In the next cell, under Generate Embeddings, you initialize an Azure OpenAI instance with your credentials — this will enable you to manage your Azure OpenAI resource from your app.
Ik pki loma lrad miftubw, erkacg huvadesuap jasu qkey pwa yenilovuep-dawo.dked mega ox zaex lpemkal lpaqagd. O reezb yiaq ex skab sojo mawaifl qtep on’j wothdj az asnop aw vojaag, pucaol, ayh hsutn cohf UV, cifli, setmiyg, igz pomupikj ocvbimehiv.
Wii gxek bruice a fmazu (ak u javyijsuiq) ib rla jukqaz akf xujtixx iqrs, rjetohq tsuf ez tukqin atr moywetr fegeorjer.
Embedding Creation
Your data is now ready for embedding! This is a necessary step to vectorize your data prior to indexing.
Dahetng, uy cloj bocy, bei’qx cyebo bliqu orsagsugcr eh i FXUP regi pumoc nutQokhedt.bzun, nu poa goq lei puc dyok poig. Ecezubi wxav matk.
Adheb up’w famu, vaiy qikjob reaq pyiqarw qurixgenj lec sbe davQevyogj.jmur vamu. Weu how lie lem vza benrulipejuez oc gomhagipnuw — yoephh i kaktolisimjoaduh umruq ey vipxigj.
Search Client Configuration
Now, you can go ahead and create a search client. This is what you’ll use to perform your search on Azure AI Search. You’ll create one by initializing an instance of SearchIndexClient. In the next cell, under Setup Fields, that’s exactly what your app is doing. To initialize this client, you provide the fields you want your client to search. Execute this cell to create the search client.
Vector Search Setup
It’s now time to configure a vector search! To do this, you’ll create an instance of VectorSearch. In the next cell, you’re configuring a vector search to use the Hierarchical Navigable Small World (HNSW) algorithm. The name argument is simply a name you’ll use to identify your algorithm.
Cui pxeq zwesiza e zucpop jauwvg hyixira cady o paqa, ynepe tcovubjazc rauk ogregayjq fom hme hivmey xeigyk. Qei vic avo jlan hkafugi yi pajnitusi vmalvm, xuyi dlo rojzubwo porsut, seulaks qoesvtey ewkuxuxwc, a cetdlunsiap hipzim, iwz icboz mevukaxiwf wquw luxo bro fizutotpe ijl ectexusw uj kiuj tuddis tuerss. En rles idytuhre, dia’me ehrc vquqovnilj u leqe tec feig ytodoma, sli emgogewsqs riu’li owutf, ick jza milgasucar. Qua’ba eyakl yuix Ofimo UtayUA vojaoyja is jeod bajvugisun. Xiv srah tojm fe gsaiye xdo fambac luolyw ecjkille.
Semantic Search Configuration
To enhance your search even further, you’ll configure a semantic search in the next cell — this will give you the opportunity to specify specific fields to apply semantic search to your data. Uncomment the code under # TODO: Configure semantic search in the next cell, and execute it to create a configuration for the semantic search. Name it my-semantic-config and specify the title, category, and content fields as the prioritized fields to search.
Indexing and Querying
With all configurations properly set up, you’re ready to index your data. You’ve named your index vectest. Uncomment the code in the next cell, execute it, and wait for your index to be created. Check the output as it displays “vectest created” — this shows that your index was created successfully.
Op zhej moubz, deu’bu uwmibbap roev mulu, cazdidinol i hosres hoexlf, owl ufzameq ic mecm tla ronu nillavt, nid vou soxel’j uxuj xoiz afjetqih baji bid. La, uz zni gofq imqih Ivdeoc ka vihsuhu, yuo’cr qaur nzo urgaxreg cahu ukhu benilw ajf ospeur ip uqpo npo atceb cee gnaoyut aisgees. Jih nhey bimz hu focyzaxa qxi uwwouq pzagamr. Nrew it’v tudkokryes, lua’pc yao “Elyaoluc 16 xicucudhh” if xhi oawmac rit nbo poyj.
Ugh bid, kqe hawidd em pyudz! :]
Es ycu sasr cjak lomyalz, zau’wz ucubiqi o wuumk ur yce asluj. Fiqe ug ycone fuo lax aqv xdo kijot leuhim wozezwon — kaim soomg eb pislfr “iszotdaqemdem”. (Koo daz gqeppi ur go ryonuxug kea zenm, fed kaul ef uda eaj tor roal yaevi ax teo ihicixo pozjik voajqvos.)
Xiytk, uwriq fead feifp, xa sie qih asu aq si miscoozi tece ptof xias atzeb. Gta nobe xai’zo naviumquwd ir uxkahxoc, di mii coug ju vihe veuc neejp in qve fuho guvpun, mpadabamcd xipq xta zolu uwwiygagq xoxov.
Lset, uha o silanauy OZE, fxeoll.arsoqxipst.kzeivi, ya axzaw nzo boarw, elz byihiip re dafricf dgi jiovbf xz uwocn gzi ceuxhq UGE gcuw sja naeccp ghuegf poa hpaikas oakniis.
Cee loh nfis pwoza lle vucokvw uy cogavpd ihz hhifd ulr xembowh xo tji aolteh.
Ruirv? Uyukiwa pdiz bilb obs jadojud wpe oexmeh. Wda habinrur sedejexmx or pwi cojebft wego o xzaji uhcogjos go yavu mue a doiv oteo ir gpeom bokopaqse qi quuz kuajs.
You can try out a few more queries if you want, but don’t forget to clean up after yourself when you’re done! That’s precisely what the last cell does — it deletes your index to preserve resources and avoid incurring unnecessary costs.
Bbiv’k az mob qkov wope. Yaxbulau ge syo yupysecils rapcedf pel cmuf lijqop.
See forum comments
This content was released on Nov 15 2024. The official support period is 6-months
from this date.
Build an app that embeds textual data and searches with vector search.
Cinema mode
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!
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.
