I-AI Agents ehlanganisa idatha ehlelekile futhi engahleliwe: Ukuguqula Analytics Support and Ngaphesheya Nama-Amazon Q

Njengoba izinhlangano zifuna ukuthola inani elikhudlwana emininingwaneni yazo ye-AWS Support, amaqembu okusebenza afuna izindlela zokuguqula amacala okusekelwa okuluhlaza kanye nemicimbi yezempilo ibe yimininingwane engasebenziseka. Ngenkathi amathuluzi okuhlaziya kwendabuko anganikeza amandla ayisisekelo wokubika, amaqembu adinga izixazululo ezinobuchwepheshe ezingaqonda futhi acubungule imibuzo yolimi lwemvelo mayelana nedatha yazo yokusebenza. I-Retrieval-Augmented Nexgreved Generation (Rag) yokwakha ifomu lesisekelo sokwenza kahle imiphumela emikhulu yolimi ngokuthola imininingwane egunyaziwe yedatha ngaphandle kwemininingwane yabo yokuqeqesha ngaphambi kokuphendula izimpendulo ngaphambi kokukhiqiza izimpendulo. Lo mbuso usebenzisa amandla okusesha i-semantic kanye namakhono wokubuyisa imininingwane ukuthuthukisa ukunemba.

Eposini lethu le-blog yangaphambilini, uthola imininingwane yokusebenza enenjongo futhi esebenzayo kusuka kuma-AWS usebenzisa i-Amazon Q Business, sethula isixazululo esisekwe ku-Rag sisebenzisa i-Amazon Q. Kodwa-ke, ngenkathi le ndlela idlula kuseshini ye-semantic, ingabhekana nezinselelo ngokuhlaziywa kwezinombolo okuqondile kanye nokuhlanganiswa. Kulokhu okuthunyelwe, sibhekana nalemikhawulo ngokubonisa ukuthi ungathuthukisa kanjani i-Amazon Q ngama-plugins ngokwezifiso ukuthuthukisa ama-analytics wokusekelwa kanye nempendulo yezehlakalo. Isixazululo sethu sihlanganisa amandla we-rag nge-data yedatha ehlelekile, enika amandla izimpendulo ezinembile kakhulu zemibuzo yokuhlaziya mayelana nedatha yakho yokusekelwa kwe-AWS. Imiyalo enemininingwane yokuhanjiswa kwesixazululo kulokhu okuthunyelwe iyatholakala kumasampula ethu amasampula wesampula.

Ukuqonda ukwakheka kwe-rag ye-analytics

I-Rag Architecture Exlels ekutholeni imininingwane efanelekile ngokufanisa okususelwa kumongo, inika amandla ukusebenzisana kolimi lwemvelo ngedatha yangaphandle. Kodwa-ke, ukwakhiwa okuyisisekelo kokusesha okufanayo kokufana kwe-vector, okubeka phambili ukuhambisana kwe-semantic ngamandla okuhlaziya okuhlangene, kungenisa ukungalungile okuphambili. Ake sihlole lokhu kukhawulelwa ngombuzo olula:

Give me total count of support cases in Feb 2025

Okulandelayo impendulo ye-rag kuphela ekhombisa ukuthi uhlelo luzama ukuhlanganisa imininingwane kusuka kumadokhumenti ahlukahlukene, ukubika amacala angama-190 ngezinhlamvu ezingaba khona.

Based on the provided JSON files, there were 190 AWS support cases documented in 
February 2025, calculated from the following case counts: 17 cases from Feb 1-3, 
12 cases from Feb 4-5, 21 cases from Feb 7-8, 21 cases from Feb 8-10, 16 cases from 
Feb 10-11, 10 cases from Feb 11-12, 23 cases from Feb 19-20, 22 cases from Feb 20-21,
27 cases from Feb 23-24, and 21 cases from Feb 25-26.

Kodwa-ke, lapho kuthuthukiswa ngamakhono okubuza wedatha ahlelekile, umbuzo ofanayo uveza amacala okusekelwa angama-958, ukubalwa okuqondile okuqinisekisiwe ngokumelene nedatha yangempela:

Based on the query results, there were a total of 958 support cases in February 2025.

Lo mkhawulo uqala ukwenzeka ngokwengeziwe ngemibuzo eyinkimbinkimbi edinga ukuhlaziywa kwezigaba:

Give me OpenSearch Support cases, distribution based on severity, opened in Jan 2025?

