Dynamic-Function-Calling-Agent / tool_pairs_enhanced.jsonl
jlov7's picture
feat: Multi-tool selection and robustness testing
6639f75
{"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_stock_price\",\n \"description\": \"Get current stock price for a ticker\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"ticker\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"ticker\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nWhat's Apple's current stock price?<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"get_stock_price\", \"arguments\": {\"ticker\": \"AAPL\"}}", "rejected": "I'll help you get Apple's current stock price using our market data."}
{"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_document\",\n \"description\": \"Analyze document content for insights\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"document_text\": {\n \"type\": \"string\"\n },\n \"analysis_type\": {\n \"type\": \"string\"\n },\n \"focus_areas\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"required\": [\n \"document_text\",\n \"analysis_type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze this quarterly report: 'Q4 2024 showed remarkable growth with revenue increasing 25% year-over-year to $2.3 billion. Our flagship product line contributed 60% of total revenue, while emerging markets expanded by 40%. Key challenges include supply chain optimization and talent acquisition in our European operations.' Focus on financial performance and operational insights.<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_document\", \"arguments\": {\"document_text\": \"Q4 2024 showed remarkable growth with revenue increasing 25% year-over-year to $2.3 billion. Our flagship product line contributed 60% of total revenue, while emerging markets expanded by 40%. Key challenges include supply chain optimization and talent acquisition in our European operations.\", \"analysis_type\": \"comprehensive\", \"focus_areas\": [\"financial\", \"operational\"]}}", "rejected": "I'll analyze that quarterly report for you, focusing on the financial and operational aspects."}
{"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_email\",\n \"description\": \"Send an email 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 \"priority\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"to\",\n \"subject\",\n \"body\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSend an email to [email protected] about the project delay with subject 'Project Timeline Update' explaining that due to unexpected technical challenges and resource constraints, we need to extend the deadline by two weeks to ensure quality delivery.<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"send_email\", \"arguments\": {\"to\": \"[email protected]\", \"subject\": \"Project Timeline Update\", \"body\": \"Due to unexpected technical challenges and resource constraints, we need to extend the deadline by two weeks to ensure quality delivery.\", \"priority\": \"high\"}}", "rejected": "I'll send that email about the project delay to John 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\": \"search_database\",\n \"description\": \"Search database records\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"query\": {\n \"type\": \"string\"\n },\n \"filters\": {\n \"type\": \"object\"\n },\n \"limit\": {\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"query\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSearch for customers with names containing O'Brien or D'Angelo who registered after 2023-01-01 and have premium status, limit to 50 results<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"search_database\", \"arguments\": {\"query\": \"customers with names containing OBrien or DAngelo registered after 2023-01-01\", \"filters\": {\"status\": \"premium\", \"registration_date\": \">2023-01-01\"}, \"limit\": 50}}", "rejected": "I'll search the database for those premium customers with Irish names registered this year."}
{"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_api_endpoint\",\n \"description\": \"Configure API endpoint settings\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"endpoint\": {\n \"type\": \"string\"\n },\n \"methods\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"authentication\": {\n \"type\": \"object\",\n \"properties\": {\n \"type\": {\n \"type\": \"string\"\n },\n \"credentials\": {\n \"type\": \"object\"\n }\n }\n },\n \"rate_limits\": {\n \"type\": \"object\",\n \"properties\": {\n \"requests_per_minute\": {\n \"type\": \"integer\"\n },\n \"burst_limit\": {\n \"type\": \"integer\"\n }\n }\n }\n },\n \"required\": [\n \"endpoint\",\n \"methods\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSet up the /api/v2/users endpoint to accept GET and POST requests with OAuth2 authentication using client credentials, and rate limiting of 100 requests per minute with burst up to 150<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"configure_api_endpoint\", \"arguments\": {\"endpoint\": \"/api/v2/users\", \"methods\": [\"GET\", \"POST\"], \"authentication\": {\"type\": \"oauth2\", \"credentials\": {\"grant_type\": \"client_credentials\"}}, \"rate_limits\": {\"requests_per_minute\": 100, \"burst_limit\": 150}}}", "rejected": "I'll configure that API endpoint with OAuth2 authentication and the specified rate limits."}
