awesome jevDIRECTORY스폰서Star on GitHub

JevDeepResearch

sunyasheng

GPT directs the research; Jev uses Choice and Noul to locate evidence across document regions concurrently, and code returns original passages for GPT to verify and continue. The released integration pairs Pi-Serini BM25 search with Jev batches of 20, 40, or 60 documents.

GitHub 저장소 ↗검색 및 필터
라이선스
Apache-2.0
GitHub Stars
1
소스 확인일
—

Jev가 판단하는 지점

Within each supplied source region, Choice selects source-line locations and Noul estimates whether the region addresses each evidence question. Code validates the answers, merges selected ranges, and returns verbatim evidence. Source loading and dependent research steps remain sequential; Jev region requests run concurrently.

프로젝트의 용도

Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.

검토 범위

공개 소스와 연동 논리를 확인했습니다.

소스 및 구현

같은 분류의 프로젝트