Kubernetes infra (#1088)

* feat(chart): create kube infra

* feat(chart): create kube infra

* feat(chart): create kube infra

* feat(chart): create kube infra

* feat(chart): create kube infra

* feat(chart): create kube infra

* feat(chart): create kube infra

* feat(chart): create kube infra

* feat(chart): create kube infra

* feat(chart): create kube infra

* feat(chart): create kube infra

* feat(chart): create kube infra

* feat(chart): add hpa

* feat(chart): add service monitor

* feat(chart): test

* feat(chart): fix lint

* feat(chart): remove pm2

* feat(chart): fix

* feat(chart): fix

* feat(chart): fix

* feat(chart): fix

* feat(chart): fix

* feat(chart): fix

* feat(chart): fix

* feat(chart): fix

* feat(chart): fix

* feat(chart): fix

* feat(chart): fix

* feat(chart): fix

* feat(chart): fix

* feat(chart): fix

* feat(chart): fix

* update replicas count

* json logs

* use internal image for prod env

* Add LOG_LEVEL in prod yaml

* Get rid of unused staging env

* add an image build for internal registry

---------

Co-authored-by: Nathan Sarrazin <[email protected]>

.github/workflows/deploy-prod.yml

@@ -0,0 +1,69 @@
+name: Deploy to k8s
+on:
+  # run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+jobs:
+  build-and-publish-huggingchat-image:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Tailscale
+        uses: huggingface/tailscale-action@main
+        with:
+          authkey: ${{ secrets.TAILSCALE_AUTHKEY }}
+
+      - name: Extract package version
+        id: package-version
+        run: |
+          VERSION=$(jq -r .version package.json)
+          echo "VERSION=$VERSION" >> $GITHUB_OUTPUT
+          MAJOR=$(echo $VERSION | cut -d '.' -f1)
+          echo "MAJOR=$MAJOR" >> $GITHUB_OUTPUT
+          MINOR=$(echo $VERSION | cut -d '.' -f1).$(echo $VERSION | cut -d '.' -f2)
+          echo "MINOR=$MINOR" >> $GITHUB_OUTPUT
+
+      - name: Docker metadata
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: |
+            ghcr.io/huggingface/chat-ui
+          tags: |
+            type=raw,value=${{ steps.package-version.outputs.VERSION }},enable=${{github.event_name == 'release'}}
+            type=raw,value=${{ steps.package-version.outputs.MAJOR }},enable=${{github.event_name == 'release'}}
+            type=raw,value=${{ steps.package-version.outputs.MINOR }},enable=${{github.event_name == 'release'}}
+            type=raw,value=latest,enable={{is_default_branch}}
+            type=sha,enable={{is_default_branch}}
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to Registry
+        uses: docker/login-action@v2
+        with:
+          registry: registry.internal.huggingface.tech
+          username: ${{ secrets.DOCKER_INTERNAL_USERNAME }}
+          password: ${{ secrets.DOCKER_INTERNAL_PASSWORD }}
+
+      - name: Build and Publish Docker Image without DB
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: Dockerfile
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          platforms: linux/amd64
+          cache-to: type=gha,mode=max,scope=amd64
+          cache-from: type=gha,scope=amd64
+          provenance: false
+          build-args: |
+            INCLUDE_DB=false
+            APP_BASE=/chat
+            PUBLIC_APP_COLOR=yellow

.github/workflows/deploy-release.yml

@@ -1,4 +1,4 @@
-name: Deploy to production
+name: Deploy to production spaces
 on:
   # run this workflow manually from the Actions tab
   workflow_dispatch:

.github/workflows/deploy-staging.yml

@@ -1,24 +0,0 @@
-name: Deploy to staging environment
-on:
-  push:
-    branches: [main]
-
-  # to run this workflow manually from the Actions tab
-  workflow_dispatch:
-
-jobs:
-  sync-to-hub:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check large files
-        uses: ActionsDesk/[email protected]
-        with:
-          filesizelimit: 10485760 # this is 10MB so we can sync to HF Spaces
-      - uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
-          lfs: true
-      - name: Push to hub
-        env:
-          HF_DEPLOYMENT_TOKEN: ${{ secrets.HF_DEPLOYMENT_TOKEN }}
-        run: git push https://nsarrazin:[email protected]/spaces/huggingchat/chat-ui-staging main

