Abasizi bezingxoxo ze-Artificial Intelligence (AI) bakhelwe ukunikeza izimpendulo ezinembile, zesikhathi sangempela ngokusebenzisa umzila ohlakaniphile wemibuzo emisebenzini ye-AI efaneleke kakhulu. Ngezinsizakalo ze-AI ezikhiqizayo ze-AWS ezifana I-Amazon Bedrock, onjiniyela bangakha amasistimu aphatha ngobuchwepheshe futhi aphendule izicelo zabasebenzisi. I-Amazon Bedrock iyisevisi ephethwe ngokugcwele enikeza ukukhetha kwamamodeli esisekelo asebenza kahle kakhulu (ama-FM) ezinkampanini ezihamba phambili ze-AI ezifana ne-AI21 Labs, Anthropic, Cohere, Meta, Stability AI, ne-Amazon esebenzisa i-API eyodwa, kanye nesethi ebanzi amakhono owadingayo ukuze wakhe izinhlelo zokusebenza ze-AI ezikhiqizayo ngokuvikeleka, ubumfihlo, kanye ne-AI enesibopho.

Lokhu okuthunyelwe kuhlola izindlela ezimbili eziyinhloko zokuthuthukisa abasizi be-AI: ukusebenzisa izinsizakalo eziphethwe njenge Ama-ejenti we-Amazon Bedrock, kanye nokusebenzisa ubuchwepheshe bomthombo ovulekile njenge I-LangChain. Sihlola izinzuzo nezinselele ngayinye, ukuze ukwazi ukukhetha indlela efaneleke kakhulu yezidingo zakho.

Yini umsizi we-AI?

Umsizi we-AI isistimu ehlakaniphile eqonda imibuzo yolimi lwemvelo futhi isebenzisana namathuluzi ahlukahlukene, imithombo yedatha, nama-API ukwenza imisebenzi noma ukubuyisa ulwazi egameni lomsebenzisi. Abasizi be-AI abaphumelelayo banamakhono abalulekile alandelayo:

• Ukucutshungulwa kolimi lwemvelo (NLP) nokugeleza kwengxoxo
• Ukuhlanganiswa kwesisekelo solwazi nosesho lwe-semantic ukuze kuqondwe futhi kubuyiswe ulwazi olufanele olususelwe kuma-nuances womongo wengxoxo
• Imisebenzi esebenzayo, efana nemibuzo yesizindalwazi kanye ngokwezifiso I-AWS Lambda imisebenzi
• Ukusingatha izingxoxo ezikhethekile nezicelo zabasebenzisi

Sibonisa izinzuzo zabasizi be-AI sisebenzisa ukuphathwa kwedivayisi ye-inthanethi Yezinto (IoT) njengesibonelo. Kulesi simo sokusetshenziswa, i-AI ingasiza ochwepheshe baphathe imishini kahle ngemiyalo elanda idatha noma ezenzakalelayo imisebenzi, iqondise ukusebenza kokukhiqiza.

Ama-ejenti wendlela ye-Amazon Bedrock

Ama-ejenti we-Amazon Bedrock ikuvumela ukuthi wakhe izinhlelo zokusebenza ze-AI ezikhiqizayo ezingasebenzisa izinyathelo eziningi kumasistimu enkampani nemithombo yedatha. Inikeza amakhono abalulekile alandelayo:

• Ukudalwa kokwaziswa okuzenzakalelayo kusuka kumiyalo, imininingwane ye-API, nolwazi lomthombo wedatha, okonga amaviki omzamo wobunjiniyela osheshayo
• I-Retrieval Augmented Generation (RAG) ukuze ixhume ama-ejenti ngokuphephile emithonjeni yedatha yenkampani futhi inikeze izimpendulo ezifanele.
• Ukuhlelwa nokusebenza kwemisebenzi enezinyathelo eziningi ngokuhlukanisa izicelo zibe ukulandelana okunengqondo nokubiza ama-API adingekayo
• Ukubonakala ekucabangeni kwe-ejenti ngokusebenzisa umkhondo we-chain-of-thought (CoT), okuvumela ukuxazulula inkinga nokuqondisa kokuziphatha okuyimodeli.
• Yazisa amakhono obunjiniyela ukuze uguqule isifanekiso sokwaziswa esikhiqizwe ngokuzenzakalelayo sokulawula okuthuthukisiwe kwabasebenzeli

