Jev in production › Search, ranking and matching
llama-index-jev
Drop-in LlamaIndex reranker and router scores or chooses via Jev's typed Score and Choice outputs, positioned as cheaper than LLM-as-judge rerankers.
The source publishes no measured number.
- Use
- Search, ranking and matching
- Industry
- AI infrastructure
- Form
- Open-source tool
- Stage
- Announced
- Plugs into
- LlamaIndex
- Listed
- 2026-09-25
- Found via
- github
- Repository
- WiktorB2004/llama-index-jev
- Stars
- 8
- Forks
- 1
- Last push
- 2026-09-25
- Language
- Python
- License
- MIT
The README opens with
Drop-in LlamaIndex reranker and router powered by TypeSafe Jev: typed Score / Choice answers, cheap compared to LLM-as-judge — not a Cohere or FlagEmbedding cross-encoder.
Independent community project. Not affiliated with TypeSafe or LlamaIndex.
Docs: wiktorb2004.github.io/llama-index-jev. Paste-and-run walkthroughs (OpenRouter, mock embeddings / MockLLM so you do not need an OpenAI key): examples/.
Package docs: JevRerank · JevSingleSelector / JevMultiSelector.
Badge
For the project's own README, linking back here:
Also used for search, ranking and matching
- jegrep $0.01–0.03
- pi-web-search ~2k free uses/month
- Jev Graph Search 81.8%
- Jev RAG 0.444
- oko (bartlomein) 13–44% fewer tokens
- jevsearch 83%
- GStars 1500
- askgrep $0.0049