Verity retrieves, scores, and cites its evidence before it generates a sentence — and says so plainly when the evidence isn't there. Hybrid BM25 + vector retrieval, two-stage reranking, and a calibrated hallucination fallback, running on Kubernetes.
Documents are split with recursive chunking and tagged with source metadata, so every downstream answer can be traced back to where it came from.
Dense vector similarity is blended with BM25 keyword scoring, so exact terms and acronyms surface even when their embedding match is weak.
A second, query-aware pass reorders the top candidates — a check that's too slow to run on the whole corpus but cheap on twenty finalists.
Every chunk is labeled high, medium, or low confidence before it's allowed anywhere near the model.
The model is instructed to answer only from what was retrieved, and to cite which source backs each claim.
If the strongest match falls under threshold, Verity says the evidence isn't there — instead of guessing.
AWS EC2 running k3s, a lightweight Kubernetes distribution — rolling deploys, health probes, and self-healing pods.
Multi-stage Docker builds pushed to AWS ECR, keeping runtime images lean and reproducible.
ChromaDB for dense retrieval, paired with an in-memory BM25 index rebuilt per query for hybrid search.
Llama 3.1 8B served via Groq — sub-200ms generation on constrained, citation-aware prompts.
JWT sessions and Google OAuth, served over HTTPS via Let's Encrypt and Traefik ingress.
Prometheus metrics on every query path, plus a continuous evaluation suite that checks retrieval quality on each deploy.