Lokhu okulandelayo ukuphendula okuphelele okukhombisa ukuphehla okulinganiselwe noma okungalungile kokuhlukaniswa:

Based on the support cases data from January 2025, here is the severity distribution 
for OpenSearch cases: 

Urgent: One case was opened regarding cluster health degradation and production system 
downtime

Normal: Two cases were identified:
1. A case about OpenSearch RI Exchange
2. A case concerning blue/green deployment upgrade from version 1.3 to 2.17

The cases demonstrate varying levels of urgency, with one critical production issue 
and two normal severity cases requiring standard response times.

Ngobungcweti bedatha ehlelekile, sithola ukusatshalaliswa okuqondile okuphezulu:

Based on the query results for OpenSearch Support cases opened in January 2025,
here's the distribution by severity:
1. Normal severity: 4 cases
2. Critical severity: 4 cases
3. High severity: 3 cases
4. Low severity: 2 cases
5. Urgent severity: 1 case

In total, there were 14 OpenSearch Support cases opened in January 2025. 
The distribution shows that Normal and Critical severity cases were the most common, 
followed by High severity cases. There were fever Low and Urgent severity cases 
during this period.

Igebe landa kakhulu lapho kusebenza ngokuhlaziywa kobukhulu obuhlukahlukene. Cabanga ngombuzo olandelayo onobukhulu obuningi obulindele ukuhlaziya okuningiliziwe ngenhlanganisela ye-akhawunti namaphethini wesikhashana.

QAPHELA:

Find accounts with frequent high-priority support cases since January 2024, 
excluding limit increase requests. For each account and AWS service combination, 
show the total number of cases and how many different days had issues. 
Only include results where there were more than 3 cases, and sort results by the 
highest number of cases first.

Impendulo:

Based on the analysis of high-priority support cases since January 2024, excluding
limit increase requests, here are the key findings:

1. The account with the most frequent high-priority cases is 111111111111, with 
60 cases for the Connect service.
2. The top 5 account and service combinations with the highest number of cases are:
* Account 111111111111 (Connect): 60 cases
* Account 222222222222 (RDS Oracle): 52 cases
* Account 333333333333 (OpenSearch Service): 38 cases
* Account 444444444444 (Aurora PostgreSQL): 25 cases
* Account 555555555555 (EMR): 23 cases

The services that appear most frequently in the top results are:
* Aurora PostgreSQL
* OpenSearch Service
* RDS Oracle
* EMR
* DynamoDB

Interestingly, the number of total cases matches the number of unique days with 
cases for each account-service combination. This suggests that these accounts 
are experiencing issues on different days rather than multiple issues on the 
same day.

There are 89 account-service combinations that have more than 3 high-priority 
cases since January 2024.

Some accounts appear multiple times with different services, indicating they 
may be experiencing issues across various AWS offerings. For example:
* Account 222222222222 appears with RDS Oracle (52 cases), DynamoDB (18 cases), 
and Aurora PostgreSQL (6 cases)
* Account 111111111111 appears with Connect (60 cases) and other services

This information can be useful for identifying accounts that may need additional 
support or proactive engagement to address recurring issues. Would you like to 
focus on a specific aspect of this data or explore further details about 
particular accounts or services?

Okulandelayo ukusabela kwe-rag kuphela okubonisa ukungakwazi ukucubungula umbuzo ofanayo oyinkimbinkimbi:

Based on the provided data source, I cannot provide a complete analysis of 
high-priory support cases and their frequency patterns. While there are support 
cases mentioned in the data from January 2024, the data does not contain 
sufficient information about case priorities or enough cases per account 
to identity patterns meeting the threshold of more than 3 cases. 
Additionally, while some technical and customer service cases are shown, 
the data is fragmented across different dates without providing a comprehensive 
view of case volumes or frequencies per account and service.

Lezi zibonelo zibonisa ukuthi i-REG ilwenza kanjani kuphela ngemibuzo yokuhlaziya yobunzima obukhulayo, kanti isixazululo sethu se-plugin-ethuthukisiwe siletha isixazululo sethu sihambisa okuqondile, okuhlelekile kuwo wonke amazinga. Lapho usebenza ngezimo ezidinga ukuhlaziywa kwamanani eziqondile, singathuthukisa amakhono e-rag ngezindlela ezihlelekile:

• Ukuhlakulela nokuhlaziywa kwephethini: Lapho umsebenzisi ekhuthaza ukuhlanganisa imibuzo ehlanganisiwe (njengokubala, amanani, noma ukusatshalaliswa), adinga ukuhlanganiswa kwamanani okuqondile ngokubukwa okuhleliwe ukuhlinzeka ngemiphumela ehlelekile. Ukusesha okufanayo kwe-vector kukodwa akukwazi ukuqinisekisa ukuqina kwamanani aqondile, ukwenza i-metadata ehlelekile kubalulekile kubaluleke ngalezi zimo zokuhlaziya.
• Ukuhlaziywa komongo nokuxhumanisa: Idatha engahleliwe yangaphandle idinga ubunjiniyela bedatha abacabangayo ukuze bakhiphe futhi balondoloze i-metadata ehlelekile (njengezinsuku zokudala, izigaba, amazinga wobude, nezinhlobo zesevisi). Ngenkathi i-rag idlula ekutholeni okuqukethwe okufanayo ngezikhathi, i-metadata echazwe kahle inika amandla ukuhlunga okuqondile namakhono okubuza. Isibonelo, lapho uhlaziya izingqinamba zokusebenza kohlelo, i-metadata ehlelekile mayelana nesikhathi sezehlakalo, izinsizakalo ezithintekile, futhi ukuncika kwazo kunika amandla ukuhlaziya umthelela ophelele ngokuhambisana nokufanisa okuqondile.

Ukuthuthukisa i-Q Support-Insights nge-Agentic AI

Ukwakha kwisixazululo se-Q Quaption-Insights (QSI) kwethulwa ekubukeni okusebenzayo nokusebenza okusebenzayo kusuka kuma-AWS usebenzisa i-Amazon Q Ibhizinisi, sizokhombisa ukuthi singathuthukisa kanjani amakhono okuhlaziya nge-agentic ai ngokwakha ama-plugins angokwezifiso. Lokhu kuthuthukiswa kugcina ukuqaliswa kwesisekelo kwe-QSI ngenkathi kwengeza ukucubungula kokuhlaziya okuqondile ngokuhleleka okuhleliwe kwe-metadata.

Ukubuka konke kwe-QSI

Isixazululo se-Amazon Q Supports (QSi) siqukethe izingxenye ezimbili eziphambili:

1. Ukuqoqwa kwedatha Iphini libe line
   • Imodyuli yokuqongelela iqoqo le-AWS Lambda
   • Imininingwane yokusekelwa iqukethe amacala okusekela ama-AWS, imicimbi yezempilo, kanye namasheke we-Advisor athembekile
   • I-Amazon IzinkundlaBridge zokuqoqwa kwedatha ezenzakalelayo. I-Pipeline yedatha inika amandla izindlela zokuvumelanisa ezimbili:
     • Ukuvuselelwa kwamacala wesikhathi sangempela: Icubungula amacala okusekela ama-AWS ngokusebenzisa izimbangela ezenzelwe umcimbi (CreateCase, AddCommunicationToCase, ResolveCase, ReopenCase).
     • Ukuvumelanisa okungokomlando nokuhlanzekile: Yenza ukuvumelanisa kwedatha yokuqala yomlando futhi kuvuselela idatha ye-AWS ethembekile yezeluleko nsuku zonke.
   • Igcina idatha ngefomethi ye-JSON in Centrang Imazon Isitoreji Service (I-Amazon S3) Ibhakede
   • Isekela ukuhlanganiswa kwedatha ye-akhawunti eminingi ngezinhlangano ze-AWS
2. Imvelo yesicelo sebhizinisi le-Amazon Q
   • Ukuhanjiswa kwesicelo sebhizinisi le-Amazon Q
   • Isixhumi se-Amazon S3 sokuhlanganiswa komthombo wedatha
   • Ukucushwa kwesipiliyoni sewebhu sokusebenzisana komsebenzisi
   • Ukufakazelwa ubuqiniso ngokusebenzisa isikhungo se-AWS IAM

Inika amandla ukuhlanganiswa kwemibuzo ngama-plugins wangokwezifiso we-Amazon Q

Ama-plugins ngokwezifiso anweba ibhizinisi le-Amazon Q ukuhlanganisa ukusesha kwe-semantic ngamakhono okuhlaziya okuqondile. Imininingwane elandelayo yokuqalisa imininingwane elandelayo sikufinyelela kanjani isixazululo se-QSI QSI:

• Ukusebenza kwe-Augssion QSA kwemvelo kolimi lwemvelo ngamakhono obukhono obuhleliwe
• Iguqula izicelo zokuhlaziya zibe yinto eqondile ye-Amazon Athena SQL esebenzisa imodeli enkulu yezilimi ezinkulu (LLM)
• Ukhipha imibuzo ngokumelene namatafula we-metadata ahlelekile
• Ihlinzeka ngemiphumela eqondile yezinombolo eceleni kwezimpendulo zokucinga ze-semantic

