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.
- License
- Apache-2.0
- GitHub Stars
- 1
- Source reviewed
- —
Where Jev makes a decision
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.
What this project offers
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
Review scope
Author and repository text is preserved where clear; missing languages are enriched automatically. Checks establish source-level Jev integration, not runtime, safety, or performance validation.
Sources and implementation
Related projects
pg-jev
realZachi · Data & Search
Adds natural-language filtering, classification, and ranking of rows to PostgreSQL queries.
jev-search
superagents-lab · Data & Search
Searches the web with Jev choosing sources and time ranges, then ranking returned links.
llama-index-jev
WiktorB2004 · Data & Search
Provides Jev rerankers and routers for LlamaIndex to score retrieved passages or select query tools.
jevsome-projects
ozers · Data & Search
A Jev project directory and discovery pipeline that stores integration evidence and can use Jev for classification.