Jev Search
Turn a plain-language request into source choices, search lanes, and visibly ranked links without generating an answer.
What Jev decides
Which query, sources, and time range fit the request, and how relevant each returned result is.
Jev Search asks Jev to interpret the request, choose search terms, sources, and time ranges, then score returned titles and snippets for relevance while Search1API performs the actual searches.
- Jev role
- Interpret the search request and rank retrieved candidates while external engines perform retrieval.
- Input
- The user request followed by result titles, snippets, source identities, and URLs from the selected search lanes.
- Output
- Typed search intent plus relevance scores used to merge and order result links.
- Decision frequency
- Once for search intent and again for result ranking on each search request.
- Fallback
- Try configured Jev providers only for eligible provider failures; retain successful search lanes and show warnings for failed sources.
How it works
Overview
Jev Search is a web search interface that keeps interpretation, retrieval, and ranking separate. Jev converts a natural-language request into typed search intent, the application launches supported search lanes concurrently, and Jev ranks the returned links using their titles and snippets.
Results remain links and excerpts rather than a generated synthesis. Users can override source and time filters, see relevance scores, and keep successful lanes when another engine fails. Provider fallback is limited to documented provider errors, while client and authentication errors are not retried.
- Language
- TypeScript
- License
- MIT
- Author
- Search1API
Sources
Related projects
pg-jev
Use Jev decisions directly inside PostgreSQL filters, rankings, and classifications.
What Jev decides
Whether a row matches, how strongly it matches, or which supplied label best describes it.
jev-spam-eval
A reproducible email-classification study comparing zero-shot Jev decisions with trained TF-IDF baselines.
What Jev decides
Whether an email is ham, spam, or phishing in the main experiment.
blink
Multiple Jev walkers navigate a repository tree one directory choice at a time.
What Jev decides
Which visible file or subdirectory should a walker inspect next.