{"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_data_batch\",\n \"description\": \"Process a batch of data records\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"input_files\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"output_format\": {\n \"type\": \"string\"\n },\n \"transformations\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"object\"\n }\n },\n \"validation_rules\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"required\": [\n \"input_files\",\n \"output_format\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nProcess files data_2024_q1.csv, data_2024_q2.csv, and data_2024_q3.csv into JSON format with transformations to normalize currency fields and validate that all records have valid email addresses and phone numbers<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"process_data_batch\", \"arguments\": {\"input_files\": [\"data_2024_q1.csv\", \"data_2024_q2.csv\", \"data_2024_q3.csv\"], \"output_format\": \"json\", \"transformations\": [{\"type\": \"normalize\", \"field\": \"currency\"}, {\"type\": \"standardize\", \"field\": \"phone\"}], \"validation_rules\": [\"valid_email\", \"valid_phone\", \"required_fields\"]}}", "rejected": "I'll process those quarterly data files with currency normalization and validation rules."}
{"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\": \"generate_financial_report\",\n \"description\": \"Generate comprehensive financial report\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"report_type\": {\n \"type\": \"string\"\n },\n \"date_range\": {\n \"type\": \"object\",\n \"properties\": {\n \"start_date\": {\n \"type\": \"string\"\n },\n \"end_date\": {\n \"type\": \"string\"\n }\n }\n },\n \"departments\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"metrics\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"breakdown_by\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"format\": {\n \"type\": \"string\"\n },\n \"include_comparisons\": {\n \"type\": \"boolean\"\n }\n },\n \"required\": [\n \"report_type\",\n \"date_range\",\n \"departments\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nCreate a quarterly P&L report for Sales, Marketing, and Operations departments from 2024-07-01 to 2024-09-30, including revenue, expenses, and profit margins broken down by region and product line in Excel format with year-over-year comparisons<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"generate_financial_report\", \"arguments\": {\"report_type\": \"profit_and_loss\", \"date_range\": {\"start_date\": \"2024-07-01\", \"end_date\": \"2024-09-30\"}, \"departments\": [\"Sales\", \"Marketing\", \"Operations\"], \"metrics\": [\"revenue\", \"expenses\", \"profit_margin\"], \"breakdown_by\": [\"region\", \"product_line\"], \"format\": \"excel\", \"include_comparisons\": true}}", "rejected": "I'll generate that quarterly P&L report with regional and product breakdowns plus YoY comparisons."}
{"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\": \"update_employee_record\",\n \"description\": \"Update employee information in HR system\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"employee_id\": {\n \"type\": \"string\"\n },\n \"updates\": {\n \"type\": \"object\",\n \"properties\": {\n \"personal_info\": {\n \"type\": \"object\"\n },\n \"job_details\": {\n \"type\": \"object\"\n },\n \"compensation\": {\n \"type\": \"object\"\n }\n }\n },\n \"effective_date\": {\n \"type\": \"string\"\n },\n \"approval_required\": {\n \"type\": \"boolean\"\n },\n \"notification_settings\": {\n \"type\": \"object\"\n }\n },\n \"required\": [\n \"employee_id\",\n \"updates\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nUpdate employee EMP-12345's record with promotion to Senior Data Scientist in the Analytics team, salary increase to $135,000 annually, new manager Sarah Johnson (EMP-67890), effective January 15th 2025, requiring approval and sending notifications to HR and the employee<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"update_employee_record\", \"arguments\": {\"employee_id\": \"EMP-12345\", \"updates\": {\"personal_info\": {\"manager_id\": \"EMP-67890\", \"manager_name\": \"Sarah Johnson\"}, \"job_details\": {\"title\": \"Senior Data Scientist\", \"department\": \"Analytics\", \"team\": \"Analytics\"}, \"compensation\": {\"annual_salary\": 135000, \"currency\": \"USD\"}}, \"effective_date\": \"2025-01-15\", \"approval_required\": true, \"notification_settings\": {\"notify_hr\": true, \"notify_employee\": true, \"notify_manager\": true}}}", "rejected": "I'll update that employee record with the promotion details and compensation changes, requiring approvals."}
{"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\": \"create_content\",\n \"description\": \"Create content with rich formatting\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"title\": {\n \"type\": \"string\"\n },\n \"content\": {\n \"type\": \"string\"\n },\n \"metadata\": {\n \"type\": \"object\"\n },\n \"tags\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"required\": [\n \"title\",\n \"content\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nCreate a blog post titled 'The New Era of AI: What's Next?' with content discussing how AI is transforming industries, including quotes from experts, tagged with AI, technology, and future<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"create_content\", \"arguments\": {\"title\": \"The New Era of AI: What's Next?\", \"content\": \"AI is transforming industries with experts saying AI will revolutionize everything and we are just getting started. The future holds tremendous potential.\", \"metadata\": {\"category\": \"technology\", \"author\": \"AI Research Team\"}, \"tags\": [\"AI\", \"technology\", \"future\"]}}", "rejected": "I'll create that blog post about AI's new era with the expert quotes and proper tagging."}
