Vector Search Without a Vector Database: When Postgres Is Enough
When pgvector or even a plain in-memory scan is enough for semantic search, with a runnable demo of the filtered-search trap that returns too few rows and the pgvector 0.8 fix.
GPU cloud, LLM APIs, hosting and vector search: what they cost, how they fail, and how to keep them under control.
This hub covers the services behind AI features: LLM APIs, GPU cloud, hosting and vector search. The current posts are developer-focused: making API calls reliable, keeping the bill predictable, and choosing between Postgres and a dedicated vector database.
Prices change, so posts here point to the provider's own pricing page and say when it was read, instead of quoting numbers from memory.
When pgvector or even a plain in-memory scan is enough for semantic search, with a runnable demo of the filtered-search trap that returns too few rows and the pgvector 0.8 fix.
A tested Node.js module that adds a per-user daily token budget and a TTL response cache around any LLM call, plus the habits that keep an AI feature's bill predictable.
A short, tested Node.js module that adds a hard timeout, backoff with jitter, Retry-After handling and schema-validated JSON to any chat-style LLM API call.