \"language\": \"en\", \"include_emotions\": true}}", "rejected": "I will analyze the sentiment of that text"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"get_weather_forecast\",\n \"description\": \"Get weather forecast\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"location\": {\n \"type\": \"string\"\n },\n \"days\": {\n \"type\": \"integer\"\n },\n \"units\": {\n \"type\": \"string\"\n },\n \"include_hourly\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"location\",\n \"days\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nGet 3-day weather forecast for New York in metric units with hourly details<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"get_weather_forecast\", \"arguments\": {\"location\": \"New York\", \"days\": 3, \"units\": \"metric\", \"include_hourly\": true}}", "rejected": "I will get the weather forecast for New York"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"convert_currency\",\n \"description\": \"Convert currency amounts\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"amount\": {\n \"type\": \"number\"\n },\n \"from_currency\": {\n \"type\": \"string\"\n },\n \"to_currency\": {\n \"type\": \"string\"\n },\n \"include_fees\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"amount\",\n \"from_currency\",\n \"to_currency\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nConvert 100 US dollars to Euros with fees included<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"convert_currency\", \"arguments\": {\"amount\": 100, \"from_currency\": \"USD\", \"to_currency\": \"EUR\", \"include_fees\": true}}", "rejected": "I will convert that currency amount for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"optimize_database_query\",\n \"description\": \"Optimize database query\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"sql_query\": {\n \"type\": \"string\"\n },\n \"database_type\": {\n \"type\": \"string\"\n },\n \"performance_target\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"sql_query\",\n \"database_type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nOptimize this MySQL query for speed: SELECT id, name FROM users WHERE active = 1<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"optimize_database_query\", \"arguments\": {\"sql_query\": \"SELECT id, name FROM users WHERE active = 1\", \"database_type\": \"mysql\", \"performance_target\": \"speed\"}}", "rejected": "I will optimize that database query for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"analyze_text\",\n \"description\": \"Analyze text content\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"content\": {\n \"type\": \"string\"\n },\n \"type\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"content\",\n \"type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze this text: The CEO said we have made tremendous progress this quarter<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_text\", \"arguments\": {\"content\": \"The CEO said we have made tremendous progress this quarter\", \"type\": \"analysis\"}}", "rejected": "I will analyze that text for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"send_message\",\n \"description\": \"Send a message\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"to\": {\n \"type\": \"string\"\n },\n \"subject\": {\n \"type\": \"string\"\n },\n \"body\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"to\",\n \"subject\",\n \"body\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSend email to john@company.com with subject Meeting Update and body The meeting has been rescheduled to tomorrow at 2 PM<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"send_message\", \"arguments\": {\"to\": \"john@company.com\", \"subject\": \"Meeting Update\", \"body\": \"The meeting has been rescheduled to tomorrow at 2 PM\"}}", "rejected": "I will send that email for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"process_query\",\n \"description\": \"Process database query\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"query\": {\n \"type\": \"string\"\n },\n \"database\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"query\",\n \"database\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nRun query SELECT name FROM users WHERE created_at > 2023-01-01 on the main database<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"process_query\", \"arguments\": {\"query\": \"SELECT name FROM users WHERE created_at > 2023-01-01\", \"database\": \"main\"}}", "rejected": "I will run that database query for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"configure_system\",\n \"description\": \"Configure system settings\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"timeout\": {\n \"type\": \"integer\"\n },\n \"enabled\": {\n \"type\": \"boolean\"\n },\n \"level\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"timeout\",\n \"enabled\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSet timeout to 30 seconds, enable the system, and set level to debug<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"configure_system\", \"arguments\": {\"timeout\": 30, \"enabled\": true, \"level\": \"debug\"}}", "rejected": "I will configure the system with those settings"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"process_files\",\n \"description\": \"Process multiple files\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"files\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"operation\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"files\",\n \"operation\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nProcess files data.csv, results.json, and report.pdf with merge operation<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"process_files\", \"arguments\": {\"files\": [\"data.csv\", \"results.json\", \"report.pdf\"], \"operation\": \"merge\"}}", "rejected": "I will process those files for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"summarize_document\",\n \"description\": \"Summarize document content\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"document_url\": {\n \"type\": \"string\"\n },\n \"summary_length\": {\n \"type\": \"string\"\n },\n \"target_audience\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"document_url\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSummarize the document at https://example.com/report.pdf for executives with brief length<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"summarize_document\", \"arguments\": {\"document_url\": \"https://example.com/report.pdf\", \"summary_length\": \"brief\", \"target_audience\": \"executive\"}}", "rejected": "I will summarize that document for executives"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"analyze_sentiment\",\n \"description\": \"Analyze text sentiment\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"text\": {\n \"type\": \"string\"\n },\n \"language\": {\n \"type\": \"string\"\n },\n \"include_emotions\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"text\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze sentiment of this text: The product was excellent and delivery was fast with emotion details in English<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_sentiment\", \"arguments\": {\"text\": \"The product was excellent and delivery was fast\", \"language\": \"en\", \"include_emotions\": true}}", "rejected": "I will analyze the sentiment of that text"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"get_weather_forecast\",\n \"description\": \"Get weather forecast\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"location\": {\n \"type\": \"string\"\n },\n \"days\": {\n \"type\": \"integer\"\n },\n \"units\": {\n \"type\": \"string\"\n },\n \"include_hourly\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"location\",\n \"days\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nGet 3-day weather forecast for New York in metric units with hourly details<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"get_weather_forecast\", \"arguments\": {\"location\": \"New York\", \"days\": 3, \"units\": \"metric\", \"include_hourly\": true}}", "rejected": "I will get the weather forecast for New York"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"convert_currency\",\n \"description\": \"Convert currency amounts\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"amount\": {\n \"type\": \"number\"\n },\n \"from_currency\": {\n \"type\": \"string\"\n },\n \"to_currency\": {\n \"type\": \"string\"\n },\n \"include_fees\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"amount\",\n \"from_currency\",\n \"to_currency\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nConvert 100 US dollars to Euros with fees included<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"convert_currency\", \"arguments\": {\"amount\": 100, \"from_currency\": \"USD\", \"to_currency\": \"EUR\", \"include_fees\": true}}", "rejected": "I will convert that currency amount for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"optimize_database_query\",\n \"description\": \"Optimize database query\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"sql_query\": {\n \"type\": \"string\"\n },\n \"database_type\": {\n \"type\": \"string\"\n },\n \"performance_target\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"sql_query\",\n \"database_type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nOptimize this MySQL query for speed: SELECT id, name FROM users WHERE active = 1<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"optimize_database_query\", \"arguments\": {\"sql_query\": \"SELECT id, name FROM users WHERE active = 1\", \"database_type\": \"mysql\", \"performance_target\": \"speed\"}}", "rejected": "I will optimize that database query for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"analyze_text\",\n \"description\": \"Analyze text content\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"content\": {\n \"type\": \"string\"\n },\n \"type\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"content\",\n \"type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze this text: The CEO said we have made tremendous progress this quarter<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_text\", \"arguments\": {\"content\": \"The CEO said we have made tremendous progress this quarter\", \"type\": \"analysis\"}}", "rejected": "I will analyze that text for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"send_message\",\n \"description\": \"Send a message\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"to\": {\n \"type\": \"string\"\n },\n \"subject\": {\n \"type\": \"string\"\n },\n \"body\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"to\",\n \"subject\",\n \"body\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSend email to john@company.com with subject Meeting Update and body The meeting has been rescheduled to tomorrow at 2 PM<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"send_message\", \"arguments\": {\"to\": \"john@company.com\", \"subject\": \"Meeting Update\", \"body\": \"The meeting has been rescheduled to tomorrow at 2 PM\"}}", "rejected": "I will send that email for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"process_query\",\n \"description\": \"Process database query\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"query\": {\n \"type\": \"string\"\n },\n \"database\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"query\",\n \"database\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nRun query SELECT name FROM users WHERE created_at > 2023-01-01 on the main database<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"process_query\", \"arguments\": {\"query\": \"SELECT name FROM users WHERE created_at > 2023-01-01\", \"database\": \"main\"}}", "rejected": "I will run that database query for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"configure_system\",\n \"description\": \"Configure system settings\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"timeout\": {\n \"type\": \"integer\"\n },\n \"enabled\": {\n \"type\": \"boolean\"\n },\n \"level\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"timeout\",\n \"enabled\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSet timeout to 30 seconds, enable the system, and set level to debug<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"configure_system\", \"arguments\": {\"timeout\": 30, \"enabled\": true, \"level\": \"debug\"}}", "rejected": "I will configure the system with those settings"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"process_files\",\n \"description\": \"Process multiple files\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"files\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"operation\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"files\",\n \"operation\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nProcess files data.csv, results.json, and report.pdf with merge operation<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"process_files\", \"arguments\": {\"files\": [\"data.csv\", \"results.json\", \"report.pdf\"], \"operation\": \"merge\"}}", "rejected": "I will process those files for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"summarize_document\",\n \"description\": \"Summarize document content\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"document_url\": {\n \"type\": \"string\"\n },\n \"summary_length\": {\n \"type\": \"string\"\n },\n \"target_audience\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"document_url\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSummarize the document at https://example.com/report.pdf for executives with brief