{"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_settings\",\n \"description\": \"Configure system settings and parameters\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"cache_size_mb\": {\n \"type\": \"integer\"\n },\n \"enable_logging\": {\n \"type\": \"boolean\"\n },\n \"log_level\": {\n \"type\": \"string\"\n },\n \"timeout_seconds\": {\n \"type\": \"number\"\n },\n \"allowed_origins\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"feature_flags\": {\n \"type\": \"object\"\n }\n },\n \"required\": [\n \"cache_size_mb\",\n \"enable_logging\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSet cache to 512 MB, enable logging at debug level, timeout of 30.5 seconds, allow origins from localhost:3000 and *.company.com, and enable experimental features for beta users but disable legacy support<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"configure_system_settings\", \"arguments\": {\"cache_size_mb\": 512, \"enable_logging\": true, \"log_level\": \"debug\", \"timeout_seconds\": 30.5, \"allowed_origins\": [\"localhost:3000\", \"*.company.com\"], \"feature_flags\": {\"experimental_features\": true, \"beta_user_access\": true, \"legacy_support\": false}}}", "rejected": "I'll configure those system settings with the specified cache, logging, and feature flags."}
{"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 with detailed parameters\",\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 \"enum\": [\n \"metric\",\n \"imperial\",\n \"kelvin\"\n ]\n },\n \"include_hourly\": {\n \"type\": \"boolean\"\n },\n \"alert_types\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"required\": [\n \"location\",\n \"days\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nGet a 5-day weather forecast for San Francisco, California in metric units with hourly breakdown and alerts for severe weather, precipitation, and temperature extremes<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"get_weather_forecast\", \"arguments\": {\"location\": \"San Francisco, California\", \"days\": 5, \"units\": \"metric\", \"include_hourly\": true, \"alert_types\": [\"severe_weather\", \"precipitation\", \"temperature_extremes\"]}}", "rejected": "I'll get that detailed 5-day forecast for San Francisco with hourly data and weather alerts."}
{"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 with detailed options\",\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 \"date\": {\n \"type\": \"string\"\n },\n \"include_fees\": {\n \"type\": \"boolean\"\n },\n \"precision\": {\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"amount\",\n \"from_currency\",\n \"to_currency\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nConvert 2,500.75 US dollars to Japanese yen using exchange rates from December 15th, 2024, include conversion fees, and show result with 2 decimal places precision<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"convert_currency\", \"arguments\": {\"amount\": 2500.75, \"from_currency\": \"USD\", \"to_currency\": \"JPY\", \"date\": \"2024-12-15\", \"include_fees\": true, \"precision\": 2}}", "rejected": "I'll convert that amount from USD to JPY using the specified date and including fees."}
{"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 with advanced options\",\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 \"confidence_threshold\": {\n \"type\": \"number\"\n },\n \"aspects\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"required\": [\n \"text\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze the sentiment of this customer review: 'The product quality exceeded my expectations, but the delivery was delayed by a week. Customer service was helpful in resolving the issue.' Include emotion analysis and focus on product quality, delivery, and customer service aspects with 0.8 confidence threshold<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_sentiment\", \"arguments\": {\"text\": \"The product quality exceeded my expectations, but the delivery was delayed by a week. Customer service was helpful in resolving the issue.\", \"language\": \"en\", \"include_emotions\": true, \"confidence_threshold\": 0.8, \"aspects\": [\"product_quality\", \"delivery\", \"customer_service\"]}}", "rejected": "I'll analyze the sentiment of that customer review, focusing on the specific aspects you mentioned."}
{"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_document\",\n \"description\": \"Analyze document content for insights\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"document_text\": {\n \"type\": \"string\"\n },\n \"analysis_type\": {\n \"type\": \"string\"\n },\n \"focus_areas\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"required\": [\n \"document_text\",\n \"analysis_type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze this quarterly report: 'Q4 2024 showed remarkable growth with revenue increasing 25% year-over-year to $2.3 billion. Our flagship product line contributed 60% of total revenue, while emerging markets expanded by 40%. Key challenges include supply chain optimization and talent acquisition in our European operations.' Focus on financial performance and operational insights.<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_document\", \"arguments\": {\"document_text\": \"Q4 2024 showed remarkable growth with revenue increasing 25% year-over-year to $2.3 billion. Our flagship product line contributed 60% of total revenue, while emerging markets expanded by 40%. Key challenges include supply chain optimization and talent acquisition in our European operations.\", \"analysis_type\": \"comprehensive\", \"focus_areas\": [\"financial\", \"operational\"]}}", "rejected": "I'll analyze that quarterly report for you, focusing on the financial and operational aspects."}
