Jev candidate ranker
jev_rankRank files, symbols, errors, or skills against a plain-language query and get only the top hit that genuinely answers. No embeddings or repo indexing; lists over 250 are chunked and re-ranked.
Instructions
Rank files, symbols, errors, or skills against a plain-language query. No embeddings. One Choice over candidate ids plus a Noul that the top hit actually answers the query (so a forced winner cannot masquerade as a match). Max 250 candidates per Jev call; larger lists are chunked then re-ranked. Pass candidates in; this server does not index the repo.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"query": "<query>",
"candidates": "<candidates>"
},
"name": "jev_rank"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | ||
| query | Yes | What you are looking for, in natural language | |
| top_k | No | How many ranked candidates to return. Default 5. | |
| candidates | Yes | Candidates to rank. More than 250 are chunked, then the winners are re-ranked. |