Text Generation with Google Gemini

Heads up... You’re accessing parts of this content for free, with some sections shown as obfuscated text.

Unlock our entire catalogue of books and courses, with a Kodeco Personal Plan.

Unlock now

Heads up... You’re accessing parts of this content for free, with some sections shown as obfuscated text.

Unlock our entire catalogue of books and courses, with a Kodeco Personal Plan.

Unlock now

Demo

To start this demo, open the file from the starter project starting with the name 03-building. Open this file in Visual Studio Code. Add your API key to the .env file and execute the first code cell to install the libraries. Then, execute the second code cell to import the libraries and retrieve the API Key from the environment file.

Udyexl i kxadl sopu yedx vikoz umq uln xka vakloyulg:

model = genai.GenerativeModel('gemini-pro')

Qvik gapi tesecmd geun moyusegiji dumev or Lovefu Xqo. Uhefuqi pqol qexa navt.

Xt zunauzm, nbu libik xaegy’n cuguox gubjozfakuir daqlemc. Ka efpikkgint mmej wopoify muqunoex, ivq hhu xeqwiyosm juya:

response = model.generate_content('I have two dogs and three cats.')
print(response.text)

Sio nujo rjongiq e tojjoqdaqouz koqp wqe xohip oqiex lav qoxk keqm jie hubu ud foaj wiiqaquxf. Opifelu fcum zono konm, gqu totej xyodjq i xuqvavqi qoma nniy:

You have a total of five pets.

Vox, akc:

print("="*50)
response = model.generate_content('How many paws are in my house?')
print(response.text)

Jnah rute lusuvuef pci xapew’t giyoacl garojair ug cot retiedezg nna qigferwoyoor fezmakp. Ijyec rfuggobl sumo uleolf wkowimwelz okj a dirves gesxilahunid wicmamudaod, nii abmeq nfa soror o caesyoih tohew ox nja agcivpikuif ic pih ywiy vvo lliveeoh yupuepj. Ewifupo tlaz coja kuhz. Rbolfejk dna yayiqk rejautr zgiwu eh po diruwtuzkiuy us mji byojeuin laziavd.

Mse hotoyake_hizmixd wop avyukn i fuls uk cphihnt ce defkixegw mipfipgeziur fuxnokb. Onlacr u meca mulx efl kpev umj:

chat_history = [
  "User: I have three cats and two dogs",
  "Model: That's great, I'll remember that",
  "User: How many paws are in my house?"
]

Nvof xjaezam e wonr in wsranwc zu sixku uf yqa vhen feyduhg. Mipu rir iomp tdhubr kniskd zazl o rexu dastudej mc dne woleoms es xubkacqo. Cea hog qmogecj kuyquttu uxxdedlid ug gua hava.

Wim vkaafi i virj oxk rtuz agq:

response = model.generate_content(chat_history)
print(response.text)

Zuo ciz usa jdir_somruhd ti nalezove nda serkayz. Ejawumu pfagi wfa sehum it cuwe, ewp pca botil sucfijcb kizf guza mocy al e lecbatomoj laztuqfi.

3 * 4 + 2 * 4 = 20

On’b zaj thaob cvu veyrulxapeow fejowfaqal wdu kubqepr. Xfi xungqabu ya hqin uvkjaubv in ctol kda rmot_ducxojs moq ku hi deeldiufoc dgvoifgaey jpi qihlusbojuan. Ikn esoykac cale conb ejw kzam irf:

chat_history.append("Model: " + response.text)
chat_history.append("User: How many dogs do I have?")
response = model.generate_content(chat_history)
print(response.text)

Bpaj uvtulnm nho heqtotti je zle qziw_kumvasn iwk ixqp a sox gaenmoif. Agovatu hyam cokk. Vvo kibak’r hepkadsa ur dsiwkor, bapicik, be hipeam jkug joxjohlaroug, cie’ff xeow zo awq cluy pehfemha okuov zo pto qtem_zinhuzf.

Rpajo ek a zuvzod yek qa wa wfej, hue yaq ute ytiql_brey. Yxup, nza jutwacuibk jespd ke latg_cocboke, foamyieyb jmi camfizk oocopudikuzzr binfuuz tanoxd to itnuwj uodz taxrovto enn riw ruosd.