{"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_email\",\n \"description\": \"Send an email 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 \"priority\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"to\",\n \"subject\",\n \"body\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSend an email to [email protected] about the project delay with subject 'Project Timeline Update' explaining that due to unexpected technical challenges and resource constraints, we need to extend the deadline by two weeks to ensure quality delivery.<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"send_email\", \"arguments\": {\"to\": \"[email protected]\", \"subject\": \"Project Timeline Update\", \"body\": \"Due to unexpected technical challenges and resource constraints, we need to extend the deadline by two weeks to ensure quality delivery.\", \"priority\": \"high\"}}", "rejected": "I'll send that email about the project delay to John 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\": \"search_database\",\n \"description\": \"Search database records\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"query\": {\n \"type\": \"string\"\n },\n \"filters\": {\n \"type\": \"object\"\n },\n \"limit\": {\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"query\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSearch for customers with names containing O'Brien or D'Angelo who registered after 2023-01-01 and have premium status, limit to 50 results<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"search_database\", \"arguments\": {\"query\": \"customers with names containing OBrien or DAngelo registered after 2023-01-01\", \"filters\": {\"status\": \"premium\", \"registration_date\": \">2023-01-01\"}, \"limit\": 50}}", "rejected": "I'll search the database for those premium customers with Irish names registered this year."}
{"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 with detailed parameters\",\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 \"enum\": [\n \"metric\",\n \"imperial\",\n \"kelvin\"\n ]\n },\n \"include_hourly\": {\n \"type\": \"boolean\"\n },\n \"alert_types\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"required\": [\n \"location\",\n \"days\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nGet a 5-day weather forecast for San Francisco, California in metric units with hourly breakdown and alerts for severe weather, precipitation, and temperature extremes<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"get_weather_forecast\", \"arguments\": {\"location\": \"San Francisco, California\", \"days\": 5, \"units\": \"metric\", \"include_hourly\": true, \"alert_types\": [\"severe_weather\", \"precipitation\", \"temperature_extremes\"]}}", "rejected": "I'll get that detailed 5-day forecast for San Francisco with hourly data and weather alerts."}
{"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 with detailed options\",\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 \"date\": {\n \"type\": \"string\"\n },\n \"include_fees\": {\n \"type\": \"boolean\"\n },\n \"precision\": {\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"amount\",\n \"from_currency\",\n \"to_currency\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nConvert 2,500.75 US dollars to Japanese yen using exchange rates from December 15th, 2024, include conversion fees, and show result with 2 decimal places precision<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"convert_currency\", \"arguments\": {\"amount\": 2500.75, \"from_currency\": \"USD\", \"to_currency\": \"JPY\", \"date\": \"2024-12-15\", \"include_fees\": true, \"precision\": 2}}", "rejected": "I'll convert that amount from USD to JPY using the specified date and including fees."}
{"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 with advanced options\",\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 \"confidence_threshold\": {\n \"type\": \"number\"\n },\n \"aspects\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"required\": [\n \"text\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze the sentiment of this customer review: 'The product quality exceeded my expectations, but the delivery was delayed by a week. Customer service was helpful in resolving the issue.' Include emotion analysis and focus on product quality, delivery, and customer service aspects with 0.8 confidence threshold<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_sentiment\", \"arguments\": {\"text\": \"The product quality exceeded my expectations, but the delivery was delayed by a week. Customer service was helpful in resolving the issue.\", \"language\": \"en\", \"include_emotions\": true, \"confidence_threshold\": 0.8, \"aspects\": [\"product_quality\", \"delivery\", \"customer_service\"]}}", "rejected": "I'll analyze the sentiment of that customer review, focusing on the specific aspects you mentioned."}
{"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_document\",\n \"description\": \"Analyze document content for insights\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"document_text\": {\n \"type\": \"string\"\n },\n \"analysis_type\": {\n \"type\": \"string\"\n },\n \"focus_areas\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"required\": [\n \"document_text\",\n \"analysis_type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze this quarterly report: 'Q4 2024 showed remarkable growth with revenue increasing 25% year-over-year to $2.3 billion. Our flagship product line contributed 60% of total revenue, while emerging markets expanded by 40%. Key challenges include supply chain optimization and talent acquisition in our European operations.' Focus on financial performance and operational insights.<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_document\", \"arguments\": {\"document_text\": \"Q4 2024 showed remarkable growth with revenue increasing 25% year-over-year to $2.3 billion. Our flagship product line contributed 60% of total revenue, while emerging markets expanded by 40%. Key challenges include supply chain optimization and talent acquisition in our European operations.\", \"analysis_type\": \"comprehensive\", \"focus_areas\": [\"financial\", \"operational\"]}}", "rejected": "I'll analyze that quarterly report for you, focusing on the financial and operational aspects."}