.prettierignore

@@ -3,6 +3,7 @@ node_modules
 /build
 /.svelte-kit
 /package
+/chart
 .env
 .env.*
 !.env.example

chart/Chart.yaml

@@ -0,0 +1,5 @@
+apiVersion: v2
+name: chat-ui
+version: 0.0.0-latest
+type: application
+icon: https://huggingface.co/front/assets/huggingface_logo-noborder.svg

chart/env/prod.yaml

@@ -0,0 +1,333 @@
+image:
+  repository: registry.internal.huggingface.tech/chat-ui
+  name: chat-ui
+
+nodeSelector:
+  role-hub-utils: "true"
+
+tolerations:
+  - key: CriticalAddonsOnly
+    operator: Equal
+    
+ingress:
+  path: "/chat"
+  annotations:
+    external-dns.alpha.kubernetes.io/hostname: "chat-ui.hub-alb.huggingface.tech"
+    alb.ingress.kubernetes.io/healthcheck-path: "/healthcheck"
+    alb.ingress.kubernetes.io/listen-ports: "[{\"HTTP\": 80}, {\"HTTPS\": 443}]"
+    alb.ingress.kubernetes.io/group.name: "hub-prod"
+    alb.ingress.kubernetes.io/scheme: "internet-facing"
+    alb.ingress.kubernetes.io/ssl-redirect: "443"
+    alb.ingress.kubernetes.io/tags: "Env=prod,Project=hub,Terraform=true"
+    alb.ingress.kubernetes.io/target-node-labels: "role-hub-utils=true"
+    kubernetes.io/ingress.class: "alb"
+
+envVars:
+  ALTERNATIVE_REDIRECT_URLS: '["huggingchat://login/callback"]'
+  APP_BASE: "/chat"
+  ENABLE_ASSISTANTS: "true"
+  ENABLE_ASSISTANTS_RAG: "true"
+  EXPOSE_API: "true"
+  MESSAGES_BEFORE_LOGIN: 0
+  METRICS_PORT: 5565
+  LOG_LEVEL: "debug"
+  MODELS: >
+    [
+      {
+        "name" : "CohereForAI/c4ai-command-r-plus",
+        "tokenizer": "Xenova/c4ai-command-r-v01-tokenizer",
+        "description": "Command R+ is Cohere's latest LLM and is the first open weight model to beat GPT4 in the Chatbot Arena!",
+        "modelUrl": "https://huggingface.co/CohereForAI/c4ai-command-r-plus",
+        "websiteUrl": "https://docs.cohere.com/docs/command-r-plus",
+        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/cohere-logo.png",
+        "parameters": {
+          "stop": ["<|END_OF_TURN_TOKEN|>"],
+          "truncate" : 28672,
+          "max_new_tokens" : 4096,
+          "temperature" : 0.3
+        },
+        "promptExamples" : [
+          {
+            "title": "Write an email from bullet list",
+            "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
+          }, {
+            "title": "Code a snake game",
+            "prompt": "Code a basic snake game in python, give explanations for each step."
+          }, {
+            "title": "Assist in a task",
+            "prompt": "How do I make a delicious lemon cheesecake?"
+          }
+        ]
+      },
+      {
+        "name" : "meta-llama/Meta-Llama-3-70B-Instruct",
+        "description": "Generation over generation, Meta Llama 3 demonstrates state-of-the-art performance on a wide range of industry benchmarks and offers new capabilities, including improved reasoning.",
+        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/meta-logo.png",
+        "modelUrl": "https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct",
+        "websiteUrl": "https://llama.meta.com/llama3/",
+        "tokenizer" : "philschmid/meta-llama-3-tokenizer",
+        "promptExamples" : [
+          {
+            "title": "Write an email from bullet list",
+            "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
+          }, {
+            "title": "Code a snake game",
+            "prompt": "Code a basic snake game in python, give explanations for each step."
+          }, {
+            "title": "Assist in a task",
+            "prompt": "How do I make a delicious lemon cheesecake?"
+          }
+        ],
+        "parameters": {
+          "stop": ["<|eot_id|>"],
+          "truncate": 6144,
+          "max_new_tokens": 2047
+        }
+      },
+      {
+        "name" : "HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1",
+        "tokenizer": "HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1",
