Repo · Search & RAG

FastGate

Multilingual EN/UZ/RU RAG helpdesk where TypeSafe Jev is the System One decision layer before the LLM writes, with an independent benchmark.

Open github.com ↗

From the repository

Jev (TypeSafe AI) as a System One decision layer for a multilingual EN/UZ/RU RAG helpdesk, with an independent benchmark

ai-agentsevaluationjevllm-routingmultilingualragtypesafe-aiuzbek

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 108 search & rag projects →

Related projects