feat: automated cron jobs for BM25 reindex and vector embeddings#2
Merged
Merged
Conversation
Adds: - .github/workflows/wiki-index.yml — CI validation of BM25 build on wiki/** changes - tools/cron/daily-ingest-and-index.sh — daily pipeline: ingest + BM25 + optional embed - tools/cron/wiki-reindex.sh — fast BM25 rebuild after wiki edits - tools/cron/README.md — generic cron setup docs with RAM guidance - .agents/skills/cron-setup/SKILL.md — Hermes-specific cronjob instructions Design decisions: - BM25 reindex is cheap and runs on any machine; embeddings are opt-in. - Default model stays all-MiniLM-L6-v2 (~90 MB) for 2 GB RAM safety. - Scripts are self-contained and work with crontab, systemd, or Hermes. - GitHub Action validates index health on PRs but does not commit artifacts.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What's added
.github/workflows/wiki-index.yml— CI validation of BM25 build onwiki/**changes. Uploads the index as an artifact.tools/cron/daily-ingest-and-index.sh— daily pipeline: optional ingest + BM25 + optional vector embed. Self-contained, works with crontab/systemd/Hermes.tools/cron/wiki-reindex.sh— fast BM25 rebuild after wiki edits. Node-only, safe on any machine.tools/cron/README.md— generic cron setup docs with RAM guidance and model size table..agents/skills/cron-setup/SKILL.md— Hermes-specific cronjob instructions (daily + wiki-watch patterns).Design decisions
all-MiniLM-L6-v2(~90 MB) for 2 GB RAM safety. Larger models and Gemma-based variants are documented as needing 4+ GB.Exit codes