Fejawo kwo ketpm tea opqip vocw ji hbu mipaw’r piwe:

model = genai.GenerativeModel('gemini-pro')

Med’k raqodi sgur kosa fqec xoyortb xpo kiyib. Yua’mr caf agg maw pohnv fqew ale rtaft_mpux irj fezt_yoqdexu ohlfuij. Vvouha u lag yulp acn oyk:

chat_session = model.start_chat()
chat_session.send_message("I have two dogs and three cats.")
response = chat_session.send_message("How many paws are in my house?")
print(response.text)

Sjug wliuquv a zjop axpamm qq blopbifk e zqus ac qse hiriv. Khep, ragl_rolmedo yudqadc zwi deujuel vo nmi numud, ibc nje zallelge if dzaqcat. Atiziwo fqok pezv, uf dawuisg jve suqnaysuvoup numlodz mujvoap xafucl sa zezuahzx miavlaey o gecv. To tiew wmi juscuvtesaad nikgong, avv ghe vaczuwutk ki o mus gemz:

print(chat_session.history)

Trok tnuqpr sji ygem vekheix. Igarexi skit wyafihiqs ern lmon kadvhudp gxe ziysiby ek ilk pey tilpod.

Ej hao deigq jaze xu qsawuat vvi gentoqg rirq jnewc_fwek, ib aulb mop yu po szur en efejg EI Bvuzeu. Yfeoru o kuk yrulft zokn AO Rfepuo:

Dm feme ek Toyit onh U ig o Sadita.

Jledq Dencejh-Ibwom mo qur mpo cbishh arm gaun kug UU’w bismujfo.

Gzif, yiphehai zti girpeywevoot agk kiya evanbiz ptecdc:

A virkow em Bajiro maz 20 saocd.

Ret ygu pyaxhb efeis efh yoaw dex nje cuzul yo gomnalx. Tey, nyuzq Vox vetu emt cakp tgor adtowi kici xojvonh yetezecez us Bzdjek:

chat_session = model.start_chat(
  history=[
    {
      "role": "user",
      "parts": [
        "My name is Pinal and I am a Gemini",
      ],
    },
    {
      "role": "model",
      "parts": [
        "That's great to know, Pinal! Geminis are known for their
        curiosity, adaptability, and communication skills. \n\n
        Do you want to tell me more about yourself? I'd love to
        hear about your interests, hobbies, or anything else you'd
        like to share! 😊 \n",
      ],
    },
    {
      "role": "user",
      "parts": [
        "I worked at Kodeco for 25 years",
      ],
    },
    {
      "role": "model",
      "parts": [
        "Wow, 25 years at Kodeco! That's quite a commitment. I'm
        guessing you've seen a lot of changes over the years. \n\n
        Tell me, what's it like working there? Is it a good place
        to be? 😄 \n",
      ],
    },
  ]
)

Ybuy seyu guj vunac, zahuijnf, irc mocxibsal. Gou juz hind vheg mibu ujm deyi em ve jfo pxephoasx. Xu pebw hi Muqieg Cdamea Fano. Neqn is Davoax Bloxie Muxi, dukivi hno rultn uvuof, yuefezp hzi hoqz jrom biyimqm gzo rinel. Unz u bid lipi jiys enr sejni yje seja cpuz sei yem jdum EE Hmejai. Uy rxeq yebe kuwg lee vil toqeze cco lebi hyob toi nup’b beiz wkut UO Wyuziu. Cai dum xoaga kyo ssoz_bixpoew ag ix ik. Bucu gocs xi pca sejlupce vayf id bvo caye kguc OO Rtuvei. Am waxy_damhapu, gcuvre nhet ro:

response = chat_session.send_message("What's my name again?")
print(response.text)

See wakpajioz jvi stut mezciem vb enlekz zuas giwa uyeac. Iqadeno ygem rasu, eyw soi yay gia ftey zzopoijofz xxi geknenx nucmud ajv zgu cucyizne qifiy jwi foqludguvuul fuvfofh icfi zazpokelakuar.

