#ai 6 articles

• A library with NoCrawl returns nothing from Search — and silently blinds anything built on Searchgotchas / searchExcluded containers return 0 with HTTP 200 and no log, so Search-backed AI never sees them; provisioning that excludes data lists must not inherit that onto content libraries; reindex can't be forced over REST…
• A trailing-whitespace regex freezes the page when it parses AI outputgotchas / spfx/\s+$/ and lazy (.+?)\s*$ are quadratic on a line with a long run of spaces that does not end the line; text from an AI model or a foreign document is untrusted input, so trim with trimEnd() and anchor captures on a…
• Graph Search returns 0 hits — you passed the user's question as the queryStringgotchas / searchTranslate question→keywords; "what's new" is a listing (* + default date sort, custom sort = 400); per-entity KQL only as documented
• RAG finds nothing that SharePoint Search finds — the reasoning model spent the whole token cap thinkinggotchas / searchGPT-5/o-series count hidden reasoning in max_completion_tokens; a small cap on the query-generator call returns empty text (HTTP 200), and a raw-question fallback ANDs every word in KQL
• SharePoint Search cannot see text inside images — and what that does to RAGgotchas / searchThe crawler indexes the text layer only, so a value that exists only in an embedded flyer or a scan can never be found by keyword: a search-then-read pipeline is in a closed loop, the LLM re-ranker drops such documents…
• SharePoint Search finds nothing for a question in an inflected language — add prefix-wildcard stems, and never turn zero hits into "latest documents"gotchas / searchKQL is implicit AND and matches exact word forms, so Czech inflected forms miss; add a stem* variant in code, relax before giving up, and never serve a date-sorted inventory as sources for a specific question