+        "description": "Zephyr 141B-A35B is a fine-tuned version of Mistral 8x22B, trained using ORPO, a novel alignment algorithm.",
+        "modelUrl": "https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1",
+        "websiteUrl": "https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1",
+        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/zephyr-logo.png",
+        "parameters": {
+          "truncate" : 24576,
+          "max_new_tokens" : 8192,
+        },
+        "preprompt" : "You are Zephyr, an assistant developed by KAIST AI, Argilla, and Hugging Face. You should give concise responses to very simple questions, but provide thorough responses to more complex and open-ended questions. You are happy to help with writing, analysis, question answering, math, coding, and all sorts of other tasks.",
+        "promptExamples" : [
+          {
+            "title": "Write a poem",
+            "prompt": "Write a poem to help me remember the first 10 elements on the periodic table, giving each element its own line."
+          }, {
+            "title": "Code a snake game",
+            "prompt": "Code a basic snake game in python, give explanations for each step."
+          }, {
+            "title": "Assist in a task",
+            "prompt": "How do I make a delicious lemon cheesecake?"
+          }
+        ]
+      },
+      {
+        "name" : "mistralai/Mixtral-8x7B-Instruct-v0.1",
+        "description" : "The latest MoE model from Mistral AI! 8x7B and outperforms Llama 2 70B in most benchmarks.",
+        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/mistral-logo.png",
+        "websiteUrl" : "https://mistral.ai/news/mixtral-of-experts/",
+        "modelUrl": "https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1",
+        "tokenizer": "mistralai/Mixtral-8x7B-Instruct-v0.1",
+        "preprompt" : "",
+        "chatPromptTemplate": "<s> {{#each messages}}{{#ifUser}}[INST]{{#if @first}}{{#if @root.preprompt}}{{@root.preprompt}}\n{{/if}}{{/if}} {{content}} [/INST]{{/ifUser}}{{#ifAssistant}} {{content}}</s> {{/ifAssistant}}{{/each}}",
+        "parameters" : {
+          "temperature" : 0.6,
+          "top_p" : 0.95,
+          "repetition_penalty" : 1.2,
+          "top_k" : 50,
+          "truncate" : 24576,
+          "max_new_tokens" : 8192,
+          "stop" : ["</s>"]
+        },
+        "promptExamples" : [
+          {
+            "title": "Write an email from bullet list",
+            "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
+          }, {
+            "title": "Code a snake game",
+            "prompt": "Code a basic snake game in python, give explanations for each step."
+          }, {
+            "title": "Assist in a task",
+            "prompt": "How do I make a delicious lemon cheesecake?"
+          }
+        ]
+      },
+      {
+          "name" : "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
+          "description" : "Nous Hermes 2 Mixtral 8x7B DPO is the new flagship Nous Research model trained over the Mixtral 8x7B MoE LLM.",
+          "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/nous-logo.png",
+          "websiteUrl" : "https://nousresearch.com/",
+          "modelUrl": "https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
+          "tokenizer": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
+          "chatPromptTemplate" : "{{#if @root.preprompt}}<|im_start|>system\n{{@root.preprompt}}<|im_end|>\n{{/if}}{{#each messages}}{{#ifUser}}<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n{{/ifUser}}{{#ifAssistant}}{{content}}<|im_end|>\n{{/ifAssistant}}{{/each}}",
+          "promptExamples": [
+            {
+              "title": "Write an email from bullet list",
+              "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
+            }, {
+              "title": "Code a snake game",
