CalibratedDecisions.

Docs · Search & RAG

Cookbook: Line-by-Line Search

Semantic search over GitHub's Terms of Service: one request ranks all 218 lines with a Choice while a Noul checks whether the document contains an…

Open docs.typesafe.ai ↗

How builders describe it

Semantic search over GitHub's Terms of Service: one request ranks all 218 lines with a Choice while a Noul checks whether the document contains an answer at all, including when it should say no.
**My first Jev result!** Recreated the example "Line-by-line search" ( to process real Terms of Service (ToS) docs, and identifying the specific lines of the ToS that were related to user or vendor ownership of input/output content (AI Vendor ToS'), and then compared that to the same function being…

The decision Jev makes

Rank candidates against a query, or answer whether a passage is relevant.

Where it fits

Search pipelines retrieve too much. These projects use Jev as a reranker or relevance check after the first search, so only useful results reach the user or the model. All 61 search & rag projects →

Related projects