docs(search): describe the search and fetch pipeline #14

Merged
inference-bot merged 1 commits from ed/docs:search-pipeline into main 2026-11-19 22:36:44 +00:00
Contributor

Explain the two stages: SearXNG queries DuckDuckGo and Brave, then Keenable fetches the top result pages. Name the SearXNG instance URL and disclose Keenable's logging, retention, processing location, and training use. Correct the claim that web search has no external dependency.

Explain the two stages: SearXNG queries DuckDuckGo and Brave, then Keenable fetches the top result pages. Name the SearXNG instance URL and disclose Keenable's logging, retention, processing location, and training use. Correct the claim that web search has no external dependency.
ed added 1 commit 2026-11-19 19:32:00 +00:00
Explain the two stages: SearXNG queries DuckDuckGo and Brave, then Keenable fetches the top result pages. Name the SearXNG instance URL and disclose Keenable's logging, retention, processing location, and training use. Correct the claim that web search has no external dependency.
ed force-pushed search-pipeline from dad815e6c5 to b0edbf2c33 2026-11-19 19:32:00 +00:00 Compare
inference-bot left a comment
Owner

Reviewed: claims verified against Keenable privacy/data docs; SearXNG URL and keyless path match the live config.

Reviewed: claims verified against Keenable privacy/data docs; SearXNG URL and keyless path match the live config.
inference-bot merged commit 1f23ea1d78 into main 2026-11-19 22:36:44 +00:00
Owner

@ed — following up on this merge: we replaced the Keenable page fetch with a co-op-owned service (fetch.inference.coop, repo co-op/fetcher). It runs on our Cloudron, keeps no copy of URLs or page text, has no access log, and refuses internal addresses. The member-facing text you added has been updated in #16 (privacy §5/§7/§9, getting-started, infrastructure), and I requested you as reviewer there so the wording gets your check. The search engines (DuckDuckGo, Brave) still receive queries; only the page fetch is now ours.

@ed — following up on this merge: we replaced the Keenable page fetch with a co-op-owned service (`fetch.inference.coop`, repo `co-op/fetcher`). It runs on our Cloudron, keeps no copy of URLs or page text, has no access log, and refuses internal addresses. The member-facing text you added has been updated in **#16** (privacy §5/§7/§9, getting-started, infrastructure), and I requested you as reviewer there so the wording gets your check. The search engines (DuckDuckGo, Brave) still receive queries; only the page fetch is now ours.
Sign in to join this conversation.
No Reviewers
No labels
2 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: co-op/docs#14