+              "prompt": "Code a basic snake game in python, give explanations for each step."
+            }, {
+              "title": "Assist in a task",
+              "prompt": "How do I make a delicious lemon cheesecake?"
+            }
+          ],
+          "parameters": {
+            "temperature": 0.7,
+            "top_p": 0.95,
+            "repetition_penalty": 1,
+            "top_k": 50,
+            "truncate": 24576,
+            "max_new_tokens": 2048,
+            "stop": ["<|im_end|>"]
+          }
+        },
+          {
+        "name" : "google/gemma-1.1-7b-it",
+        "description": "Gemma 7B 1.1 is the latest release in the Gemma family of lightweight models built by Google, trained using a novel RLHF method.",
+        "websiteUrl" : "https://blog.google/technology/developers/gemma-open-models/",
+        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/google-logo.png",
+        "modelUrl": "https://huggingface.co/google/gemma-1.1-7b-it",
+        "preprompt": "",
+        "chatPromptTemplate" : "{{#each messages}}{{#ifUser}}<start_of_turn>user\n{{#if @first}}{{#if @root.preprompt}}{{@root.preprompt}}\n{{/if}}{{/if}}{{content}}<end_of_turn>\n<start_of_turn>model\n{{/ifUser}}{{#ifAssistant}}{{content}}<end_of_turn>\n{{/ifAssistant}}{{/each}}",
+        "promptExamples": [
+          {
+            "title": "Write an email from bullet list",
+            "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
+          }, {
+            "title": "Code a snake game",
+            "prompt": "Code a basic snake game in python, give explanations for each step."
+          }, {
+            "title": "Assist in a task",
+            "prompt": "How do I make a delicious lemon cheesecake?"
+          }
+        ],
+        "parameters": {
+            "do_sample": true,
+            "truncate": 7168,
+            "max_new_tokens": 1024,
+            "stop" : ["<end_of_turn>"]
+          }
+      },
+
+            {
+          "name": "mistralai/Mistral-7B-Instruct-v0.2",
+          "displayName": "mistralai/Mistral-7B-Instruct-v0.2",
+          "description": "Mistral 7B is a new Apache 2.0 model, released by Mistral AI that outperforms Llama2 13B in benchmarks.",
+          "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/mistral-logo.png",
+          "websiteUrl": "https://mistral.ai/news/announcing-mistral-7b/",
+          "modelUrl": "https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2",
+          "tokenizer": "mistralai/Mistral-7B-Instruct-v0.2",
+          "preprompt": "",
+          "chatPromptTemplate" : "<s>{{#each messages}}{{#ifUser}}[INST] {{#if @first}}{{#if @root.preprompt}}{{@root.preprompt}}\n{{/if}}{{/if}}{{content}} [/INST]{{/ifUser}}{{#ifAssistant}}{{content}}</s>{{/ifAssistant}}{{/each}}",
+          "parameters": {
+            "temperature": 0.3,
+            "top_p": 0.95,
+            "repetition_penalty": 1.2,
+            "top_k": 50,
+            "truncate": 3072,
+            "max_new_tokens": 1024,
+            "stop": ["</s>"]
+          },
+          "promptExamples": [
+            {
+              "title": "Write an email from bullet list",
+              "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
+            }, {
+              "title": "Code a snake game",
+              "prompt": "Code a basic snake game in python, give explanations for each step."
+            }, {
+              "title": "Assist in a task",
+              "prompt": "How do I make a delicious lemon cheesecake?"
+            }
+          ]
+        },
+        {
+          "name": "microsoft/Phi-3-mini-4k-instruct",
+          "tokenizer": "microsoft/Phi-3-mini-4k-instruct",
+          "description" : "Phi-3 Mini-4K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model built upon datasets used for Phi-2.",