Ungasebenzisa ama-Agent we-Amazon Bedrock kanye Izisekelo Zolwazi ze-Amazon Bedrock ukwakha nokuphakela abasizi be-AI kumacala okusebenzisa umzila ayinkimbinkimbi. Banikeza inzuzo yamasu konjiniyela nezinhlangano ngokwenza lula ukuphathwa kwengqalasizinda, ukuqinisa ukukala, ukuthuthukisa ukuphepha, nokunciphisa ukuphakamisa okusindayo okungahlukanisiwe. Ziphinde zivumele ikhodi yesendlalelo sohlelo lokusebenza elula ngoba i-logic yomzila, i-vectorization, nenkumbulo iphethwe ngokugcwele.

Ukubukwa kwesisombululo

Lesi sixazululo sethula umsizi we-AI wengxoxo oklanyelwe ukuphathwa kwedivayisi ye-IoT nokusebenza lapho kusetshenziswa i-Anthropic's Claude v2.1 ku-Amazon Bedrock. Umsebenzi oyinhloko womsizi we-AI kulawulwa isethi yemiyalelo ebanzi, eyaziwa ngokuthi ukwaziswa kwesistimu, echaza amakhono ayo kanye nezindawo zobuchwepheshe. Lesi siqondiso siqinisekisa ukuthi umsizi we-AI angakwazi ukuphatha imisebenzi eminingi, kusukela ekuphatheni ulwazi lwedivayisi ukuya ekusebenziseni imiyalo yokusebenza.

"""The following is the system prompt that outlines the full scope of the AI assistant's capabilities:
You are an IoT Ops agent that handles the following activities:
- Looking up IoT device information
- Checking IoT operating metrics (historical data)
- Performing actions on a device-by-device ID
- Answering general questions
You can check device information (Device ID, Features, Technical Specifications, Installation Guide, Maintenance and Troubleshooting, Safety Guidelines, Warranty, and Support) from the "IotDeviceSpecs" knowledge base.
Additionally, you can access device historical data or device metrics. The device metrics are stored in an Athena DB named "iot_ops_glue_db" in a table named "iot_device_metrics". 
The table schema includes fields for oil level, temperature, pressure, received_at timestamp, and device_id.
The available actions you can perform on the devices include start, shutdown, and reboot."""

Ihlonyiswe ngalawa makhono, njengoba kuchaziwe ekwazisweni kwesistimu, umsizi we-AI ulandela ukugeleza komsebenzi okuhlelekile ukubhekana nemibuzo yabasebenzisi. Isibalo esilandelayo sinikeza ukumelwa okubonakalayo kwalokhu kuhamba komsebenzi, okubonisa isinyathelo ngasinye kusukela ekusebenzelaneni kokuqala komsebenzisi kuya ekuphenduleni kokugcina.

Uhlelo lokusebenza lwakhiwe yizinyathelo ezilandelayo:

1. Inqubo iqala lapho umsebenzisi ecela umsizi ukuthi enze umsebenzi; isibonelo, ukucela amaphoyinti edatha aphezulu wedivayisi ethile ye-IoT device_xxx. Lokhu kufakwa kombhalo kuyathathwa futhi kuthunyelwe kumsizi we-AI.
2. Umsizi we-AI uhumusha okokufaka kombhalo komsebenzisi. Isebenzisa umlando wengxoxo enikeziwe, amaqembu esenzo, nezisekelo zolwazi ukuqonda umongo nokunquma imisebenzi edingekayo.
3. Ngemuva kokuthi inhloso yomsebenzisi isincozululiwe futhi yaqondwa, umsizi we-AI uchaza imisebenzi. Lokhu kusekelwe emiyalweni ehunyushwa umsizi njengokuya kokwaziswa kwesistimu nokokufaka komsebenzisi.
4. Imisebenzi ibe isiqhutshwa ngochungechunge lwezingcingo ze-API. Lokhu kwenziwa ngokusebenzisa I-React prompting, ehlukanisa umsebenzi ube uchungechunge lwezinyathelo ezicutshungulwa ngokulandelana:
   1. Ukuhlola amamethrikhi edivayisi, sisebenzisa i- check-device-metrics iqembu lesenzo, elibandakanya ikholi ye-API eya emisebenzini ye-Lambda bese ibuza I-Amazon Athena ngedatha eceliwe.
   2. Ngezenzo eziqondile zedivayisi njengokuqala, ukumisa, noma ukuqalisa kabusha, sisebenzisa i action-on-device iqembu lesenzo, elicela umsebenzi we-Lambda. Lo msebenzi uqala inqubo ethumela imiyalo kudivayisi ye-IoT. Kulokhu okuthunyelwe, umsebenzi we-Lambda uthumela izaziso usebenzisa Isevisi ye-imeyili Elula ye-Amazon (I-Amazon SES).
   3. Sisebenzisa i-Knowledge Bases ye-Amazon Bedrock ukuze silande kudatha yomlando egcinwe njengokushumeka ku- Isevisi ye-Amazon OpenSearch i-vector database.
5. Ngemuva kokuthi imisebenzi isiqediwe, impendulo yokugcina yenziwa yi-Amazon Bedrock FM futhi idluliselwe kumsebenzisi.
6. Ama-ejenti e-Amazon Bedrock agcina ngokuzenzakalelayo imininingwane esebenzisa iseshini esezingeni eliphezulu ukuze kugcinwe ingxoxo efanayo. Isimo siyasuswa ngemva kokuphela kwesikhathi sokungenzi lutho esilungisekayo.

Ukubuka konke kwezobuchwepheshe

Umdwebo olandelayo ubonisa ukwakheka ukuze kusetshenziswe umsizi we-AI nama-Agents we-Amazon Bedrock.

Iqukethe izingxenye ezibalulekile ezilandelayo:

• Isixhumi esibonakalayo sengxoxo -Isixhumi esibonakalayo sengxoxo sisebenzisa i-Streamlit, umtapo wolwazi we-Python womthombo ovulekile owenza kube lula ukudalwa kwezinhlelo zokusebenza zewebhu ezikhangayo zokufunda ngomshini (ML) nesayensi yedatha. Isingathwa ngo Isevisi ye-Amazon Elastic Container (Amazon ECS) nge AWS Fargate, futhi ifinyelelwa kusetshenziswa I-Application Load Balancer. Ungasebenzisa i-Fargate nge-Amazon ECS ukuze usebenzise iziqukathi ngaphandle kokuphatha amaseva, amaqoqo, noma imishini ebonakalayo.
• Ama-ejenti we-Amazon Bedrock - Ama-ejenti e-Amazon Bedrock aqedela imibuzo yomsebenzisi ngochungechunge lwezinyathelo zokucabanga nezenzo ezihambisanayo ezisekelwe Ukwaziswa kwe-ReAct:
  • Izisekelo Zolwazi ze-Amazon Bedrock - Izisekelo Zolwazi ze-Amazon Bedrock zihlinzeka ngokuphathwa ngokugcwele I-RAG ukuze unikeze umsizi we-AI ukufinyelela kudatha yakho. Esimeni sethu sokusetshenziswa, silayishe imininingwane yedivayisi ku- Isevisi ye-Amazon Simple Storage (Amazon S3) ibhakede. Isebenza njengomthombo wedatha kwisisekelo solwazi.
  • Amaqembu esenzo - Lawa ama-schema e-API achaza imisebenzi ethile ye-Lambda ukuze uxhumane namadivayisi we-IoT nezinye izinsiza ze-AWS.
  • I-Anthropic Claude v2.1 ku-Amazon Bedrock - Le modeli ihumusha imibuzo yabasebenzisi futhi ihlele ukuhamba kwemisebenzi.
  • I-Amazon Titan Embeddings – Le modeli isebenza njengemodeli yokushumeka umbhalo, iguqule umbhalo wolimi lwemvelo—usuke egameni elilodwa ukuya kumadokhumenti ayinkimbinkimbi—uwenze amavekhtha ezinombolo. Lokhu kunika amandla amandla okusesha ama-vector, okuvumela isistimu ukuthi ihambisane nemibuzo yabasebenzisi nesisekelo solwazi esihlobene kakhulu nosesho olusebenzayo.

