Docs / source reviewed
jevcrawl
Choose crawl links by goal and return relevant source passages
How this project uses Jev
- Input
- The goal, page title and URL, segmented text, link labels, and passages already retained
- Jev decides
- Noul questions score passage relevance, answer-page and hub links, and whether collected passages cover the goal
- Code executes
- Code prioritizes traversal and returns verbatim text with URLs and character offsets; three consecutive decision failures trigger breadth-first traversal with unscored passages marked uncertain
Evidence and limitations
Apache-2.0 license and pinned 0.2.0 request/fallback code reviewed; not run. Defaults to jev-1.13.0. Goals, page text and links go to TypeSafe. Author benchmarks use small samples and were not reproduced. Verbatim output does not establish complete evidence, correct scores or immunity to prompt injection.
This project has not been run independently here. Author-reported results are not independently verified results.
Original sources
- https://github.com/RayenMlayeh/jevcrawl/blob/7d1f91609221ae221926dd952cd4aa76263924ec/LICENSE ↗
- https://github.com/RayenMlayeh/jevcrawl/blob/7d1f91609221ae221926dd952cd4aa76263924ec/jevcrawl/decide/client.py ↗
- https://github.com/RayenMlayeh/jevcrawl/blob/7d1f91609221ae221926dd952cd4aa76263924ec/README.md ↗
- https://github.com/RayenMlayeh/jevcrawl/blob/7d1f91609221ae221926dd952cd4aa76263924ec/jevcrawl/decide/decider.py ↗
- https://github.com/RayenMlayeh/jevcrawl/blob/7d1f91609221ae221926dd952cd4aa76263924ec/jevcrawl/decide/questions.py ↗
- https://github.com/RayenMlayeh/jevcrawl/blob/7d1f91609221ae221926dd952cd4aa76263924ec/jevcrawl/config.py ↗
- https://github.com/RayenMlayeh/jevcrawl/blob/7d1f91609221ae221926dd952cd4aa76263924ec/jevcrawl/crawl/loop.py ↗