AshwinUgale

AshwinUgale/goldset

Turn real traffic/traces into a versioned, deduped, coverage-tracked LLM regression suite — a curation accelerator with a human-confirmed golden gate.

1 stars 0 forks 1 watchers Python MIT License
ai clustering dataset-curation drift-detection evaluation golden-dataset llm llm-eval llmops mlops pii python regression-testing test-generation
View on GitHub Website
6 Open Issues Need Help Last updated: Aug 8, 2026

Open Issues Need Help

View All on GitHub
Optionally emit promptfoo assertions for structural expectations (tool_called / final_state) about 2 hours ago
enhancement help wanted
AshwinUgale/goldset
1

Turn real traffic/traces into a versioned, deduped, coverage-tracked LLM regression suite — a curation accelerator with a human-confirmed golden gate.

Python
#ai#clustering#dataset-curation#drift-detection#evaluation#golden-dataset#llm#llm-eval#llmops#mlops#pii#python#regression-testing#test-generation
Add machine-readable `--json` output to reporting commands about 2 hours ago
enhancement help wanted
AshwinUgale/goldset
1

Turn real traffic/traces into a versioned, deduped, coverage-tracked LLM regression suite — a curation accelerator with a human-confirmed golden gate.

Python
#ai#clustering#dataset-curation#drift-detection#evaluation#golden-dataset#llm#llm-eval#llmops#mlops#pii#python#regression-testing#test-generation
Provide a reference scenario runner in `examples/` about 2 hours ago
enhancement help wanted
AshwinUgale/goldset
1

Turn real traffic/traces into a versioned, deduped, coverage-tracked LLM regression suite — a curation accelerator with a human-confirmed golden gate.

Python
#ai#clustering#dataset-curation#drift-detection#evaluation#golden-dataset#llm#llm-eval#llmops#mlops#pii#python#regression-testing#test-generation
Document the scenario runner transcript format + add a worked example about 2 hours ago
documentation good first issue
AshwinUgale/goldset
1

Turn real traffic/traces into a versioned, deduped, coverage-tracked LLM regression suite — a curation accelerator with a human-confirmed golden gate.

Python
#ai#clustering#dataset-curation#drift-detection#evaluation#golden-dataset#llm#llm-eval#llmops#mlops#pii#python#regression-testing#test-generation
Expand the built-in PII detector set (AWS key, JWT, IBAN, MAC address) about 2 hours ago
enhancement good first issue
AshwinUgale/goldset
1

Turn real traffic/traces into a versioned, deduped, coverage-tracked LLM regression suite — a curation accelerator with a human-confirmed golden gate.

Python
#ai#clustering#dataset-curation#drift-detection#evaluation#golden-dataset#llm#llm-eval#llmops#mlops#pii#python#regression-testing#test-generation
Add a plain-JSON export format to `goldset export` (`--format json`) about 2 hours ago
enhancement good first issue
AshwinUgale/goldset
1

Turn real traffic/traces into a versioned, deduped, coverage-tracked LLM regression suite — a curation accelerator with a human-confirmed golden gate.

Python
#ai#clustering#dataset-curation#drift-detection#evaluation#golden-dataset#llm#llm-eval#llmops#mlops#pii#python#regression-testing#test-generation