{"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_email\",\n \"description\": \"Send an email 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 \"priority\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"to\",\n \"subject\",\n \"body\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSend an email to [email protected] about the project delay with subject 'Project Timeline Update' explaining that due to unexpected technical challenges and resource constraints, we need to extend the deadline by two weeks to ensure quality delivery.<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"send_email\", \"arguments\": {\"to\": \"[email protected]\", \"subject\": \"Project Timeline Update\", \"body\": \"Due to unexpected technical challenges and resource constraints, we need to extend the deadline by two weeks to ensure quality delivery.\", \"priority\": \"high\"}}", "rejected": "I'll send that email about the project delay to John 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\": \"search_database\",\n \"description\": \"Search database records\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"query\": {\n \"type\": \"string\"\n },\n \"filters\": {\n \"type\": \"object\"\n },\n \"limit\": {\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"query\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSearch for customers with names containing O'Brien or D'Angelo who registered after 2023-01-01 and have premium status, limit to 50 results<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"search_database\", \"arguments\": {\"query\": \"customers with names containing OBrien or DAngelo registered after 2023-01-01\", \"filters\": {\"status\": \"premium\", \"registration_date\": \">2023-01-01\"}, \"limit\": 50}}", "rejected": "I'll search the database for those premium customers with Irish names registered this year."}
{"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 with detailed parameters\",\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 \"enum\": [\n \"metric\",\n \"imperial\",\n \"kelvin\"\n ]\n },\n \"include_hourly\": {\n \"type\": \"boolean\"\n },\n \"alert_types\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"required\": [\n \"location\",\n \"days\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nGet a 5-day weather forecast for San Francisco, California in metric units with hourly breakdown and alerts for severe weather, precipitation, and temperature extremes<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"get_weather_forecast\", \"arguments\": {\"location\": \"San Francisco, California\", \"days\": 5, \"units\": \"metric\", \"include_hourly\": true, \"alert_types\": [\"severe_weather\", \"precipitation\", \"temperature_extremes\"]}}", "rejected": "I'll get that detailed 5-day forecast for San Francisco with hourly data and weather alerts."}
{"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 with detailed options\",\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 \"date\": {\n \"type\": \"string\"\n },\n \"include_fees\": {\n \"type\": \"boolean\"\n },\n \"precision\": {\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"amount\",\n \"from_currency\",\n \"to_currency\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nConvert 2,500.75 US dollars to Japanese yen using exchange rates from December 15th, 2024, include conversion fees, and show result with 2 decimal places precision<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"convert_currency\", \"arguments\": {\"amount\": 2500.75, \"from_currency\": \"USD\", \"to_currency\": \"JPY\", \"date\": \"2024-12-15\", \"include_fees\": true, \"precision\": 2}}", "rejected": "I'll convert that amount from USD to JPY using the specified date and including fees."}
{"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 with advanced options\",\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 \"confidence_threshold\": {\n \"type\": \"number\"\n },\n \"aspects\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"required\": [\n \"text\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze the sentiment of this customer review: 'The product quality exceeded my expectations, but the delivery was delayed by a week. Customer service was helpful in resolving the issue.' Include emotion analysis and focus on product quality, delivery, and customer service aspects with 0.8 confidence threshold<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_sentiment\", \"arguments\": {\"text\": \"The product quality exceeded my expectations, but the delivery was delayed by a week. Customer service was helpful in resolving the issue.\", \"language\": \"en\", \"include_emotions\": true, \"confidence_threshold\": 0.8, \"aspects\": [\"product_quality\", \"delivery\", \"customer_service\"]}}", "rejected": "I'll analyze the sentiment of that customer review, focusing on the specific aspects you mentioned."}
{"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_document\",\n \"description\": \"Analyze document content for insights\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"document_text\": {\n \"type\": \"string\"\n },\n \"analysis_type\": {\n \"type\": \"string\"\n },\n \"focus_areas\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"required\": [\n \"document_text\",\n \"analysis_type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze this quarterly report: 'Q4 2024 showed remarkable growth with revenue increasing 25% year-over-year to $2.3 billion. Our flagship product line contributed 60% of total revenue, while emerging markets expanded by 40%. Key challenges include supply chain optimization and talent acquisition in our European operations.' Focus on financial performance and operational insights.<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_document\", \"arguments\": {\"document_text\": \"Q4 2024 showed remarkable growth with revenue increasing 25% year-over-year to $2.3 billion. Our flagship product line contributed 60% of total revenue, while emerging markets expanded by 40%. Key challenges include supply chain optimization and talent acquisition in our European operations.\", \"analysis_type\": \"comprehensive\", \"focus_areas\": [\"financial\", \"operational\"]}}", "rejected": "I'll analyze that quarterly report for you, focusing on the financial and operational aspects."}