+          "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/microsoft-logo.png",
+          "modelUrl": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct",
+          "websiteUrl": "https://azure.microsoft.com/en-us/blog/introducing-phi-3-redefining-whats-possible-with-slms/",
+          "preprompt": "",
+          "chatPromptTemplate": "<s>{{preprompt}}{{#each messages}}{{#ifUser}}<|user|>\n{{content}}<|end|>\n<|assistant|>\n{{/ifUser}}{{#ifAssistant}}{{content}}<|end|>\n{{/ifAssistant}}{{/each}}",
+          "parameters": {
+            "stop": ["<|end|>", "<|endoftext|>", "<|assistant|>"],
+            "max_new_tokens": 1024,
+            "truncate": 3071
+          },
+          "promptExamples": [
+            {
+              "title": "Write an email from bullet list",
+              "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
+            }, {
+              "title": "Code a snake game",
+              "prompt": "Code a basic snake game in python, give explanations for each step."
+            }, {
+              "title": "Assist in a task",
+              "prompt": "How do I make a delicious lemon cheesecake?"
+            }
+          ]
+        },
+        {
+          "name": "meta-llama/Meta-Llama-3-8B-Instruct",
+          "tokenizer" : "philschmid/meta-llama-3-tokenizer",
+          "parameters": {
+            "temperature": 0.1,
+            "stop": ["<|eot_id|>"],
+          },
+          "unlisted": true
+        }
+    ]
+  NODE_ENV: "prod"
+  NODE_LOG_STRUCTURED_DATA: true
+  OLD_MODELS: >
+    [
+      { "name": "bigcode/starcoder" },
+      { "name": "OpenAssistant/oasst-sft-6-llama-30b-xor" },
+      { "name": "HuggingFaceH4/zephyr-7b-alpha" },
+      { "name": "openchat/openchat_3.5" },
+      { "name": "openchat/openchat-3.5-1210" },
+      { "name": "tiiuae/falcon-180B-chat" },
+      { "name": "codellama/CodeLlama-34b-Instruct-hf" },
+      { "name": "google/gemma-7b-it" },
+      { "name": "meta-llama/Llama-2-70b-chat-hf" },
+      { "name": "codellama/CodeLlama-70b-Instruct-hf" },
+      { "name": "openchat/openchat-3.5-0106" }
+    ]
+  PUBLIC_ORIGIN: "https://huggingface.co"
+  PUBLIC_SHARE_PREFIX: "https://hf.co/chat"
+  PUBLIC_ANNOUNCEMENT_BANNERS: "[]"
+  PUBLIC_APP_NAME: "HuggingChat"
+  PUBLIC_APP_ASSETS: "huggingchat"
+  PUBLIC_APP_COLOR: "yellow"
+  PUBLIC_APP_DESCRIPTION: "Making the community's best AI chat models available to everyone."
+  PUBLIC_APP_DISCLAIMER_MESSAGE: "Disclaimer: AI is an area of active research with known problems such as biased generation and misinformation. Do not use this application for high-stakes decisions or advice."
+  PUBLIC_APP_DATA_SHARING: 0
+  PUBLIC_APP_DISCLAIMER: 1
+  PUBLIC_PLAUSIBLE_SCRIPT_URL: "/js/script.js"
+  PUBLIC_APPLE_APP_ID: "6476778843"
+  REQUIRE_FEATURED_ASSISTANTS: "true"
+  TASK_MODEL: "meta-llama/Meta-Llama-3-8B-Instruct"
+  TEXT_EMBEDDING_MODELS: >
+    [{
+      "name": "bge-base-en-v1-5-sxa",
+      "displayName": "bge-base-en-v1-5-sxa",
+      "chunkCharLength": 512,
+      "endpoints": [{ 
+        "type": "tei",
+        "url": "https://huggingchat-tei.hf.space/"
+      }]
+    }]
+  WEBSEARCH_BLOCKLIST: '["youtube.com", "twitter.com"]'
+
+externalSecrets:
+  enabled: true
+  secretStoreName: "chat-ui-prod-secretstore"
+  secretName: "chat-ui-prod-secrets"
+  parameters:
+    MONGODB_URL: "hub-prod-chat-ui-mongodb-url"
+    OPENID_CONFIG: "hub-prod-chat-ui-openid-config"
+    SERPER_API_KEY: "hub-prod-chat-ui-serper-api-key"
+    HF_TOKEN: "hub-prod-chat-ui-hf-token"
+    WEBHOOK_URL_REPORT_ASSISTANT: "hub-prod-chat-ui-webhook-report-assistant"
+    ADMIN_API_SECRET: "hub-prod-chat-ui-admin-api-secret"
+    USAGE_LIMITS: "hub-prod-chat-ui-usage-limits"
+
+autoscaling:
+  enabled: true
+  minReplicas: 6
+  maxReplicas: 30
+  targetMemoryUtilizationPercentage: "70"
+  targetCPUUtilizationPercentage: "70"
+
+monitoring:
+  enabled: true

