Privacy choices
This site may send the owner a minimal page-visit notice with page, browser, device type, and resolution. If you accept analytics, it can also remember an anonymous visit/session ID and collect richer engagement signals.
Read the privacy noticeUsed in: alex-os-project
Used with pgvector for semantic content retrieval, with a keyword-scoring fallback.
Used with pgvector for semantic content retrieval, with a keyword-scoring fallback.
Alex OS's retrieval layer when Postgres/pgvector is configured.
Alex OS's retrieval layer when Postgres/pgvector is configured.
Vector search powers Alex OS's retrieval layer, using pgvector for semantic lookup with a keyword-scoring fallback when needed.
Vector Search
Alex uses vector search via pgvector to retrieve semantically relevant content in Alex OS. When pgvector isn't configured, a keyword-scoring fallback keeps retrieval functional. Experience level: working knowledge, actively in use.
Where it's applied
This is the retrieval layer inside Alex OS — the FastAPI service that sits between the CMS and the public site. Queries are embedded and matched against stored vectors in Postgres, so responses are grounded in actual content rather than generated from scratch.
How this fits together
Vector search here isn't standalone — it's one component of a broader RAG setup. The pgvector integration handles semantic retrieval; the fallback handles edge cases. If you're curious about the full retrieval and reasoning pipeline, the Alex OS project and the RAG & Knowledge Retrieval expertise page cover the wider picture.