{"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_email\",\n \"description\": \"Send an email 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 \"priority\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"to\",\n \"subject\",\n \"body\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSend an email to [email protected] about the project delay with subject 'Project Timeline Update' explaining that due to unexpected technical challenges and resource constraints, we need to extend the deadline by two weeks to ensure quality delivery.<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"send_email\", \"arguments\": {\"to\": \"[email protected]\", \"subject\": \"Project Timeline Update\", \"body\": \"Due to unexpected technical challenges and resource constraints, we need to extend the deadline by two weeks to ensure quality delivery.\", \"priority\": \"high\"}}", "rejected": "I'll send that email about the project delay to John 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\": \"search_database\",\n \"description\": \"Search database records\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"query\": {\n \"type\": \"string\"\n },\n \"filters\": {\n \"type\": \"object\"\n },\n \"limit\": {\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"query\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSearch for customers with names containing O'Brien or D'Angelo who registered after 2023-01-01 and have premium status, limit to 50 results<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"search_database\", \"arguments\": {\"query\": \"customers with names containing OBrien or DAngelo registered after 2023-01-01\", \"filters\": {\"status\": \"premium\", \"registration_date\": \">2023-01-01\"}, \"limit\": 50}}", "rejected": "I'll search the database for those premium customers with Irish names registered this year."}
{"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 with detailed parameters\",\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 \"enum\": [\n \"metric\",\n \"imperial\",\n \"kelvin\"\n ]\n },\n \"include_hourly\": {\n \"type\": \"boolean\"\n },\n \"alert_types\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"required\": [\n \"location\",\n \"days\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nGet a 5-day weather forecast for San Francisco, California in metric units with hourly breakdown and alerts for severe weather, precipitation, and temperature extremes<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"get_weather_forecast\", \"arguments\": {\"location\": \"San Francisco, California\", \"days\": 5, \"units\": \"metric\", \"include_hourly\": true, \"alert_types\": [\"severe_weather\", \"precipitation\", \"temperature_extremes\"]}}", "rejected": "I'll get that detailed 5-day forecast for San Francisco with hourly data and weather alerts."}
{"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 with detailed options\",\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 \"date\": {\n \"type\": \"string\"\n },\n \"include_fees\": {\n \"type\": \"boolean\"\n },\n \"precision\": {\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"amount\",\n \"from_currency\",\n \"to_currency\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nConvert 2,500.75 US dollars to Japanese yen using exchange rates from December 15th, 2024, include conversion fees, and show result with 2 decimal places precision<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"convert_currency\", \"arguments\": {\"amount\": 2500.75, \"from_currency\": \"USD\", \"to_currency\": \"JPY\", \"date\": \"2024-12-15\", \"include_fees\": true, \"precision\": 2}}", "rejected": "I'll convert that amount from USD to JPY using the specified date and including fees."}
{"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 with advanced options\",\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 \"confidence_threshold\": {\n \"type\": \"number\"\n },\n \"aspects\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"required\": [\n \"text\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze the sentiment of this customer review: 'The product quality exceeded my expectations, but the delivery was delayed by a week. Customer service was helpful in resolving the issue.' Include emotion analysis and focus on product quality, delivery, and customer service aspects with 0.8 confidence threshold<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_sentiment\", \"arguments\": {\"text\": \"The product quality exceeded my expectations, but the delivery was delayed by a week. Customer service was helpful in resolving the issue.\", \"language\": \"en\", \"include_emotions\": true, \"confidence_threshold\": 0.8, \"aspects\": [\"product_quality\", \"delivery\", \"customer_service\"]}}", "rejected": "I'll analyze the sentiment of that customer review, focusing on the specific aspects you mentioned."}
{"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_document\",\n \"description\": \"Analyze document content for insights\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"document_text\": {\n \"type\": \"string\"\n },\n \"analysis_type\": {\n \"type\": \"string\"\n },\n \"focus_areas\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"required\": [\n \"document_text\",\n \"analysis_type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze this quarterly report: 'Q4 2024 showed remarkable growth with revenue increasing 25% year-over-year to $2.3 billion. Our flagship product line contributed 60% of total revenue, while emerging markets expanded by 40%. Key challenges include supply chain optimization and talent acquisition in our European operations.' Focus on financial performance and operational insights.<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_document\", \"arguments\": {\"document_text\": \"Q4 2024 showed remarkable growth with revenue increasing 25% year-over-year to $2.3 billion. Our flagship product line contributed 60% of total revenue, while emerging markets expanded by 40%. Key challenges include supply chain optimization and talent acquisition in our European operations.\", \"analysis_type\": \"comprehensive\", \"focus_areas\": [\"financial\", \"operational\"]}}", "rejected": "I'll analyze that quarterly report for you, focusing on the financial and operational aspects."}
