Understand OpenAI training JSONL generation | Pixie CRM Help Centre Canonical: https://pixiecrm.com/help-centre/understand-openai-training-jsonl-generation Publisher: Pixie Technologies LLC Fine-tuning job lifecycle Understand OpenAI training JSONL generation Pixie CRM guidance. Follow the route for your workspace, check your role and enabled modules, and verify the result before moving on. Follow this guide to review the exact line-oriented format sent to the provider. Audience: CRM administrators and authorised staff; Permission: Technical administrator; Module v1.0.0; Where to goCode-backed reference → OpenAiProvider::formatTrainingData Before you start - Use an account with Technical administrator and confirm the intended record or setting before making a change. - Follow the exact route above. If the screen or action is absent, check module activation, ownership and permissions rather than using another person’s account. - Use controlled test data for configuration, integration, email, AI, payment, portal or automation changes before production-wide use. What this guide helps you do Review the exact line-oriented format sent to the provider. The instructions reflect the supplied module’s registered menus, controller actions, views, settings and code-backed validation flow. Follow these steps - Go to Code-backed reference → OpenAiProvider::formatTrainingData. - Select the relevant record, filter, report, model or configuration described below. - Use the displayed action or read the current values without altering unrelated data. - Compare the output with the code-backed rules and expected result in this guide. - Record or correct any mismatch before relying on the output in production. Fields and options ActionUnderstand OpenAI training JSONL generation Exact navigationCode-backed reference → OpenAiProvider::formatTrainingData Module version1.0.0 VerificationVerify the saved record, status, output or setting in the same workspace and review any linked activity, file or notification. Rules and limits - Every retained example becomes one JSON object per line. - Messages contain system, user and assistant roles. - Unicode is not escaped. Check it worked - The supported understand openai training jsonl generation flow completes without bypassing permission or validation checks. - The resulting record, setting, status, file, delivery event or external response is visible from the relevant workspace. - Unexpected validation, provider or linked-record errors are investigated before retrying. Security, privacy and operational checks - Restrict the API key and AI settings to authorised administrators. - Do not submit confidential, special-category or unnecessary personal data to the external AI provider. - Check generated text before using it in customer, staff, legal, financial or compliance communication. - Monitor provider billing and retention independently because this module has no built-in cost dashboard. Related guides Understand previous pcrm-model cleanup before a new job (https://pixiecrm.com/help-centre/understand-previous-pcrm-model-cleanup-before-a-new-job)Understand the temporary training-file path and cleanup (https://pixiecrm.com/help-centre/understand-the-temporary-training-file-path-and-cleanup)Start an OpenAI fine-tuning job (https://pixiecrm.com/help-centre/start-an-openai-fine-tuning-job)Open the OpenAI fine-tuning workspace (https://pixiecrm.com/help-centre/open-the-openai-fine-tuning-workspace)Review available fine-tuned OpenAI models (https://pixiecrm.com/help-centre/review-available-fine-tuned-openai-models)Browse all OpenAI Integration guides (https://pixiecrm.com/help-centre/category/openai-integration)Enterprise Integrations (https://pixiecrm.com/help-centre/category/enterprise-integrations)Data Privacy Security (https://pixiecrm.com/help-centre/category/data-privacy-security)Support Knowledge (https://pixiecrm.com/help-centre/category/support-knowledge)