** Gudanar da Kayan Aiki na atomatik tare da StackGen da LangChain: Haɓaka Ma'aikatan AI da Samfuran Samfura don Tsararren DevOps Automation da Gudanar da Kayayyakin Kayayyakin Kayayyakin Ciniki**
** Gabatarwa ***
A cikin shimfidar wuri mai sauri na dijital na yau, buƙatun sarrafa kayan aiki mai inganci da daidaitawa bai taɓa yin girma ba. Ayyukan DevOps na al'ada galibi suna dogara da tsarin aiki da rubutun hannu, wanda zai iya haifar da kurakurai, rashin daidaituwa, da ƙulli. Don magance waɗannan ƙalubalen, muna shaida bullar ƙungiyoyin samar da ababen more rayuwa masu cin gashin kansu, tsarin da ke ba da damar yin amfani da wakilai na AI da ƙirar ƙira don sarrafa kai da haɓaka sarrafa kayan more rayuwa. A cikin wannan labarin, za mu shiga cikin duniya mai ban sha'awa na StackGen da LangChain, fasahohi guda biyu masu yanke hukunci waɗanda ke kawo sauyi kan yadda muke sarrafa abubuwan more rayuwa.
** Menene StackGen?**
StackGen shine tushen bude-bude, girgije-agnostic ingantattun kayan aikin tsararru wanda ke ba da damar ƙirƙirar warkar da kai, ƙwanƙwasa kai, da haɓaka abubuwan more rayuwa. An gina shi a saman tsarin gine-gine na zamani, StackGen yana ba masu haɓakawa damar ayyana saitunan abubuwan more rayuwa ta amfani da babban matakin, ƙirar magana. Sannan ana fassara wannan ma'anar cikin ayyukan samar da ababen more rayuwa da ayyukan gudanarwa, waɗanda injin da aka rarrabawa ke aiwatar da su.
** Menene LangChain?**
LangChain ɗakin karatu ne na Python wanda ke ba da haɗin kai don ginawa da haɗa wakilan AI, ƙirar ƙira, da sauran abubuwan koyon injin cikin tsarin software. Ta hanyar yin amfani da LangChain, masu haɓakawa na iya ƙirƙirar ƙaƙƙarfan aikace-aikacen AI-kore waɗanda ke koyo daga bayanai, daidaitawa ga yanayin canza yanayin, da yanke shawara. A cikin mahallin StackGen, LangChain yana ba da damar haɗakar wakilai na AI waɗanda za su iya nazarin ayyukan abubuwan more rayuwa, tsinkaya abubuwan da ba su da kyau, da ɗaukar matakan gyara don kula da ingantaccen tsarin tsarin.
** Ƙirƙirar kayan more rayuwa mai zaman kanta tare da StackGen da LangChain ***
Don kwatanta ikon StackGen da LangChain, bari mu ɗauki misali mai sauƙi. A ce muna gina dandamali na e-kasuwanci na tushen gajimare wanda ke buƙatar ma'auni mai ƙima, babban kayan aiki. Yin amfani da StackGen, za mu iya ayyana wani babban tsari wanda ke ƙayyadad da abubuwan abubuwan da ake so, gami da adadin nodes, nau'ikan misali, da saitunan cibiyar sadarwa.
`` Python
suna: e-commerce-platform bayanin: Kayan aikin dandamali na e-kasuwanci Shafin: 1.0
sassa:
- suna: uwar garken yanar gizo Saukewa: EC2 Properties: misali-nau'in: t2.micro ami: abc123 kungiyoyin tsaro: [web-server-sg]
- suna: database nau'in: RDS Properties: misali-nau'in: db.t2.micro engine: postgres database-name: e-commerce-db sunan mai amfani: e-commerce-user kalmar sirri: e-commerce-password
dangantaka:
- uwar garken yanar gizo -> database
A cikin wannan misali, mun bayyana ma'auni mai sauƙi na kayan aikin da ya ƙunshi sabar yanar gizo da kuma bayanan bayanai. Sashin 'bangaren' yana ƙayyadaddun abubuwan haɗin kai, gami da nau'ikan su, kaddarorinsu, da alaƙa. Sashin 'dangantaka' yana bayyana haɗin kai tsakanin abubuwan haɗin gwiwa.
Na gaba, za mu yi amfani da LangChain don haɗawa da wakilin AI wanda zai iya nazarin ayyukan ababen more rayuwa da ɗaukar matakan gyara don kula da mafi kyawun halayen tsarin. Za mu ƙirƙiri wakilin AI mai sauƙi wanda ke sa ido kan yadda ake amfani da CPU kuma yana daidaita nau'ikan misali daidai.