chart/templates/_helpers.tpl

@@ -0,0 +1,22 @@
+{{- define "name" -}}
+{{- default $.Release.Name | trunc 63 | trimSuffix "-" -}}
+{{- end -}}
+
+{{- define "app.name" -}}
+chat-ui
+{{- end -}}
+
+{{- define "labels.standard" -}}
+release: {{ $.Release.Name | quote }}
+heritage: {{ $.Release.Service | quote }}
+chart: "{{ include "name" . }}"
+app: "{{ include "app.name" . }}"
+{{- end -}}
+
+{{- define "labels.resolver" -}}
+release: {{ $.Release.Name | quote }}
+heritage: {{ $.Release.Service | quote }}
+chart: "{{ include "name" . }}"
+app: "{{ include "app.name" . }}-resolver"
+{{- end -}}
+

chart/templates/config.yaml

@@ -0,0 +1,10 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  labels: {{ include "labels.standard" . | nindent 4 }}
+  name: {{ include "name" . }}
+  namespace: {{ .Release.Namespace }}
+data:
+  {{- range $key, $value := $.Values.envVars }}
+  {{ $key }}: {{ $value | quote }}
+  {{- end }}

chart/templates/deployment.yaml

@@ -0,0 +1,66 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  labels: {{ include "labels.standard" . | nindent 4 }}
+  name: {{ include "name" . }}
+  namespace: {{ .Release.Namespace }}
+spec:
+  progressDeadlineSeconds: 600
+  {{- if not $.Values.autoscaling.enabled }}
+  replicas: {{ .Values.replicas }}
+  {{- end }}
+  revisionHistoryLimit: 10
+  selector:
+    matchLabels: {{ include "labels.standard" . | nindent 6 }}
+  strategy:
+    rollingUpdate:
+      maxSurge: 25%
+      maxUnavailable: 25%
+    type: RollingUpdate
+  template:
+    metadata:
+      labels: {{ include "labels.standard" . | nindent 8 }}
+      {{- if $.Values.envVars.NODE_LOG_STRUCTURED_DATA }}
+      annotations:
+        co.elastic.logs/json.expand_keys: "true"
+      {{- end }}
+    spec:
+      containers:
+        - name: chat-ui
+          image: "{{ .Values.image.repository }}/{{ .Values.image.name }}:{{ .Values.image.tag }}"
+          imagePullPolicy: {{ .Values.image.pullPolicy }}
+          readinessProbe:
+            failureThreshold: 30
+            periodSeconds: 10
+            httpGet:
+              path: {{ $.Values.envVars.APP_BASE | default "" }}/healthcheck
+              port: {{ $.Values.envVars.APP_PORT | default 3000 | int }}
+          livenessProbe:
+            failureThreshold: 30
+            periodSeconds: 10
+            httpGet:
+              path: {{ $.Values.envVars.APP_BASE | default "" }}/healthcheck
+              port: {{ $.Values.envVars.APP_PORT | default 3000 | int }}
+          ports:
+            - containerPort: {{ $.Values.envVars.APP_PORT | default 3000 | int }}
+              name: http
+              protocol: TCP
+            {{- if $.Values.monitoring.enabled }}
+            - containerPort: {{ $.Values.envVars.METRICS_PORT | default 5565 | int }}
+              name: metrics
+              protocol: TCP
+            {{- end }}
+          resources: {{ toYaml .Values.resources | nindent 12 }}
+          envFrom:
+            - configMapRef:
+                name: {{ include "name" . }}
+          {{- if $.Values.externalSecrets.enabled }}
+            - secretRef:
+                name: {{ $.Values.externalSecrets.secretName }}
+          {{- end }}
+      nodeSelector: {{ toYaml .Values.nodeSelector | nindent 8 }}
+      tolerations: {{ toYaml .Values.tolerations | nindent 8 }}
+      volumes:
+        - name: config
+          configMap:
+            name: {{ include "name" . }}

chart/templates/hpa.yaml

@@ -0,0 +1,45 @@
+{{- if $.Values.autoscaling.enabled }}
+apiVersion: autoscaling/v2
+kind: HorizontalPodAutoscaler
+metadata:
+  labels: {{ include "labels.standard" . | nindent 4 }}
+  name: {{ include "name" . }}
+  namespace: {{ .Release.Namespace }}
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: {{ include "name" . }}
+  minReplicas: {{ $.Values.autoscaling.minReplicas }}
+  maxReplicas: {{ $.Values.autoscaling.maxReplicas }}
+  metrics:
+    {{- if ne "" $.Values.autoscaling.targetMemoryUtilizationPercentage }}
+    - type: Resource
+      resource:
+        name: memory
+        target:
+          type: Utilization
+          averageUtilization: {{ $.Values.autoscaling.targetMemoryUtilizationPercentage | int }}
+    {{- end }}
+    {{- if ne "" $.Values.autoscaling.targetCPUUtilizationPercentage }}
+    - type: Resource
+      resource:
+        name: cpu
+        target:
+          type: Utilization
+          averageUtilization: {{ $.Values.autoscaling.targetCPUUtilizationPercentage | int }}
+    {{- end }}
+  behavior:
+    scaleDown:
+      stabilizationWindowSeconds: 600
+      policies:
+        - type: Percent
+          value: 10
+          periodSeconds: 60
+    scaleUp:
+      stabilizationWindowSeconds: 0
+      policies:
+        - type: Pods
+          value: 1
+          periodSeconds: 30
+{{- end }}

