verifywise-ai/VerifyWise LLM Evaluation

Run LLM evaluations against a VerifyWise instance and gate CI on quality thresholds. Supports chatbot, RAG, and agent use cases.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
api_urlVerifyWise instance URLyes
project_idProject IDyes
dataset_idDataset ID to evaluate againstyes
metricsComma-separated metric names (e.g. answer_relevancy,bias,toxicity)yes
model_nameModel to evaluate (e.g. gpt-4o-mini, claude-3.5-sonnet)yes
model_providerProvider: openai | anthropic | google | mistral | xai | self-hostedyes
judge_modelJudge LLM for metric scoringnogpt-4o
judge_providerJudge LLM providernoopenai
thresholdPass/fail threshold (0.0–1.0)no0.7
timeout_minutesMax wait time in minutesno30
poll_interval_secondsSeconds between status pollsno15
experiment_nameCustom experiment name (auto-generated if empty)no""
fail_on_thresholdFail the step when thresholds are not metnotrue
post_pr_commentPost results as a comment on the pull requestnotrue
vw_api_tokenVerifyWise API tokenyes
llm_api_keyAPI key for the model being evaluatedyes
judge_api_keyAPI key for the judge LLM (defaults to llm_api_key if not set)no""
namedescription
passedWhether all metrics passed (true/false)
results_pathPath to results JSON
summary_pathPath to Markdown summary
experiment_idID of the created experiment