Uses of Class
org.ek9lang.assist.QuestionRegistry
Packages that use QuestionRegistry
-
Uses of QuestionRegistry in org.ek9lang.assist
Methods in org.ek9lang.assist that return QuestionRegistryModifier and TypeMethodDescriptionstatic QuestionRegistryQuestionRegistry.createDefault()Create a registry from all .ek9 QA resource files.static QuestionRegistryQuestionRegistry.createDefaultWithProtocol()Create a combined registry with both language and protocol Q&A entries.static QuestionRegistryQuestionRegistry.createProtocol()Create a registry from protocol Q&A JSON resource files.Methods in org.ek9lang.assist with parameters of type QuestionRegistryModifier and TypeMethodDescriptionvoidTrainingDataDumper.dumpChatJsonl(QuestionRegistry registry, PrintStream out) Dump all Q&A pairs as chat-format JSONL (for models expecting conversation).voidTrainingDataDumper.dumpJsonl(QuestionRegistry registry, PrintStream out) Dump all Q&A pairs as instruction/response JSONL to the given output stream.voidTrainingDataDumper.dumpMlxChatJsonl(QuestionRegistry registry, PrintStream out) Dump all Q&A pairs as mlx_lm chat-format JSONL with system prompt and cross-reference resolution.voidTrainingDataDumper.dumpMlxChatJsonl(QuestionRegistry registry, PrintStream out, boolean includeThinking) Dump mlx_lm chat-format JSONL with optional Qwen3 thinking traces.QuestionMatcher.findBestMatches(String input, QuestionRegistry registry) Find the best matching questions using default max results (3).QuestionMatcher.findBestMatches(String input, QuestionRegistry registry, int maxResults) Find the best matching questions for the given input text.QuestionMatcher.findByCategory(String input, QuestionRegistry registry) Find a category whose name fuzzy-matches the input.QuestionMatcher.findScoredMatches(String input, QuestionRegistry registry, int maxResults) Find best matches with scores, so callers can distinguish best from also-relevant.(package private) StringTrainingDataDumper.resolveReferences(String text, QuestionRegistry registry) Resolve cross-references in text by replacing "See Q{id}" with the referenced Q&A's summary.intTrainingDataDumper.writeTrainingData(QuestionRegistry registry, Path outputDir) Write mlx_lm training data directory structure with stratified train/valid split.intTrainingDataDumper.writeTrainingData(QuestionRegistry registry, Path outputDir, boolean includeThinking) Write mlx_lm training data with optional Qwen3 thinking traces.