Ukucutshungulwa kweMetadata

Ukuze sikwazi ukwenza amakhono okubumbana okuqondile, sisebenzise uhlaka lokucubungula iMetadata oluqinile lezo zinhlaka kanye nedatha yokusekela izinkomba:

• Usebenzisa iqoqo ledatha le-QSI ekhona e-Amazon S3
• Kukhishwe i-metadata ehlelekile kusuka kumacala okusekela ematafuleni amabili acishe abumbeka
• Igcina izinkambu ezibucayi njengezinsuku, izigaba, amazinga wobude
• Inika amandla ukuhlunga okuqondile kanye namandla okuhlanganisa

Ukuhlaziywa komthombo wokuwela umthombo

Isixazululo sinika amandla ukuhlaziya okuphelele emithonjeni yedatha eminingi ngamakhono okuqondanisa ahlakaniphile:

• Izixhumanisi zisekela amacala anemicimbi yezempilo
• Inika amandla ukuhlolwa okuphelele kokusebenza
• Isekela ukutholwa kwamaphethini kuyo yonke imithombo yedatha eminingi

Ukubuka konke kwezakhiwo

Lo mfanekiso olandelayo ukhombisa ukuthi isixazululo esithuthukisiwe se-Amazon q sihlanganisa kanjani ama-plugins ngokwezifiso ane-QSI yokwakha ekhona. Umdwebo ukhombisa ukugeleza okuvela kumbuzo womsebenzisi ngokusebenza kokuhlaziya ekuphenduleni kwesizukulwane, ukugqamisa ukuthi ihlelwe kanjani idatha yedatha esetshenziselwa ukusesha okusekelwe ku-semantic.

Lapho umsebenzisi ehambisa umbuzo wokuhlaziya njenge Show me OpenSearch case distribution based on severityinqubo elandelayo yenzeka:

1. I-plugin yangokwezifiso ithola inhloso yokuhlaziya futhi ibangele umsebenzi we-lambda
2. Umsebenzi weLambda usebenzisa i-Amazon Bedrock LLM ukuguqula umbuzo wolimi lwemvelo ube ngokuqondile athena sql
3. Umbuzo ukhipha ngokumelene ne-metadata ehlelekile e-Athena
4. Imiphumela ihlelwe emuva ngolimi lwemvelo futhi yethulwe eceleni kwezimpendulo zendabuko zendabuko

Le ndlela inika amandla ama-analytics aqondile ngenkathi egcina abasebenzisi be-interface interface balindele.

Isibonelo sokuqalisa

Nakhu ukusebenzisana okuyisampula okubonisa amakhono athuthukisiwe. Ake siqale ngombuzo oyisisekelo ukuze uqonde ivolumu ye-OpenSearch Case ephelele, kusetshenziswa ukubuya kwedatha okuhlelekile:

QAPHELA:

Give me OpenSearch cases in Jan 2025

Impendulo:

Based on the query results for OpenSearch cases in January 2025, here's a summary:
1. Total cases: 15
2. Severity breakdown:
Critical: 4 cases
High: 3 cases
Urgent: 1 case
Normal: 3 cases
Low: 2 cases
3. Status: All cases are resolved
4. Most common issues:
Cluster health problems (yellow status)
Blue/Green deployment issues
Performance concerns (high CPU utilization)
5. Services involved:
OpenSearch Service Managed Cluster: 13 cases
OpenSearch Service Ingestion: 2 cases

The cases span various topics including cluster health, deployments, performance, 
and configuration issues. Is there a specific aspect of these cases you'd like 
more information on?

Manje, usebenzisa amakhono we-rag ukuhlaziya okuqukethwe kwecala elingahleliwe ngokuqonda kwezakhiwo:

QAPHELA:

Out of these, what are the OpenSearch issues that are related to architecture 
deficiencies? 

Impendulo:

Based on the available data, several architectural issues have been identified in OpenSearch deployments:

* The shard count per node exceeding recommended limits is a significant 
architectural concern, with validation errors occurring when scaling up 
node counts. The recommended limit is 1,000 shards per node and exceeding 
this requires careful architectural planning. 

* Master node scaling is another architectural challenge, where insufficient 
master node capacity can limit cluster expansion. This requires proper 
configuration of master node instance types according to the number of nodes 
and shards in the domain. 

