Skip to content

Use Cases

Explore common architectures and solutions built with Uni.

### [RAG & Knowledge Graphs](rag-knowledge-graph.md) Combine vector retrieval with graph traversal for smarter AI context.
### [Real-Time Fraud Detection](fraud-detection.md) High-velocity ingestion and low-latency pattern matching to stop fraud.
### [Recommendation Engines](recommendation-engine.md) Hybrid vector/graph scoring for personalized product and content discovery.
### [Supply Chain & BOM](supply-chain.md) Recursive analysis and document storage for complex component hierarchies.

Common Themes

Uni excels in scenarios that require:

  1. Multiple Data Models: You need Graph for relationships and Vector for similarity.
  2. Low Latency: You need to traverse deep relationships faster than a relational JOIN.
  3. Simplified Stack: You want to avoid maintaining a separate vector DB and graph DB.
  4. High Ingest: You need to handle real-time write streams without locking readers.