LlamaIndex Jev
unofficial LlamaIndex adapter where Jev `Score`s each retrieved passage and `Choice`/`Noul` selects the query engine, with nfcorpus nDCG@5 0.340→0.396 at about $0.0003/query.
何を判断するか
CHOICE
Picks one option from a fixed set
SCORE
Rates against ordered levels
NOUL
Answers a yes / no question
Inferred from this project's own one-line summary in the community list — it reads as a CHOICE + SCORE decision. Read the source to confirm.
CHOICE 呼び出しの形
この質問型の一般的な骨格であって、このプロジェクトの実際のコードではない。
from typesafe import TypeSafe
ts = TypeSafe() # reads TYPESAFE_API_KEY
result = ts.evaluate(
state=page_state,
questions={
"next_action": {
"type": "choice",
"options": ["click", "scroll", "type", "done"],
"instructions": "What should the agent do next?",
}
},
)
action = result["next_action"] # the chosen option
confidence = result["next_action_confidence"]インフラ / SDK / 連携の他のプロジェクト
jev-mcp (jkudish)proof-of-concept MCP server that puts Jev claim verification, content screening, and candidate ranking behind standard MCP tools.eveVercel's eve engine ships Jev as the default evaluation model (`typesafe-ai/jev`) in its experimental evaluate path.AI CLIVercel Labs CLI that can run Jev as the evaluation model for its `evaluate` command.jev-mcp (blakestone-x)MCP server exposing Jev classify, score, check, match, and screen as tools for any agent, with confidence on every answer.