CalibratedDecisions.

Repo · Search & RAG

Tessmora (MMA-RAG)

Tessmora (Chinese docs): self-hosted omni-modal agentic retrieval platform for documents, images, audio and video, with opt-in TypeSafe Jev semantic…

Open github.com ↗

From the repository

Tessmora — self-hosted multimodal RAG with an autonomous research agent. Search documents, images, audio, and video with traceable citations.

agentic-ragai-agentsdocument-understandinghybrid-searchknowledge-basemultimodalqdrantragrerankingself-hostedsemantic-searchvector-search

How builders describe it

Tessmora (Chinese docs): self-hosted omni-modal agentic retrieval platform for documents, images, audio and video, with opt-in TypeSafe Jev semantic judgment for a simple-question intent fast path, choice reranking and citation-support diagnostics.

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