One embedding model, four different maximum lengths
The most downloaded sentence-embedding model ships four config files declaring 128, 256, 512 and 512 as its maximum inpu...
Guides & How-tos · Worked examples · Real numbers
Step-by-step how-tos, head-to-head comparisons and honest roundups — every guide worked through with current figures, then backed by a RECATOOLS calculator or AI-directory entry so you can act on it.
The most downloaded sentence-embedding model ships four config files declaring 128, 256, 512 and 512 as its maximum inpu...
OpenAI charges 2x input and 1.5x output on the full request once a prompt passes 272,000 tokens, so the 272,001st token...
All three major providers price a cache read at a tenth of normal input, so caching looks like the same deal everywhere....
A long session is cheap. An interrupted one is not. Every AI coding agent re-reads your whole conversation at a tenth of...
Four switches with almost the same name, doing four different things. Three are on by default. One also sets your retent...
Twenty questions with known answers, run over 205 real documents. Prefixing titles to chunks raised hit@1 from 14 to 17...
Seventy-eight lines with no dependencies join a local embedding model, a vector store and MCP. The interesting part is n...
A 46 MB model, running on your laptop, turns text into positions in space. The demonstration: a query whose only content...
Every retrieval tutorial says "point it at your vector database" and none of them tells you how to run one. One containe...
Write a prompt in Thai and it costs more than the same prompt in English — not because the model charges you differently...
The registry names a licence for only 15.5% of nodes and puts a bare filename in the field for 59.1% more. We opened 60...
ComfyUI Manager offers to install the missing nodes, you click, and a log scrolls past too fast to read. What runs in th...