Isixazululo sihlanganiswe nezinsizakalo ze-AWS ezifana neLambda yokusebenzisa ikhodi ekuphenduleni izingcingo ze-API, i-Athena yokubuza amasethi edatha, Isevisi ye-OpenSearch yokusesha ngezisekelo zolwazi, kanye ne-Amazon S3 yokugcina. Lezi zinsizakalo zisebenza ndawonye ukuze zinikeze umuzwa ongenazihibe wokuphathwa kokusebenza kwedivayisi ye-IoT ngemiyalo yolimi lwemvelo.

Izinzuzo

Lesi sixazululo sinikeza izinzuzo ezilandelayo:

• Ukusebenza okuyinkimbinkimbi:
  • Kudingeka imigqa embalwa yekhodi, ngoba ama-ejenti e-Amazon Bedrock asusa okuningi kobunzima obukhona, anciphisa umzamo wokuthuthukisa.
  • Ukuphatha imininingo egciniwe ye-vector efana ne-OpenSearch Service kwenziwa lula, ngoba Izisekelo Zolwazi ze-Amazon Bedrock ziphethe i-vectorization nokugcinwa
  • Ukuhlanganiswa nezinsiza ezihlukahlukene ze-AWS kwenziwa lula ngamaqembu ezenzo achazwe ngaphambilini
• Umuzwa wonjiniyela:
  • I-Amazon Bedrock console inikezela ngesixhumi esibonakalayo esisebenziseka kalula ukuze kuthuthukiswe ngokushesha, kuhlolwe, kanye nokuhlaziya imbangela yezimpande (RCA), ethuthukisa umuzwa wonjiniyela wonke.
• I-Agility kanye nokuvumelana nezimo:
  • Ama-ejenti e-Amazon Bedrock avumela ukuthuthukiswa okungenamthungo kuma-FM amasha (afana no-Claude 3.0) uma etholakala, ukuze isisombululo sakho sihlale sihambisana nentuthuko yakamuva.
  • Izilinganiso zesevisi nemikhawulo zilawulwa yi-AWS, inciphisa ingqalasizinda yokuqapha nokukala
• Ukuphepha:
  • I-Amazon Bedrock iyisevisi ephethwe ngokugcwele, ethobela ukuphepha okuqinile kwe-AWS kanye nezindinganiso zokuthobela, okungenzeka kube lula ukubuyekezwa kwezokuphepha kwenhlangano.

Nakuba ama-Agent e-Amazon Bedrock enikeza isixazululo esilula nesiphethwe sokwakha izinhlelo zokusebenza ze-AI zezingxoxo, ezinye izinhlangano zingakhetha indlela yomthombo ovulekile. Ezimweni ezinjalo, ungasebenzisa izinhlaka ezifana ne-LangChain, esixoxa ngazo esigabeni esilandelayo.

Indlela ye-LangChain eguquguqukayo yomzila

I-LangChain iwuhlaka lomthombo ovulekile elenza kube lula ukwakha i-AI yengxoxo ngokuvumela ukuhlanganiswa kwezinhlobo zezilimi ezinkulu (ama-LLM) namandla omzila aguquguqukayo. Nge-LangChain Expression Language (LCEL), abathuthukisi bangachaza i- ukuhamba, okukuvumela ukuthi udale amaketanga anganqunyelwe lapho ukukhishwa kwesinyathelo sangaphambilini kuchaza isinyathelo esilandelayo. Umzila usiza ukuhlinzeka ngesakhiwo nokuvumelana ekusebenzisaneni nama-LLM.

