Jev in production › Search, ranking and matching
Milvus Model (Zilliz)
pymilvus's milvus-model library ships JevRerankFunction, which sends every candidate document to TypeSafe's API as a noul relevance question in one request and returns the top results sorted by probability.
- Use
- Search, ranking and matching
- Industry
- AI infrastructure
- Form
- Open-source tool
- Stage
- In production
- Plugs into
- Milvus
- Listed
- 2026-09-23
- Found via
- github
- Repository
- milvus-io/milvus-model
- Stars
- 61
- Forks
- 30
- Last push
- 2026-09-23
- Language
- Python
- License
- Apache-2.0
The README opens with
The milvus-model library provides the integration with common embedding and reranker models for Milvus, a high performance open-source vector database built for AI applications. milvus-model lib is included as a dependency in pymilvus, the Python SDK of Milvus.
milvus-model supports embedding and reranker models from service providers like OpenAI, Voyage AI, Cohere, Jina AI, and TypeSafe (Jev), and open-source models through SentenceTransformers or Hugging Face Text Embeddings Inference (TEI) .
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