`` Python
# LangChain AI lambar wakili (ai_agent.py)
shigo da langchain
daga langchain.agents shigo da BaseAgent
aji ECommerceAgent(BaseAgent):
def __init__(kai, stackgen_config):
self.stackgen_config = stackgen_config
self.cpu_utilization_threshold = 80
def Monitor_infrastructure(kai):
# Kula da amfani da CPU kuma daidaita nau'ikan misali
cpu_utilization = self.get_cpu_utilization()
idan cpu_utilization> self.cpu_utilization_threshold:
nau'ikan_daidaita_daidaita_()
def adjust_intance_types(kai):
# Daidaita nau'ikan misali dangane da amfani da CPU
Misali_types = self.get_intance_types()
misali_type a cikin misalai_types:
idan misalin_type['cpu_utilization']> self.cpu_utilization_threshold:
Misali_type['misali_type'] = 't2.large'
# Haɗa wakilin AI tare da StackGen
stackgen_config = load_yaml ('example.yaml')
ai_agent = ECommerceAgent(stackgen_config)
ai_agent.monitor_infrastructure()
A cikin wannan misalin, mun ƙirƙiri wakili na AI mai sauƙi wanda ke sa ido kan yadda ake amfani da CPU kuma yana daidaita nau'ikan misali daidai. Mun haɗa wakilin AI tare da StackGen ta amfani da ɗakin karatu na 'langchain', wanda ke ba da haɗin kai don ginawa da haɗa wakilan AI.
** Manyan Dokoki 5-10 da Akafi Amfani da su/Snippets**
Anan akwai wasu umarni da snippets da aka fi amfani da su don StackGen da LangChain:
- ** Fayil na Kanfigareshan StackGen**:
stackgen config example.yaml - LangChain AI Agent Code:
langchain ai_agent.py - ** Haɗa Wakilin AI tare da StackGen **:
langchain haɗa ai_agent.py misali.yaml - ** Kula da Kayan Aiki **:
ai_agent.monitor_infrastructure() - ** Daidaita Nau'in Misali **:
ai_agent.daidaita_iri () - Samu Amfanin CPU:
ai_agent.get_cpu_utilization() - Samu Nau'in Misali:
ai_agent.get_instance_types() - Load YAML Configuration File:
load_yaml('example.yaml') - Ajiye fayil ɗin Kanfigareshan YAML:
save_yaml('example.yaml', stackgen_config) - Yi hangen nesa da kayan aikin kayan more rayuwa:
stackgen visualize example.yaml
Kallon gani
Don ganin abubuwan abubuwan more rayuwa, zamu iya amfani da ɗakin karatu kamar graphviz don yin jadawali dangane da fayil ɗin StackGen.
{
"type": "bar",
"data": {
"labels": ["Sabar Yanar Gizo", "Database"],
"datasets": [
{
"label": "Amfani da CPU",
"bayanai": [80, 90],
"backgroundColor": ["rgba (255, 99, 132, 0.2)", "rgba (54, 162, 235, 0.2)"],
"BorderColor": ["rgba (255, 99, 132, 1)", "rgba (54, 162, 235, 1)"],
"BorderWidth": [1, 1]
}
]
},
"zaɓi": {
"take": {
"nuna": gaskiya,
"text": "Amfani da Kwamfuta na CPU"
},
"ma'auni": {
"yAxes": [
{
"nuna": gaskiya,
"Label": {
"nuna": gaskiya,
"labelString": "Amfani da CPU (%)"
}
}
]
}
}
}
Wannan ginshiƙi yana hango yadda ake amfani da CPU na sabar gidan yanar gizo da abubuwan haɗin bayanai, yana ba da fayyace ra'ayi game da ayyukan ababen more rayuwa.
Kammalawa
Ƙaddamar da abubuwan more rayuwa masu cin gashin kansu tare da StackGen da LangChain wani tsari ne mai ƙarfi wanda ke ba da damar ƙirƙirar warkar da kai, ƙwanƙwasa kai, da haɓaka abubuwan more rayuwa. Ta hanyar yin amfani da wakilai na AI da ƙirar ƙira, masu haɓakawa za su iya sarrafa kansa da haɓaka aikin sarrafa kayan more rayuwa, rage kurakurai, rashin daidaituwa, da ƙulli. A cikin wannan labarin, mun bincika ainihin abubuwan StackGen da LangChain, gami da gine-ginen su, fayilolin daidaitawa, da haɗin gwiwar wakilin AI. Mun kuma ba da misalai masu amfani da snippets na lamba don kwatanta ƙarfin waɗannan fasahohin. Yayin da ake ci gaba da haɓaka buƙatun sarrafa kayan aiki masu inganci da ƙima, StackGen da LangChain sun shirya don taka rawar gani a nan gaba na DevOps da sarrafa kayan more rayuwa.