Kulokhu okuthunyelwe, sisebenzisa isibonelo esifanayo njengomsizi we-AI wokuphatha idivayisi ye-IoT. Kodwa-ke, umehluko omkhulu ukuthi sidinga ukuphatha imiyalo yesistimu ngokuhlukana futhi siphathe uchungechunge ngalunye njengebhizinisi elihlukile. Uchungechunge lomzila lunquma iketango lendawo ngokusekelwe kokokufaka komsebenzisi. Isinqumo senziwa ngosekelo lwe-LLM ngokudlulisa ukwaziswa kwesistimu, umlando wengxoxo, kanye nombuzo wabasebenzisi.

Ukubukwa kwesisombululo

Umdwebo olandelayo ubonisa ukuhamba komsebenzi kwesisombululo somzila.

Ukugeleza komsebenzi kuqukethe izinyathelo ezilandelayo:

1. Umsebenzisi wethula umbuzo kumsizi we-AI. Isibonelo, "Ayini ama-metrics aphezulu wedivayisi engu-1009?"
2. I-LLM ihlola umbuzo ngamunye kanye nomlando wengxoxo kusukela kuseshini efanayo ukuze inqume ubunjalo bayo nokuthi iwela ngaphansi kwasiphi isihloko (njenge-SQL, isenzo, usesho, noma i-SME). I-LLM ihlukanisa okokufaka futhi uchungechunge lomzila lwe-LCEL luthatha lokho kufaka.
3. Iketango le-router likhetha iketango lendawo ngokusekelwe kokokufakayo, futhi i-LLM inikezwa umyalo wesistimu olandelayo:

"""Given the user question below, classify it as one of the candidate prompts. You may want to modify the input considering the chat history and the context of the question. 
Sometimes the user may just assume that you have the context of the conversation and may not provide a clear input. Hence, you are being provided with the chat history for more context. 
Respond with only a Markdown code snippet containing a JSON object formatted EXACTLY as specified below. 
Do not provide an explanation to your classification beside the Markdown, I just need to know your decision on which destination and next_inputs
<candidate prompt>
physics: Good for answering questions about physics
sql: sql: Good for querying sql from AWS Athena. User input may look like: get me max or min for device x?
lambdachain: Good to execute actions with Amazon Lambda like shutting down a device or turning off an engine User input can be like, shutdown device x, or terminate process y, etc.
rag: Good to search knowledgebase and retrieve information about devices and other related information. User question can be like: what do you know about device x?
default: if the input is not well suited for any of the candidate prompts above. this could be used to carry on the conversation and respond to queries like provide a summary of the conversation
</candidate prompt>"""

I-LLM ihlola umbuzo womsebenzisi kanye nomlando wengxoxo ukuze inqume uhlobo lombuzo nokuthi iwela ngaphansi kwayiphi indawo yesihloko. I-LLM bese ihlukanisa okokufaka bese ikhipha impendulo ye-JSON ngefomethi elandelayo:

<Markdown>
```json
{{
"destination": string  name of the prompt to use
"next_inputs": string  a potentially modified version of the original input
}}
```

Iketango lomzila lisebenzisa le mpendulo ye-JSON ukuze icele uchungechunge oluhambisanayo lwendawo. Kunamaketanga endawo amane aqondene nesihloko, ngalinye linokwaziswa kwalo kwesistimu:

1. Imibuzo ehlobene ne-SQL ithunyelwa ochungechungeni lwendawo ye-SQL ukuze kusetshenziswe isizindalwazi. Ungasebenzisa i-LCEL ukwakha i- I-SQL chain.
2. Imibuzo egxile esenzweni icela uchungechunge lwendawo oya kuyo lwe-Lambda lwangokwezifiso ukuze luqhube imisebenzi. Nge-LCEL, ungazichaza ngokwakho umsebenzi wangokwezifiso; esimweni sethu, kuwumsebenzi wokuqalisa umsebenzi ochazwe ngaphambilini we-Lambda ukuthumela i-imeyili ene-ID yedivayisi ehlukanisiwe. Okokufaka komsebenzisi okuyisibonelo kungase kube “Vala idivayisi 1009.”
3. Imibuzo egxile ekusesheni iqhubekela kokuthi I-RAG uchungechunge lwendawo okuyiwa kuyo ukuze kubuyiswe ulwazi.
4. Imibuzo ehlobene nama-SME iya kuchungechunge lwezindawo okuyiwa kuzo ama-SME/uchwepheshe ukuze uthole imininingwane ekhethekile.
5. Uchungechunge lwendawo ngayinye luthatha okokufaka bese lusebenzisa amamodeli adingekayo noma imisebenzi:
   1. Iketango le-SQL lisebenzisa i-Athena ukwenza imibuzo.
   2. Iketango le-RAG lisebenzisa isevisi ye-OpenSearch ekusesheni kwe-semantic.
   3. Uchungechunge lwangokwezifiso lwe-Lambda lusebenzisa imisebenzi ye-Lambda yezenzo.
   4. I-SME/uchungechunge lochwepheshe luhlinzeka ngemininingwane kusetshenziswa imodeli ye-Amazon Bedrock.
6. Izimpendulo ezivela kuchungechunge lwendawo ngayinye zenziwe zaba imininingwane ehambisanayo yi-LLM. Le mininingwane ibe isithunyelwa kumsebenzisi, kuqedelwa umjikelezo wemibuzo.
7. Okokufaka komsebenzisi nezimpendulo zigcinwa ngaphakathi I-Amazon DynamoDB ukunikeza umongo ku-LLM yeseshini yamanje kanye nokusebenzelana okudlule. Ubude besikhathi solwazi oluqhubekayo ku-DynamoDB kulawulwa uhlelo lokusebenza.

Ukubuka konke kwezobuchwepheshe

Umdwebo olandelayo ubonisa ukwakheka kwesisombululo somzila esiguqukayo se-LangChain.

Uhlelo lokusebenza lwewebhu lwakhiwe ku-Streamlit ephethwe ku-Amazon ECS nge-Fargate, futhi lufinyelelwa kusetshenziswa i-Application Load Balancer. Sisebenzisa i-Anthropic's Claude v2.1 ku-Amazon Bedrock njenge-LLM yethu. Uhlelo lokusebenza lwewebhu lusebenzisana nemodeli lisebenzisa imitapo yolwazi ye-LangChain. Iphinde ihlanganyele nezinye izinsiza ezihlukahlukene ze-AWS, njenge-OpenSearch Service, i-Athena, ne-DynamoDB ukufeza izidingo zabasebenzisi bokugcina.

Izinzuzo

Lesi sixazululo sinikeza izinzuzo ezilandelayo:

• Ukusebenza okuyinkimbinkimbi:
  • Nakuba idinga ikhodi eyengeziwe kanye nokuthuthukiswa kwangokwezifiso, i-LangChain inikeza ukuguquguquka okukhulu nokulawula phezu kwe-logic yomzila nokuhlanganiswa nezingxenye ezihlukahlukene.
  • Ukuphatha imininingo egciniwe ye-vector efana ne-OpenSearch Service kudinga imizamo eyengeziwe yokusetha neyokulungiselela. Inqubo ye-vectorization isetshenziswa ngekhodi.
  • Ukuhlanganisa nezinsizakalo ze-AWS kungase kubandakanye ikhodi yangokwezifiso eyengeziwe nokucushwa.
• Umuzwa wonjiniyela:
  • Indlela kaLangChain esekelwe kwiPython kanye nemibhalo ebanzi ingakhanga abathuthukisi asebejwayelene nePython kanye namathuluzi omthombo ovulekile.
  • Ukuthuthukiswa okusheshayo nokulungisa iphutha kungase kudinge umzamo owengeziwe owenziwa ngesandla uma kuqhathaniswa nokusebenzisa ikhonsoli ye-Amazon Bedrock.
• I-Agility kanye nokuvumelana nezimo:
  • I-LangChain isekela ama-LLM anhlobonhlobo, ikuvumela ukuthi ushintshe phakathi kwamamodeli noma abahlinzeki abahlukene, okugqugquzela ukuguquguquka.
  • Imvelo yomthombo ovulekile ye-LangChain inika amandla ukuthuthukiswa nokwenziwa ngokwezifiso okuqhutshwa umphakathi.
• Ukuphepha:
  • Njengohlaka lomthombo ovulekile, i-LangChain ingase idinge ukubuyekezwa okuqinile kwezokuphepha kanye nokuhlolwa ngaphakathi kwezinhlangano, okungase kwengeze phezulu.