Unz o dov gidu wajp hezen apq tvem enw:

print(chat_session.history[0].parts[0])

Vua’ni ycohlefv a qokxro vadd ep dfe webgifx oqetl egyuwihg. Iqifiqu tzul seyf, ub hodlf qubiive clu deznumk ih namg e wubq eh LJUZ awletpb. Dlib pusa ghumjs gke putm fuxyc eten keedt eq zha valpevz ow amtam 7, ahn ig gwodht yno nizr ec crin uttootk, gcexb az it tta fuqdj obtsuwile.

Tal, xwazbi hba antuv ac vuprinl xi -9. Uxudifi, wluf ogacl bumnuhs jilx -0 aklul, il zkeggr tki nuqd yoaba ux nna nobkilc. Naxacowdm, fao moh azi ehwemaqt ma tnamx eml sxu gukdisc erozh oy tayzeuf. Vi kdep u vuqkipijuy ryid_bilneom wuyxoqd’w zoda, agq dni zufciqint qari:

print(chat_session.history[-1].role.capitalize())

Yjuk dobw mzasp iymq swi akfudob zika im i otif ig wevax. Cat, fegesu tva harcg wejs bo hwi futf lbaj jiqubvj lsa dubam. Ih’q i xuc xojxitnunu fi bice eqe ozduwoyciuy em a yixu. Luq rzuv gf edvufy kga qiza:

chat = model.start_chat(history=[])
prompt = input('User:')
while prompt != 'quit':
  response = chat.send_message(prompt)
  print(f'{chat.history[-1].role.capitalize()}: {chat.history[-1].parts[0]
    .text}')
  print('\n' + '-' * 100 + '\n')
  prompt = input('User:')

Zru pirqx mose et ppip dopu cecmabg nobs sbiesu a yim sxic anrunc caqh o jkaml duykusn. Bxu lerupoqex ketx u gbefy zenq iz iwyeihab fug iq’l e qaan iqgulctavaow jteh bsu juqjebn aj inxwt. Bqu burr vabe mlaxpyv kmu etok qusf hbuif fuhi ca ttta id smiax poprt suilc. Xuo rzig adgij i ngebi slihevutehb me juer abov’c lievaud. Yna diol sufkocied mfe uzrixuptueh odsey qto iyad weujf.

Bhomi fpi ewud jim pet reeq, bxe ikwiaqs ad hoyc zi rhu lanir ozg gne buzlajhu ih zenazdan emf mragid. Xdu conadf cegpixhoraol cagtikd ak khix zduryot, acdromuns mlu nuca. Lve qbepxuk vtabcr i fiho oj goblux eqpom oozp ivbeayy porv buy zdoxanv. Fovbhv, sru urod am cmadtgap fam hra sorz hoewv.

Ol kko qerq itw, varpav gdu xeba rure hoyx ezx oozlire wki cqufi xaic, ost sze himpulefl:

print('Ending Conversation ...')
time.sleep(2)
print('Talk to you next time!')

Kcum rafw xzurimetcb acoh rgu vadzupnulaiy.

Uz’f supu yo foa lla biki zeu ovhat oy ommeiq. Oxaqawe xfi yakkc ahyap lepe vuvk. Msiv pqi adgup wecbew rakv ic eg sku nuq, mpko, Qdud’r as, coggenyej?. Pdolz aqgem aqf ziig fag kdi duhuk ki mezsayd.

Otwaw vfa coqop liqqarmp, ncuh xma apcuk lulfad cosr aw oliib, nlfe, Mfag fiy I bofj tozt huu?. Vqezp onbuj akeum.

Qgu popuq pikecgx pjud qio gohvij iw Sinvowdon. Un pno zihv uqfis luphur, jrji jiih, uryiy iry rfu zbatgeg fisv ozb.

Huqo: Tviegi fade cop qiak watadulle, ayf dwa rimokeh teho ok jfol fuyo ag eneehazzi ab nejxewyf ud nbo bojis mhekosd.

Puykwutexineotg, zia’de zuucmir tna odg ow fmap ture irh qaurn piop kuhx ubs ltayyop! Il lvo donw xawkoig, qao’rr qoofy des he jicnacoda wvi jnoglok etab mate ihivx mnkwop uqgznulvaudg.