Skip to main content
Vrin is a retrieval-time reasoning layer. It sits between your data and your AI, curating the right context before the LLM ever sees it.

​
The Core Insight

Pre-inference context gathering is not the same as LLM reasoning. LLMs reason well over good context, but they can’t gather it. Standard RAG retrieves by semantic similarity, which works for simple lookups. But real questions require connecting facts across documents, timelines, and domains. Transformers can’t do this natively. Vector search doesn’t even try.

​
The 3-Stage Pipeline

1

Ingest

Documents are chunked, embedded, and analyzed. Vrin extracts structured facts (entities, relationships, temporal markers) and builds a knowledge graph alongside the vector index. Every fact is linked to its source with confidence scores.
vrin insert "ACME reported $50M revenue in Q4..." --title "ACME Q4"
vrin upload ./report.pdf
2

Retrieve & Reason

When you query, Vrin doesn’t just find similar text. It:
  1. Decomposes complex queries into sub-questions
  2. Traverses the knowledge graph to find multi-hop connections
  3. Searches the vector index for supporting text chunks
  4. Fuses results from both graph and vector retrieval
  5. Scores and filters to deliver only relevant, high-confidence context
This is the reasoning layer that standard RAG lacks.
3

Generate

The curated context (structured facts + relevant chunks) is passed to the LLM. Because the hard work of gathering and connecting information is already done, the LLM can focus on what it’s good at: synthesizing a clear, well-reasoned answer.

​
Why Not Just RAG?

Standard vector RAG has three fundamental limits:
ProblemStandard RAGVrin
Multi-hop reasoningRetrieves chunks independently, can’t connect facts across documentsGraph traversal follows entity relationships across any number of hops
Temporal awarenessNo concept of time, treats all facts equallyTracks valid_from / valid_to on every fact
Fact provenanceReturns text chunks, no structureEvery answer traces back to: source document, extracted fact, reasoning step

​
What Gets Built During Ingestion

When you insert a document, Vrin creates:
  • Text chunks in a vector index (for semantic similarity search)
  • Entities in the knowledge graph (people, companies, concepts, events)
  • Relationships between entities (typed, directional edges)
  • Temporal markers on facts that change over time
  • Confidence scores per fact (model, timestamp, extraction confidence)
The knowledge graph and vector index work together. The graph finds the right connections. The vector index provides the supporting evidence.

See it in action

Insert your first document and query it in under 2 minutes.