Isiphetho

Abasizi be-AI bengxoxo bangamathuluzi aguqulayo okwenza lula ukusebenza kanye nokuthuthukisa ulwazi lwabasebenzisi. Lokhu okuthunyelwe kuhlole izindlela ezimbili ezinamandla kusetshenziswa izinsiza ze-AWS: Ama-ejenti aphethwe e-Amazon Bedrock kanye nomzila oguquguqukayo, ovulekile womthombo we-LangChain. Ukukhetha phakathi kwalezi zindlela kuncike ezidingweni zenhlangano yakho, izintandokazi zentuthuko, kanye nezinga elifiswayo lokwenza ngokwezifiso. Kungakhathalekile ukuthi iyiphi indlela ethathiwe, i-AWS ikunikeza amandla okudala abasizi be-AI abahlakaniphile abaguqula ibhizinisi nokusebenzisana kwamakhasimende.

Thola ikhodi yesixazululo kanye nezimpahla zokuthunyelwa kwethi yethu IGitHub repository, lapho ungalandela khona izinyathelo ezinemininingwane zendlela ngayinye yengxoxo ye-AI.

Mayelana Ababhali

Ameer Hakme i-AWS Solutions Architect esekelwe ePennsylvania. Usebenzisana ne-Independent Software Vendors (ISVs) esifundeni saseNyakatho-mpumalanga, ebasiza ekuklameni nasekwakheni izinkundla eziyingozi nezesimanje ku-AWS Cloud. Uchwepheshe ku-AI/ML kanye ne-AI ekhiqizayo, u-Ameer usiza amakhasimende ukuthi avule amandla alobu buchwepheshe obuphambili. Esikhathini sakhe sokungcebeleka, uyakujabulela ukugibela isithuthuthu sakhe nokuchitha isikhathi esihle nomndeni wakhe.

USharon Li i-AI/ML Solutions Architect e-Amazon Web Services ezinze e-Boston, enothando lokuklama nokwakha izinhlelo zokusebenza ze-Generative AI ku-AWS. Usebenzisana namakhasimende ukuze asebenzise izinsizakalo ze-AWS AI/ML ukuze uthole izixazululo ezintsha.

Kawsar Kamal ungumakhi wezixazululo eziphezulu kwa-Amazon Web Services oneminyaka engaphezu kwe-15 yesipiliyoni endaweni yengqalasizinda ezenzakalelayo kanye nezokuphepha. Usiza amaklayenti aklame futhi akhe izixazululo ze-DevSecOps ne-AI/ML ku-Cloud.

• I-SEO Powered Content & PR Distribution. Khuliswa Namuhla.
• I-PlatoData.Network Vertical Generative Ai. Zinike Amandla. Finyelela Lapha.
• I-PlatoAiStream. I-Web3 Intelligence. Ulwazi Lukhulisiwe. Finyelela Lapha.
• I-PlatoESG. Ikhabhoni, I-CleanTech, Amandla, Environment, Ilanga, Ukuphathwa Kwemfucuza. Finyelela Lapha.
• I-PlatoHealth. I-Biotech kanye ne-Clinical Trials Intelligence. Finyelela Lapha.
• Source: https://aws.amazon.com/blogs/machine-learning/enhance-conversational-ai-with-advanced-routing-techniques-with-amazon-bedrock/