** Aiwatar da AI-Powered DevOps Automation tare da Kiro AI-Powered Agents da LangChain ***

** Gabatarwa ***

Yanayin DevOps yana ci gaba da sauri, tare da haɓaka haɓakar fasaha na wucin gadi (AI) da fasahar koyon injin (ML). Ɗaya daga cikin mahimman wuraren da AI ke yin tasiri mai mahimmanci shine a cikin DevOps aiki da kai. A cikin wannan labarin, za mu bincika aiwatar da fasaha na ma'aikatan AI a cikin DevOps aiki da kai, da mayar da hankali kan haɗin gwiwar Kiro AI-powered agents tare da LangChain don haɓaka kayan aiki da fasaha na fasaha.

** Menene Ma'aikatan Kiro AI-Powered?**

Ma'aikatan Kiro AI nau'in wakili ne na software wanda ke amfani da AI da ML algorithms don sarrafa ayyuka da yanke shawara. An tsara waɗannan wakilai don koyo daga bayanai da kuma daidaitawa ga canza yanayin yanayi, yana mai da su manufa don tsarin hadaddun da ƙarfi kamar bututun DevOps.

** Menene LangChain?**

LangChain ɗakin karatu ne na Python wanda ke ba da saitin kayan aiki da APIs don gina aikace-aikacen AI na tattaunawa. Yana ba masu haɓaka damar ƙirƙirar taɗi, mataimakan murya, da sauran hanyoyin tattaunawa ta amfani da sarrafa harshe na halitta (NLP) da algorithms koyon injin.

** Haɗa Ma'aikatan Kiro AI-Powered tare da LangChain ***

Don haɗa ma'aikatan Kiro AI masu ƙarfi tare da LangChain, muna buƙatar ƙirƙirar haɗin tattaunawa wanda zai iya yin hulɗa tare da wakilai da kuma samar musu da abubuwan da suka dace da abubuwan da suka dace. Anan ga babban bayyani na gine-ginen:

1. **Input mai amfani ***: Mai amfani yana hulɗa tare da mahaɗin tattaunawa, yana ba da labari ta hanyar rubutu ko murya.
2. ** Gudanar da Harshen Halitta (NLP): Ana aiwatar da shigarwar ta amfani da algorithms NLP don fitar da bayanai masu dacewa da niyya.
3. ** Zaɓin Wakilin ***: Ma'anar tattaunawa yana zaɓar madaidaicin wakili mai ƙarfi na Kiro AI dangane da shigarwar mai amfani da niyyar.
4. **Ma'amalar Agent ***: An kunna wakilin da aka zaɓa don yin ayyukan da suka dace, kamar sarrafa ayyuka ko yanke shawara.
5. **Fitowa ***: Ana sarrafa fitar da wakili kuma ana mayar da shi ga mai amfani ta hanyar tattaunawa.

Aikin Fasaha

Don aiwatar da wannan gine-gine, muna buƙatar yin amfani da haɗin haɗin Python, Tsatsa, da Harsunan shirye-shiryen Go. Anan ga ƙaƙƙarfan toshe lambar da ke nuna haɗin kai na Kiro AI-powered agents tare da LangChain: `` Python shigo da langchain daga Kiro shigo da Agent

chatbot = langchain.Chatbot( model="davinci:002", zafin jiki = 0.7, max_tokens=2048, user_agent = "Kiro AI-Powered Agent" )

Ƙirƙiri wakili mai ƙarfin Kiro AI

wakili = wakili ( suna = "Wakilina", description="Wakili mai sauƙi wanda ke sarrafa ayyuka", ayyuka=[ "umarnin gudu", "send_email", "ƙirƙiri_tikiti" ] )

Ƙayyade aiki don hulɗa tare da wakili

def interact_with_agent(input_text): # Gudanar da shigarwa ta amfani da NLP intent = langchain.extract_intent(input_text)

# Zaɓi wakilin da ya dace bisa niyya
idan niyya == "gudu_umarnin":
    agent.run_command()
elif nufin == "send_email":
    agent.send_email()
elif intent == "ƙirƙiri_tikitin":
    agent.create_ticket()

# Mayar da abin da wakili ya fitar
wakili mai dawowa.fitarwa

Gwada aikin

input_text = "Gudanar da rubutun ginin" fitarwa = interact_with_agent (input_text) buga (fitarwa)

Wannan toshe lambar yana nuna yadda ake ƙirƙirar chatbot na LangChain da wakili mai ƙarfi na Kiro AI, da kuma yadda ake hulɗa da wakili ta amfani da hanyar tattaunawa.