* Resource utilization issues, particularly around JVM Memory Pressure and 
CPU utilization, indicate potential architectural shortcomings. 
The system architecture should be designed to maintain JVM Memory Pressure 
below 80% and CPU Utilization below 85% for optimal performance. 

* The system's handling of blue/green deployments shows architectural limitations, 
as these operations cause performance impacts and increased latency during data 
migration to new nodes. 

Ukuqhubeka nokuhlaziywa okususelwa ku-rag kwemininingwane yamacala ukuhlola amaphethini wokuqalisa:

QAPHELA:

Given the high shard count, JVM, or other data can we make inferences about whether 
they are using this correctly?

Impendulo:

Based on the data discussed, there are strong indicators that the OpenSearch system 
is not being used optimally:

JVM Memory Management Issues:
1. Memory pressure consistently exceeded recommended thresholds (above 78% and 
eventually over 90%)
2. The 64GB initial heap size configuration proved inadequate for the workload
3. Circuit breaking exceptions and cluster blocks occurred due to memory issues

Shard Management Problems:
1. The system appears to have exceeded the recommended limit of 1,000 shards 
per node
2. Too many small shards created unnecessary system strain
Large shards complicated failure recovery processes

Resource Utilization:
1. Failed to maintain recommended thresholds:
2. JVM Memory Pressure should be below 80%
3. CPU Utilization should be below 85%
4. Continuous memory pressure issues

Failed snapshots
These indicators strongly suggest improper sizing and resource allocation for 
the workload, pointing to incorrect implementation or configuration of the 
OpenSearch system. Better capacity planning and adherence to best practices 
would be necessary for optimal performance.

Ekugcineni, nazi esinye isibonelo sokuhlaziywa kwedatha okuhlelekile ngombuzo oyinkimbinkimbi obonisa amakhono ahlanganisiwe ahlukahlukene:

QAPHELA:

For high-severity support cases since January 1, 2024, show the number of 
total cases and after-hours cases for each account and service combination. 
Define after-hours as before 1 PM UTC, after 1 AM UTC, or times falling within 
the weekend. Only include results with more than 3 after-hours cases. Sort by 
the highest number of after-hours cases. Exclude limit increase requests.

Impendulo:

Based on the analysis of high-severity support cases since January 1, 2024, 
here's a summary of the results, focusing on accounts and services with more 
than 3 after-hours cases:

1. The account with the highest number of after-hours cases (48) is 111111111111, 
for the Connect service. They have a total of 66 high-severity cases.
2. The second highest is account 333333333333 with 40 after-hours cases for the 
OpenSearch Service Managed Cluster, out of 49 total cases.
3. Account 222222222222 has 38 after-hours cases for RDS Oracle, out of 64 
total cases.
4. EMR service for account 555555555555 has 19 after-hours cases out of 23 
total cases.
5. Bedrock service for account 666666666666 has 17 after-hours cases out of 
24 total cases.

The results are sorted by the highest number of after-hours cases, and limit 
increase requests have been excluded as requested. After-hours cases are 
defined as those created before 1 PM UTC, after 1 AM UTC, or times falling 
within the weekend.

Would you like more details on a specific account or service, or do you need 
a further analysis of this data?

Impendulo ihlanganisa ukucubungula okuyinombolo okuqondile ngokuqonda kwe-semantic, ukuhlinzeka ngokuqonda okusebenzisekayo kokubuyekezwa okusebenzayo.

Izinzuzo nomthelela

Le plugin Architecture iletha ukuthuthuka okuningana okubalulekile:

• I-Analytics Eqondile: Ukubalwa okuqondile nokusatshalaliswa kufaka phakathi ukufana okulinganiselwe kwe-semantic
• Ukuhlaziywa Kweqiniso: Igcina umongo wokuhlaziya emintanjeni yengxoxo
• Ukuqonda kwezakhiwo: Ukuhlangana okungcono kwezinkinga ezihlobene ngokuhlaziywa okuhleliwe

Sebenzisa uhlelo lwebhizinisi le-Amazon Q

Okulandelayo inqubo eyenziwe lula ukuthunyelwa. Ngemiyalo enemininingwane, bheka imodyuli ye-Amazon Q yebhizinisi lebhizinisi.

