Contextual search engine built on graph + vector retrieval.
ambala is a hybrid retrieval system that combines semantic similarity with graph traversal to produce context-aware results.
Instead of treating search as a flat nearest-neighbor problem, Ambala evaluates relevance within a structured graph.
This project focuses on:
- Combining vector similarity with graph traversal
- Supporting context-constrained queries
- Making retrieval explainable
Early stage. Core API routes and query layer are being implemented.
- HelixDB → graph + vector storage
- TanStack Start → API layer
- Vercel → deployment
- Gemini → embeddings
MIT