chart/templates/ingress.yaml

@@ -0,0 +1,19 @@
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  annotations: {{ toYaml .Values.ingress.annotations | nindent 4 }}
+  labels: {{ include "labels.standard" . | nindent 4 }}
+  name: {{ include "name" . }}
+  namespace: {{ .Release.Namespace }}
+spec:
+  rules:
+    - host: {{ .Values.domain }}
+      http:
+        paths:
+          - backend:
+              service:
+                name: {{ include "name" . }}
+                port:
+                  name: http
+            path: {{ $.Values.ingress.path | default "/" }}
+            pathType: Prefix

chart/templates/secrets.yaml

@@ -0,0 +1,21 @@
+{{- if .Values.externalSecrets.enabled }}
+apiVersion: "external-secrets.io/v1beta1"
+kind: ExternalSecret
+metadata:
+  labels: {{ include "labels.standard" . | nindent 4 }}
+  name: {{ include "name" $ }}-external-secret
+  namespace: {{ $.Release.Namespace }}
+spec:
+  refreshInterval: 1h
+  secretStoreRef:
+    name: {{ .Values.externalSecrets.secretStoreName }}
+    kind: SecretStore
+  target:
+    name: {{ .Values.externalSecrets.secretName }}
+  data:
+    {{- range $key, $value := .Values.externalSecrets.parameters }}
+    - secretKey: {{ $key | quote }}
+      remoteRef:
+        key: {{ $value | quote }}
+    {{- end }}
+{{- end }}

chart/templates/service-monitor.yaml

@@ -0,0 +1,15 @@
+{{- if $.Values.monitoring.enabled }}
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  labels: {{ include "labels.standard" . | nindent 4 }}
+  name: {{ include "name" . }}
+  namespace: {{ .Release.Namespace }}
+spec:
+  selector:
+    matchLabels: {{ include "labels.standard" . | nindent 6 }}
+  endpoints:
+    - port: metrics
+      path: /metrics
+      interval: 15s
+{{- end }}

chart/templates/service.yaml

@@ -0,0 +1,21 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: "{{ include "name" . }}"
+  annotations: {{ toYaml .Values.service.annotations | nindent 4 }}
+  namespace: {{ .Release.Namespace }}
+  labels: {{ include "labels.standard" . | nindent 4 }}
+spec:
+  ports:
+  - name: http
+    port: 80
+    protocol: TCP
+    targetPort: http
+  {{- if $.Values.monitoring.enabled }}
+  - name: metrics
+    port: 5565
+    protocol: TCP
+    targetPort: http
+  {{- end }}
+  selector: {{ include "labels.standard" . | nindent 4 }}
+  type: {{.Values.service.type}}

chart/values.yaml

@@ -0,0 +1,44 @@
+image:
+  repository: ghcr.io/huggingface
+  name: chat-ui
+  tag: 0.0.0-latest
+  pullPolicy: IfNotPresent
+
+replicas: 3
+
+domain: huggingface.co
+
+service:
+  type: NodePort
+  annotations: { }
+
+ingress:
+  path: "/"
+  annotations: { }
+
+resources:
+  requests:
+    cpu: 1
+    memory: 8Gi
+  limits:
+    cpu: 1
+    memory: 8Gi
+nodeSelector: {}
+tolerations: []
+
+envVars: { }
+externalSecrets:
+  enabled: false
+  secretStoreName: ""
+  secretName: ""
+  parameters: { }
+
+autoscaling:
+  enabled: false
+  minReplicas: 1
+  maxReplicas: 2
+  targetMemoryUtilizationPercentage: ""
+  targetCPUUtilizationPercentage: ""
+
+monitoring:
+  enabled: false