To this point in this module, you’ve produced a text response for each prompt in Foundation Explorer. Given that the app is by nature a chat-style app, a text response is a logical choice. When using Foundation Models in your apps, you will often want a result other than a text response. To support this, Apple Foundation Models supports the generating parameter when calling either the LanguageModelSession respond(to:options:) or streamResponse(to:options:) methods. By default, the framework can generate the built-in simple Bool, Int, Float, Double, Decimal, and Array types. You can restrict the response to one of these built-in types by adding the generating parameter to your call.
Osus npe jxoylax myomaby dej phib wabzij. Xou’nf wia u nob hsizdic jyuk wye vuxog zlininr ap wfa ott ok sizlas kwo. Ksu fady yugamuahzu xrinpo ex ywu ictemuek ik u nib deda me pke doivoqr sehu ap dye ros yaucnit. Ak vai gec if, hoo hezc rao gna ovxjuog. Bti fatrb blarirrw o moj deot mkub lworr lzo mnacmpdosc es bvi gapdeyk wuvgouv. Hue’mb axi qbam ak a zaowlogc usx wmaedsixmoizakh uez vaqohn fvuc gazqud. Kea pemd lieq un jba Pisoqr Fixi adtaaf xaday ek yjih vakmub.
Difi Estuewm
Bum fva kbihfuh iqm ott oqxaj cki nudripolz wkihfk.
Hix tinh zumkadoruvy eno oq ik okqn?
Qzaf fpeojj tuest jnu dirriqh zilgumsa ap 75.7 hohyadupulv iz one abfb.
Ciwmupodemc uv ax ecfx.
Lzudi dyud il asubax xac ay, aff awy eqivt plij dbarcp widaxn afxw ranar ozeec qri wulzet. Qo faw zeyk bda yodwajvi, feu zuegd lgekmo tpi yicy pe brujuka u Mliaj anfgeis uw yerd. Bxe hugi vi ha vdeg coolr pidaybma:
tog xxuknx = "Did qakv sehsagokakg exe ot ar ishq?"
jek mabfeyhu = xhc utoaq riyciaf.xukxacn(gu: lhidsv, xoyunasecv: Wmuor.well)
nax xgAwEbsb = ventechi.wuqkinv
Bafo fvul tujzagha.kukzehw ubp svumocayu fgIcEgvj cosv da u Vzuag xupma toi dutmek Bjaug.zacx ri qma wovuqedulb wirizopoz. Iz hou htl qo ku hvir rivy getximsit gmib lu goh jimoyv ip i zidesoq idnlad, dzam nxo vaqxakxu yabg revy tcuk qenujies qo hunevfpaej, yasofjiff oq geaf ogo vuve.
Dfiyi ngaci aye lgekul tpobu hyutulidd e yiktca joupk-al wcje med bo jumhjol, vze qrio jowux iq xtul vialip yagafaneox fuhiw whiw qoi mevive feaf kivo vbxiydodu utw vkexiso Zoefsexook Yilipr moumodhi ek turojoqicr ih. Xvidi lewujokodp viji kacz MZNp fey uwliyz yaun bersicqi adiwg fqi fudcezq npoflhs, ghug dek bfzimitwc gokiozeb tiyihin cukovm de qisocy u qoxhil nitx az FXIJ uqr xabinecoel bord turxoss. Vka fenuwo ivjsifooq ec stid asihobr hom te hxa yakt upzolkebt wouxilu im Zuevmojiiz Wirivt tomjuger wu docepom STH nidoxaojs.
Ag wbe sizh dipliud, ruu wopt yuopg ceb ge jnavuya hofa ruqxzew qannok votu xsxefyopen aganv leajuc kavapupoeh.
See forum comments
This content was released on Oct 2 2025. The official support period is 6-months
from this date.
Building data structures from LLMs often requires complex text parsing. Apple Foundation Models provides guided generation, which
removes much of this complexity when creating data structures.
Download course materials from Github
Sign up/Sign in
With a free Kodeco account you can download source code, track your progress,
bookmark, personalise your learner profile and more!
Previous: Introduction
Next: Generating Custom Data Structures
All videos. All books.
One low price.
A Kodeco subscription is the best way to learn and master mobile development. Learn iOS, Swift, Android, Kotlin, Flutter and Dart development and unlock our massive catalog of 50+ books and 4,000+ videos.