kyle/sift
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs(search): don't threshold JSON score as Tavily

Browse Source 
S1: skill recipe now says result score is merged rank. Also send
non-zero --min-score to the server (N1), sort include_domains (N2),
and note that search_queries counts each sub-query (N3).
This commit is contained in:
kyle
2026-09-29 15:33:57 -07:00
parent 8b26776cdd
commit 682b9b8044
5 changed files with 20 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skill/SKILL.md
+3 -2
View File
@@ -80,8 +80,9 @@ sift search "product launch" --include-domain openai.com --topic news --time-ran
**Recipe:** after `sift search --json`, do not `sift fetch` every URL. Drop hits below a
Tavily score you care about (`--min-score`, Tavily's 0–1 scale) or take top N, then
`sift batch submit`. `web_search` is only the fallback when sift is unreachable, and it
still hits `/v2/search` with no filters.
`sift batch submit`. The `score` field is sift's merged rank, not comparable across
sources: use `--min-score` for Tavily's threshold, or take the top N. `web_search` is
only the fallback when sift is unreachable, and it still hits `/v2/search` with no filters.
## Batch