** Manyan Dokoki 5-10 da Akafi Amfani da su/Snippets**

Anan akwai wasu umarni da aka fi amfani da su da snippets don Kiro AI-powered agents da LangChain:

1. `langchain.Chatbot (samfurin = "davinci: 002", zafin jiki = 0.7, max_tokens = 2048, mai amfani_agent = "Kiro AI-Powered Agent")': Ƙirƙirar LangChain chatbot tare da ƙayyadaddun samfurin da sigogi.
2. `Agent (suna = "My Agent", description = "Wakili mai sauƙi wanda ke sarrafa ayyuka", ayyuka = ​​["gudu_umarni", "send_email", "create_ticket"])`: Yana ƙirƙira wakili mai ƙarfi na Kiro AI tare da ƙayyadadden suna, bayanin, da ayyuka.
3. `langchain.extract_intent(input_text)`: Yana aiwatar da rubutun shigarwa ta amfani da NLP don cire niyya.
4. `agent.run_command()`: Yana sa wakili ya gudanar da umarni.
5. `agent.send_email()`: Yana sa wakili ya aika imel.
6. `agent.create_ticket()`: Yana sa wakili ya ƙirƙiri tikitin.
7. `langchain.Chatbot().tambaya(input_text)`: Yayi wa chatbot tambaya kuma ya mayar da martani.
8. `langchain.Chatbot().gaya(input_text)`: Yana gaya wa chatbot bayani kuma ya mayar da martani.
9. `langchain.Chatbot().saurara()`: Yana sauraron shigarwar mai amfani kuma yana mayar da martani.
10. `langchain.Chatbot().stop()`: Tsaida chatbot kuma yana fitar da albarkatu.

**Kallon gani**

Anan ga sauƙin gani na gine-gine ta amfani da Chart.js:
Json
{
  "type": "pieChart",
  "data": {
    "labels": ["Input User", "NLP", "Zaɓin Wakili", "Ma'amalar Wakili", "Fitarwa"],
    "datasets": [
      {
        "label": "Architecture",
        "bayanai": [10, 20, 30, 40, 50],
        "Bayan launi": [
          "#FF6384",
          "#36A2EB",
          "#FFCE56",
          "#4BC0C0",
          "#FF99CC"
        ]
      }
    ]
  },
  "zabuka": {
    "take": {
      "nuna": gaskiya,
      "rubutu": "AI-Powered DevOps Automation Architecture"
    },
    "tatsuniya": {
      "nuni": gaskiya
    }
  }
}

Wannan hangen nesa yana nuna nau'ikan gine-gine daban-daban, gami da shigarwar mai amfani, NLP, zaɓin wakili, hulɗar wakili, da fitarwa.

Kammala

A cikin wannan labarin, mun bincika aiwatar da fasaha na ma'aikatan AI a cikin DevOps aiki da kai, suna mai da hankali kan haɗakar da ma'aikatan Kiro AI tare da LangChain don haɓaka kayan aiki da fasaha na fasaha. Mun nuna ƙaƙƙarfan toshe mai sauƙi wanda ke nuna haɗin kai na Kiro AI-powered agents tare da LangChain, kuma ya ba da jerin umarnin da aka fi amfani da su da snippets don Kiro AI-powered agents da LangChain. Mun kuma haɗa da hangen nesa na gine-gine ta amfani da Chart.js. Ta amfani da wakilai masu ƙarfin AI da mu'amalar tattaunawa, ƙungiyoyin DevOps na iya sarrafa ayyuka, haɓaka aiki, da rage kurakurai, sa DevOps aiki da kai mafi inganci da inganci.