Izimfuneko

1. I-AWS Cloudshell inconyelwe kusukela lapho, iza kuqala ifakwe nemitapo yolwazi edingekayo namathuluzi. Ngenye indlela, ungasebenzisa umshini wendawo nge-AWS Command Line Interface (AWS CLI) efakiwe futhi amisiwe ngeziqinisekiso ezivumelekile.
2. Amabhakede amabili e-S3:
   • Ukusekelwa kwebhakede ledatha lokugcina idatha yokusekelwa kwe-AWS
   • Ibhakede lezinsizakusebenza njengezitoreji zesikhashana zezinsizakusebenza ze-Lambda zokuhanjiswa (zingasuswa ngemuva kokuthunyelwa)
3. Isikhungo se-Iam Botneinent Center silungiselelwe
4. Isixazululo sidinga idatha yokusekela ama-AWS eqoqwe kusetshenziswa ipayipi ledatha yokusekelwa. Ungathumela manje bese wengeza idatha ngokuhamba kwesikhathi, kepha ukusebenza kuncike ekutholakaleni kwedatha kubhakede lakho le-S3.
5. Ukufinyelela ifu lika-Anthropic 3-5 Sonnet nge-Amazon Bedrock. Bona okungeziwe noma susa ukufinyelela kuma-Amazon Bedrock Foundation Models
6. Le khasi default Database kufanele ibe khona e-Athena. Uma kungenjalo, ungakha eyodwa usebenzisa umhleli we-Athena umbuzo ukudala database.

Izinyathelo Zokuphambanisa

Ungasisebenzisa umbhalo olandelayo ukuze usebenzise isisombululo se-Q. Azikho izinyathelo ezenziwa ngesandla – Umbhalo uphatha ukudala isitaki nokucushwa ngokuzenzakalelayo.

# Clone the repository
git clone 
cd q_application
chmod +x deploy_q_stacks.sh
./deploy_q_stacks.sh

Hlanza

Ukususa izinsizakusebenza, susa amabhakede we-S3 nezitaki ze-Cloudformation. Susa izitaki ze-Cloudformation nge-oda elilandelayo:

1. case-metadata-stack
2. amazon-q-stack
3. custom-plugin-stack

Qaphela ukuthi lokhu ngeke kususe amabhakede akhona we-S3, kufanele ususe ngesandla amabhakede e-S3.

Ukugcina

Ngokuhlanganisa ukuqonda kwe-semantic ye-rag ngamakhono okuhlaziya okuqondile ngama-plugins, siguqule ibhizinisi le-Amazon q libe yiplatifomu enamandla yokuhlaziya. Ezibonelweni kulokhu okuthunyelwe, ungabona ukuthi izinhlangano zingasisebenzisa kanjani lesi sithuthukisi ukuze sithole ukuqonda okunembile futhi okusebenzayo kusuka kudatha yokwesekwa kwemisha, ukusekela ukulungiswa kwezinqumo ngezinqumo ezisebenzayo kanye nokulungiswa kwemali okusebenzayo. Ngenkathi kuboniswa nge-Support Data Analytics yokuthuthuka okusebenzayo, la maphethini asebenza kuzo zonke izizinda ezihlanganisa imithombo yedatha ehlelekile nengahleliwe.

Funda kabanzi

• Hlola imibhalo ye-Amazon Q ukuqonda okuningi mayelana nokwakha ama-plugins ngokwezifiso
• Bheka lezi zinsiza ezihlobene:

Ngemibuzo kanye nempendulo, vakashela ama-AWS Re: Thumela noma Xhumana nokwesekwa kwe-AWS.

Mayelana nababhali

IChitresh saxena Unguchwepheshe we-SR. AI / ML onguchwepheshe we-tam okhethekile ezixazululweni ze-ai generative futhi ezinikezelwe ekusizeni amakhasimende atholele ngempumelelo i-AI / ML ngempumelelo kuma-AWS. Udlula ekuqondeni amakhasimende adingayo futhi anikeze ukuqondiswa kwezobuchwepheshe ukwakha, ukwethula, kanye nezixazululo ze-AI AI ezixazulula izinkinga eziyinkimbinkimbi zebhizinisi.

UKevin Morgan Imenenja yokweseka i-SR. Enterprise kuma-AWS asiza amakhasimende asheshise uhambo lwawo lokutholwa kwamafu ngokusebenzisa ubuholi kanye nokuholwa kwezobuchwepheshe. Njengelungu lesipiliyoni sonjiniyela esilandelayo se-TFC, ubheka okuhlangenwe nakho komakhi, amafule Ngaphandle komsebenzi, uKevin uyakujabulela ukuba yinkosi yomdlalo we-D & D futhi ungumdlandla we-retro compling.