length<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"summarize_document\", \"arguments\": {\"document_url\": \"https://example.com/report.pdf\", \"summary_length\": \"brief\", \"target_audience\": \"executive\"}}", "rejected": "I will summarize that document for executives"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"analyze_sentiment\",\n \"description\": \"Analyze text sentiment\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"text\": {\n \"type\": \"string\"\n },\n \"language\": {\n \"type\": \"string\"\n },\n \"include_emotions\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"text\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze sentiment of this text: The product was excellent and delivery was fast with emotion details in English<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_sentiment\", \"arguments\": {\"text\": \"The product was excellent and delivery was fast\", \"language\": \"en\", \"include_emotions\": true}}", "rejected": "I will analyze the sentiment of that text"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"get_weather_forecast\",\n \"description\": \"Get weather forecast\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"location\": {\n \"type\": \"string\"\n },\n \"days\": {\n \"type\": \"integer\"\n },\n \"units\": {\n \"type\": \"string\"\n },\n \"include_hourly\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"location\",\n \"days\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nGet 3-day weather forecast for New York in metric units with hourly details<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"get_weather_forecast\", \"arguments\": {\"location\": \"New York\", \"days\": 3, \"units\": \"metric\", \"include_hourly\": true}}", "rejected": "I will get the weather forecast for New York"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"convert_currency\",\n \"description\": \"Convert currency amounts\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"amount\": {\n \"type\": \"number\"\n },\n \"from_currency\": {\n \"type\": \"string\"\n },\n \"to_currency\": {\n \"type\": \"string\"\n },\n \"include_fees\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"amount\",\n \"from_currency\",\n \"to_currency\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nConvert 100 US dollars to Euros with fees included<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"convert_currency\", \"arguments\": {\"amount\": 100, \"from_currency\": \"USD\", \"to_currency\": \"EUR\", \"include_fees\": true}}", "rejected": "I will convert that currency amount for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"optimize_database_query\",\n \"description\": \"Optimize database query\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"sql_query\": {\n \"type\": \"string\"\n },\n \"database_type\": {\n \"type\": \"string\"\n },\n \"performance_target\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"sql_query\",\n \"database_type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nOptimize this MySQL query for speed: SELECT id, name FROM users WHERE active = 1<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"optimize_database_query\", \"arguments\": {\"sql_query\": \"SELECT id, name FROM users WHERE active = 1\", \"database_type\": \"mysql\", \"performance_target\": \"speed\"}}", "rejected": "I will optimize that database query for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"analyze_text\",\n \"description\": \"Analyze text content\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"content\": {\n \"type\": \"string\"\n },\n \"type\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"content\",\n \"type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze this text: The CEO said we have made tremendous progress this quarter<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_text\", \"arguments\": {\"content\": \"The CEO said we have made tremendous progress this quarter\", \"type\": \"analysis\"}}", "rejected": "I will analyze that text for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"send_message\",\n \"description\": \"Send a message\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"to\": {\n \"type\": \"string\"\n },\n \"subject\": {\n \"type\": \"string\"\n },\n \"body\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"to\",\n \"subject\",\n \"body\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSend email to john@company.com with subject Meeting Update and body The meeting has been rescheduled to tomorrow at 2 PM<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"send_message\", \"arguments\": {\"to\": \"john@company.com\", \"subject\": \"Meeting Update\", \"body\": \"The meeting has been rescheduled to tomorrow at 2 PM\"}}", "rejected": "I will send that email for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"process_query\",\n \"description\": \"Process database query\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"query\": {\n \"type\": \"string\"\n },\n \"database\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"query\",\n \"database\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nRun query SELECT name FROM users WHERE created_at > 2023-01-01 on the main database<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"process_query\", \"arguments\": {\"query\": \"SELECT name FROM users WHERE created_at > 2023-01-01\", \"database\": \"main\"}}", "rejected": "I will run that database query for you"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"configure_system\",\n \"description\": \"Configure system settings\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"timeout\": {\n \"type\": \"integer\"\n },\n \"enabled\": {\n \"type\": \"boolean\"\n },\n \"level\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"timeout\",\n \"enabled\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSet timeout to 30 seconds, enable the system, and set level to debug<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"configure_system\", \"arguments\": {\"timeout\": 30, \"enabled\": true, \"level\": \"debug\"}}", "rejected": "I will configure the system with those settings"} | |
| {"prompt": "<|im_start|>system\nYou are a helpful assistant that calls functions by responding with valid JSON when given a schema. Always respond with JSON function calls only, never prose.<|im_end|>\n\n<schema>\n{\n \"name\": \"process_files\",\n \"description\": \"Process multiple files\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"files\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"operation\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"files\",\n \"operation\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nProcess files data.csv, results.json, and report.pdf with merge operation<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"process_files\", \"arguments\": {\"files\": [\"data.csv\", \"results.json\", \"report.pdf\"], \"operation\": \"merge\"}}", "rejected": "I will process those files for you"} | |