2026-04-10

Mission knowledge and vector search

Structured facts and embeddings sit in Postgres so new missions can find prior work.

See also: docs/knowledge-vector-search.md, docs/database-patterns.md

When you want a model to reuse past decisions, you need a store and a retrieval method. The combination of retrieval with generation is now textbook. See Lewis et al. (2020): retrieval-augmented generation for knowledge-intensive NLP.

We store knowledge units in Postgres and use the pgvector extension for similarity search. For the graph side of the algorithm, the standard reference is Malkov and Yashunin: HNSW (approximate nearest neighbors). That hierarchical navigable small world work is what makes large nearest-neighbor queries feasible at scale in many deployments.

So what

Vector search is not magic recall. It is an index and a distance function. If the buyer does not know what is stored and how similarity is defined, the feature is a demo.