Retrieval
Everything we have written under retrieval.
7posts4this month
Oct 19, 2026 · 6 min readWhat an embedding is, and why two sentences with no shared words land togetherAn embedding turns a sentence into a position. Everything an assistant does next is geometry: what sits near the question gets read, and what sits far away never arrives.
Oct 16, 2026 · 6 min readWhat a vector database does, and why we still run PostgresEvery RAG tutorial opens by telling you to pick a vector database. Here is what one actually does, what Postgres already does, and the three conditions that make a separate system worth running.
Oct 8, 2026 · 6 min readSemantic search vs keyword searchOne finds documents that share your words. The other finds documents that share your meaning. Both fail in ways the other does not, and knowing which is which decides what your search gets wrong.
Oct 7, 2026 · 6 min readStop your assistant mixing up product versionsTwo manuals that differ in one step are nearly identical to a retrieval system. It will find both, rank them the same, and blend them into an instruction that is right for neither device.
Sep 18, 2026 · 6 min readFine-tuning vs RAG: which one do you actually need?Fine-tuning changes how a model writes. Retrieval changes what it can read. For company knowledge that difference settles the question almost every time.
Sep 10, 2026 · 7 min readWhat is RAG? Retrieval-augmented generation explainedA language model does not know your refund policy. RAG is how it reads your documents at the moment of the question, and answers from what it read.
Sep 2, 2026 · 5 min readHow to fix bad retrieval scores by changing chunk sizeWhen your assistant cites the wrong page or misses details, the problem is usually chunk size, not the model. Here's how to read scores and pick a better one.
