Topic · 9 stories
9 stories tagged search on AI Tamer, newest first.
The original and multilingual E5 embedding models were trained with a "query:" or "passage:" prefix on every input. Leave the prefixes off, or store documents with the query prefix, and retrieval quietly gets worse with no error anywhere.
DeepSeek's API guide documents Search and Fetch at 5 requests a second. The Chinese pages price each at 5 yuan per 1,000 successes; the English pages say $0.75.
XERJ published v1.0.0-rc.96 on 16 October, a Rust engine for local search. Corpus Hub is not enabled in this build.
Cloudflare's 15 October post says a July pilot on about 1% of its network fed discovery signals to OpenAI's search crawler. The page count is Cloudflare's.
Cross-encoders score a query and a document in one pass, which makes them more accurate than embedding search and too slow for a whole corpus. Use them to rerank the top hits.
The @bot account said on 7 October that Grok Bot can search, read, and monitor X. Official @grok replies say that read path needs no X connector and uses no X API credits.
A username can have equivalent encodings or resemble another name made from different characters. This explains what Unicode normalization and confusable detection each solve.
An error identifier deserves a literal search path. SQLite FTS5 can find token and prefix matches, rank the results, and leave strict spelling checks to the stored field.
turbopuffer made native embedding generally available (Sep 29, 2026): embed on write, on query, or keep BYOE. Systems overlap with index metadata fetch; Linear/Readwise beta color is vendor-stated.
