Bangun agen Tanya & Jawab secara cepat menggunakan kagent - Container Service for Kubernetes

Panduan ini menjelaskan cara menerapkan agen Question & Answer (Tanya & Jawab) menggunakan Kagent. Agen tersebut memanfaatkan model qwen3-coder-plus dari Alibaba Cloud Model Studio dan layanan Model Context Protocol (MCP) fetch untuk mengambil serta merangkum konten halaman web secara real time.

Persiapan

Buat namespace bernama kagent di kluster ACK Anda.
Pasang aplikasi kagent-crds dan kagent di namespace kagent melalui Marketplace ACK atau menggunakan Applications > Helm.
Aktifkan Alibaba Cloud Model Studio dan buat kunci API.

Langkah 1: Buat ModelConfig

Dapatkan KubeConfig kluster Anda dan gunakan kubectl untuk terhubung ke kluster. Jika kluster Anda tidak memiliki akses jaringan publik yang diaktifkan, Anda dapat menggunakan Workbench untuk terhubung ke kluster melalui jaringan internal. Di halaman Cluster Information, klik Manage Clusters Using Workbench di pojok kanan atas.

Ekspor kunci API Model Studio Anda sebagai variabel lingkungan dan buat Secret di namespace kagent.

export PROVIDER_API_KEY=${Your_Model_Studio_API_Key}
kubectl create secret generic bailian-apikey -n kagent --from-literal credential="$PROVIDER_API_KEY"

Terapkan YAML berikut untuk membuat resource ModelConfig. Provider diatur ke OpenAI karena Model Studio menyediakan API yang kompatibel dengan OpenAI.

kubectl -n kagent apply -f - <<EOF
apiVersion: kagent.dev/v1alpha2
kind: ModelConfig
metadata:
  name: bailian-provider-config
spec:
  model: qwen3-coder-plus
  apiKeySecret: bailian-apikey
  apiKeySecretKey: credential
  openAI:
    baseUrl: https://dashscope-intl.aliyuncs.com/compatible-mode/v1
  provider: OpenAI
EOF

Langkah 2: Terapkan server MCP `fetch`

Terapkan server MCP fetch di kluster ACK Anda.

kubectl -n kagent apply -f - <<EOF
apiVersion: apps/v1
kind: Deployment
metadata:
  name: streamablehttp-fetch-deployment
spec:
  replicas: 1
  selector:
    matchLabels:
      app: streamablehttp-fetch
  template:
    metadata:
      labels:
        app: streamablehttp-fetch
    spec:
      containers:
      - name: streamablehttp-fetch-container
        image: registry-cn-hangzhou.ack.aliyuncs.com/dev/streamablehttp-fetch:latest
---
apiVersion: v1
kind: Service
metadata:
  name: streamablehttp-fetch-service
spec:
  selector:
    app: streamablehttp-fetch
  ports:
    - protocol: TCP
      port: 3000
      targetPort: 3000
  type: ClusterIP
EOF

Langkah 3: Daftarkan Server MCP

Buat resource RemoteMCPServer untuk mendaftarkan layanan fetch ke Kagent. Resource ini memberi tahu sistem cara berkomunikasi dengan server MCP yang diterapkan pada langkah sebelumnya.

kubectl -n kagent apply -f - <<EOF
apiVersion: kagent.dev/v1alpha2
kind: RemoteMCPServer
metadata:
  name: streamablehttp-fetch
spec:
  description: A Model Context Protocol server that provides web content fetching capabilities. This server enables LLMs to retrieve and process content from web pages, converting HTML to Markdown for easier consumption.
  protocol: STREAMABLE_HTTP
  sseReadTimeout: 5m0s
  terminateOnClose: true
  timeout: 30s
  url: http://streamablehttp-fetch-service:3000/
EOF

Verifikasi bahwa server MCP berhasil didaftarkan dan diterima.

kubectl get RemoteMCPServer -n kagent

Output yang diharapkan:

NAME                   PROTOCOL          URL                                        ACCEPTED
streamablehttp-fetch   STREAMABLE_HTTP   http://streamablehttp-fetch-service:3000/   True

Langkah 4: Buat agen

Terapkan konfigurasi Agent.

kubectl -n kagent apply -f - <<EOF
apiVersion: kagent.dev/v1alpha2
kind: Agent
metadata:
  name: gateway-api-professor
  namespace: kagent
spec:
  declarative:
    modelConfig: bailian-provider-config
    stream: true
    systemMessage: |-
      You are a friendly and helpful agent. Use the streamablehttp-fetch tool to get GatewayAPI information from the following URLs to answer user questions about GatewayAPI.
      
      # Links
      - intro: https://gateway-api.sigs.k8s.io/
      - api-overview: https://gateway-api.sigs.k8s.io/concepts/api-overview/
      - use-case: https://gateway-api.sigs.k8s.io/concepts/use-cases/
      - servicemesh: https://gateway-api.sigs.k8s.io/mesh/
      - implementations: https://gateway-api.sigs.k8s.io/implementations/
      - v1.4 support overview: https://gateway-api.sigs.k8s.io/implementations/v1.4/
      - Full spec, large page: https://gateway-api.sigs.k8s.io/reference/spec/

      # Instructions

      - If a user's question is unclear, ask for clarification before running any tools.
      - Be friendly and enthusiastic in your responses to the user.
      - If you do not know how to answer a question, do not make up an answer.
        Reply with "Sorry, I don't know how to answer that question" and ask the user to clarify.
      - If the user asks for a summary or an overview, make sure to read the entire text before answering.

      # Response format
      - Always reply in Markdown format.
      - Your response must include a summary of the actions you performed and an explanation of the results.
    tools:
    - type: McpServer
      mcpServer:
        apiGroup: kagent.dev
        kind: RemoteMCPServer
        name: streamablehttp-fetch
        toolNames:
        - fetch
  description: This agent primarily answers questions related to the GatewayAPI specification.
  type: Declarative
EOF

Verifikasi bahwa agen dan komponen dependennya sedang berjalan.

kubectl get pod -n kagent