{"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_email\",\n \"description\": \"Send an email 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 \"priority\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"to\",\n \"subject\",\n \"body\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSend an email to [email protected] about the project delay with subject 'Project Timeline Update' explaining that due to unexpected technical challenges and resource constraints, we need to extend the deadline by two weeks to ensure quality delivery.<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"send_email\", \"arguments\": {\"to\": \"[email protected]\", \"subject\": \"Project Timeline Update\", \"body\": \"Due to unexpected technical challenges and resource constraints, we need to extend the deadline by two weeks to ensure quality delivery.\", \"priority\": \"high\"}}", "rejected": "I'll send that email about the project delay to John 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\": \"search_database\",\n \"description\": \"Search database records\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"query\": {\n \"type\": \"string\"\n },\n \"filters\": {\n \"type\": \"object\"\n },\n \"limit\": {\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"query\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSearch for customers with names containing O'Brien or D'Angelo who registered after 2023-01-01 and have premium status, limit to 50 results<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"search_database\", \"arguments\": {\"query\": \"customers with names containing OBrien or DAngelo registered after 2023-01-01\", \"filters\": {\"status\": \"premium\", \"registration_date\": \">2023-01-01\"}, \"limit\": 50}}", "rejected": "I'll search the database for those premium customers with Irish names registered this year."}
{"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 with detailed parameters\",\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 \"enum\": [\n \"metric\",\n \"imperial\",\n \"kelvin\"\n ]\n },\n \"include_hourly\": {\n \"type\": \"boolean\"\n },\n \"alert_types\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"required\": [\n \"location\",\n \"days\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nGet a 5-day weather forecast for San Francisco, California in metric units with hourly breakdown and alerts for severe weather, precipitation, and temperature extremes<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"get_weather_forecast\", \"arguments\": {\"location\": \"San Francisco, California\", \"days\": 5, \"units\": \"metric\", \"include_hourly\": true, \"alert_types\": [\"severe_weather\", \"precipitation\", \"temperature_extremes\"]}}", "rejected": "I'll get that detailed 5-day forecast for San Francisco with hourly data and weather alerts."}
{"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 with detailed options\",\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 \"date\": {\n \"type\": \"string\"\n },\n \"include_fees\": {\n \"type\": \"boolean\"\n },\n \"precision\": {\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"amount\",\n \"from_currency\",\n \"to_currency\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nConvert 2,500.75 US dollars to Japanese yen using exchange rates from December 15th, 2024, include conversion fees, and show result with 2 decimal places precision<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"convert_currency\", \"arguments\": {\"amount\": 2500.75, \"from_currency\": \"USD\", \"to_currency\": \"JPY\", \"date\": \"2024-12-15\", \"include_fees\": true, \"precision\": 2}}", "rejected": "I'll convert that amount from USD to JPY using the specified date and including fees."}
{"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 with advanced options\",\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 \"confidence_threshold\": {\n \"type\": \"number\"\n },\n \"aspects\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"required\": [\n \"text\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze the sentiment of this customer review: 'The product quality exceeded my expectations, but the delivery was delayed by a week. Customer service was helpful in resolving the issue.' Include emotion analysis and focus on product quality, delivery, and customer service aspects with 0.8 confidence threshold<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_sentiment\", \"arguments\": {\"text\": \"The product quality exceeded my expectations, but the delivery was delayed by a week. Customer service was helpful in resolving the issue.\", \"language\": \"en\", \"include_emotions\": true, \"confidence_threshold\": 0.8, \"aspects\": [\"product_quality\", \"delivery\", \"customer_service\"]}}", "rejected": "I'll analyze the sentiment of that customer review, focusing on the specific aspects you mentioned."}
