881d338b
 tangwang
评估框架
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
|
#!/usr/bin/env bash
# Search evaluation quick entrypoints. Run from any cwd; resolves repo root.
set -euo pipefail
ROOT="$(cd "$(dirname "$0")/../.." && pwd)"
cd "$ROOT"
PY="${ROOT}/.venv/bin/python"
TENANT_ID="${TENANT_ID:-163}"
QUERIES="${REPO_EVAL_QUERIES:-scripts/evaluation/queries/queries.txt}"
usage() {
echo "Usage: $0 batch|serve"
echo " batch — refresh labels + batch metrics (default: top_k=50, simple labeler, force-refresh)"
echo " serve — eval UI on http://127.0.0.1:6010/"
echo "Env: TENANT_ID (default 163), REPO_EVAL_QUERIES (default $QUERIES)"
}
case "${1:-}" in
batch)
exec "$PY" scripts/evaluation/build_annotation_set.py batch \
--tenant-id "$TENANT_ID" \
--queries-file "$QUERIES" \
--top-k 50 \
--language en \
--labeler-mode simple \
--force-refresh-labels
;;
serve)
exec "$PY" scripts/evaluation/serve_eval_web.py serve \
--tenant-id "$TENANT_ID" \
--queries-file "$QUERIES" \
--host 127.0.0.1 \
--port 6010
;;
*)
usage
exit 1
;;
esac
|