{"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_document\",\n \"description\": \"Analyze document content for insights\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"document_text\": {\n \"type\": \"string\"\n },\n \"analysis_type\": {\n \"type\": \"string\"\n },\n \"focus_areas\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"required\": [\n \"document_text\",\n \"analysis_type\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze this quarterly report: 'Q4 2024 showed remarkable growth with revenue increasing 25% year-over-year to $2.3 billion. Our flagship product line contributed 60% of total revenue, while emerging markets expanded by 40%. Key challenges include supply chain optimization and talent acquisition in our European operations.' Focus on financial performance and operational insights.<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_document\", \"arguments\": {\"document_text\": \"Q4 2024 showed remarkable growth with revenue increasing 25% year-over-year to $2.3 billion. Our flagship product line contributed 60% of total revenue, while emerging markets expanded by 40%. Key challenges include supply chain optimization and talent acquisition in our European operations.\", \"analysis_type\": \"comprehensive\", \"focus_areas\": [\"financial\", \"operational\"]}}", "rejected": "I'll analyze that quarterly report for you, focusing on the financial and operational aspects."}
{"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_email\",\n \"description\": \"Send an email 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 \"priority\": {\n \"type\": \"string\"\n }\n },\n \"required\": [\n \"to\",\n \"subject\",\n \"body\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSend an email to [email protected] about the project delay with subject 'Project Timeline Update' explaining that due to unexpected technical challenges and resource constraints, we need to extend the deadline by two weeks to ensure quality delivery.<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"send_email\", \"arguments\": {\"to\": \"[email protected]\", \"subject\": \"Project Timeline Update\", \"body\": \"Due to unexpected technical challenges and resource constraints, we need to extend the deadline by two weeks to ensure quality delivery.\", \"priority\": \"high\"}}", "rejected": "I'll send that email about the project delay to John 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\": \"search_database\",\n \"description\": \"Search database records\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"query\": {\n \"type\": \"string\"\n },\n \"filters\": {\n \"type\": \"object\"\n },\n \"limit\": {\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"query\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nSearch for customers with names containing O'Brien or D'Angelo who registered after 2023-01-01 and have premium status, limit to 50 results<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"search_database\", \"arguments\": {\"query\": \"customers with names containing OBrien or DAngelo registered after 2023-01-01\", \"filters\": {\"status\": \"premium\", \"registration_date\": \">2023-01-01\"}, \"limit\": 50}}", "rejected": "I'll search the database for those premium customers with Irish names registered this year."}
{"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 with detailed parameters\",\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 \"enum\": [\n \"metric\",\n \"imperial\",\n \"kelvin\"\n ]\n },\n \"include_hourly\": {\n \"type\": \"boolean\"\n },\n \"alert_types\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"required\": [\n \"location\",\n \"days\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nGet a 5-day weather forecast for San Francisco, California in metric units with hourly breakdown and alerts for severe weather, precipitation, and temperature extremes<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"get_weather_forecast\", \"arguments\": {\"location\": \"San Francisco, California\", \"days\": 5, \"units\": \"metric\", \"include_hourly\": true, \"alert_types\": [\"severe_weather\", \"precipitation\", \"temperature_extremes\"]}}", "rejected": "I'll get that detailed 5-day forecast for San Francisco with hourly data and weather alerts."}
{"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 with detailed options\",\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 \"date\": {\n \"type\": \"string\"\n },\n \"include_fees\": {\n \"type\": \"boolean\"\n },\n \"precision\": {\n \"type\": \"integer\"\n }\n },\n \"required\": [\n \"amount\",\n \"from_currency\",\n \"to_currency\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nConvert 2,500.75 US dollars to Japanese yen using exchange rates from December 15th, 2024, include conversion fees, and show result with 2 decimal places precision<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"convert_currency\", \"arguments\": {\"amount\": 2500.75, \"from_currency\": \"USD\", \"to_currency\": \"JPY\", \"date\": \"2024-12-15\", \"include_fees\": true, \"precision\": 2}}", "rejected": "I'll convert that amount from USD to JPY using the specified date and including fees."}
{"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 with advanced options\",\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 \"confidence_threshold\": {\n \"type\": \"number\"\n },\n \"aspects\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"required\": [\n \"text\"\n ]\n }\n}\n</schema>\n\n<|im_start|>user\nAnalyze the sentiment of this customer review: 'The product quality exceeded my expectations, but the delivery was delayed by a week. Customer service was helpful in resolving the issue.' Include emotion analysis and focus on product quality, delivery, and customer service aspects with 0.8 confidence threshold<|im_end|>\n<|im_start|>assistant\n", "chosen": "{\"name\": \"analyze_sentiment\", \"arguments\": {\"text\": \"The product quality exceeded my expectations, but the delivery was delayed by a week. Customer service was helpful in resolving the issue.\", \"language\": \"en\", \"include_emotions\": true, \"confidence_threshold\": 0.8, \"aspects\": [\"product_quality\", \"delivery\", \"customer_service\"]}}", "rejected": "I'll analyze the sentiment of that customer review, focusing on the specific aspects you mentioned."}