|
| 1 | +name: Evaluate RAG answer flow |
| 2 | + |
| 3 | +on: |
| 4 | + issue_comment: |
| 5 | + types: [created] |
| 6 | + |
| 7 | +# Set up permissions for deploying with secretless Azure federated credentials |
| 8 | +# https://learn.microsoft.com/azure/developer/github/connect-from-azure?tabs=azure-portal%2Clinux#set-up-azure-login-with-openid-connect-authentication |
| 9 | +permissions: |
| 10 | + id-token: write |
| 11 | + contents: read |
| 12 | + issues: write |
| 13 | + pull-requests: write |
| 14 | + |
| 15 | +jobs: |
| 16 | + evaluate: |
| 17 | + if: | |
| 18 | + contains('["OWNER", "CONTRIBUTOR", "COLLABORATOR", "MEMBER"]', github.event.comment.author_association) && |
| 19 | + github.event.issue.pull_request && |
| 20 | + github.event.comment.body == '/evaluate' |
| 21 | + runs-on: ubuntu-latest |
| 22 | + env: |
| 23 | + # azd required |
| 24 | + AZURE_CLIENT_ID: ${{ vars.AZURE_CLIENT_ID }} |
| 25 | + AZURE_TENANT_ID: ${{ vars.AZURE_TENANT_ID }} |
| 26 | + AZURE_SUBSCRIPTION_ID: ${{ vars.AZURE_SUBSCRIPTION_ID }} |
| 27 | + AZURE_ENV_NAME: ${{ vars.AZURE_ENV_NAME }} |
| 28 | + AZURE_LOCATION: ${{ vars.AZURE_LOCATION }} |
| 29 | + # project specific |
| 30 | + AZURE_OPENAI_SERVICE: ${{ vars.AZURE_OPENAI_SERVICE }} |
| 31 | + AZURE_OPENAI_LOCATION: ${{ vars.AZURE_OPENAI_LOCATION }} |
| 32 | + AZURE_OPENAI_API_VERSION: ${{ vars.AZURE_OPENAI_API_VERSION }} |
| 33 | + AZURE_OPENAI_RESOURCE_GROUP: ${{ vars.AZURE_OPENAI_RESOURCE_GROUP }} |
| 34 | + AZURE_DOCUMENTINTELLIGENCE_SERVICE: ${{ vars.AZURE_DOCUMENTINTELLIGENCE_SERVICE }} |
| 35 | + AZURE_DOCUMENTINTELLIGENCE_RESOURCE_GROUP: ${{ vars.AZURE_DOCUMENTINTELLIGENCE_RESOURCE_GROUP }} |
| 36 | + AZURE_DOCUMENTINTELLIGENCE_SKU: ${{ vars.AZURE_DOCUMENTINTELLIGENCE_SKU }} |
| 37 | + AZURE_DOCUMENTINTELLIGENCE_LOCATION: ${{ vars.AZURE_DOCUMENTINTELLIGENCE_LOCATION }} |
| 38 | + AZURE_COMPUTER_VISION_SERVICE: ${{ vars.AZURE_COMPUTER_VISION_SERVICE }} |
| 39 | + AZURE_COMPUTER_VISION_RESOURCE_GROUP: ${{ vars.AZURE_COMPUTER_VISION_RESOURCE_GROUP }} |
| 40 | + AZURE_COMPUTER_VISION_LOCATION: ${{ vars.AZURE_COMPUTER_VISION_LOCATION }} |
| 41 | + AZURE_COMPUTER_VISION_SKU: ${{ vars.AZURE_COMPUTER_VISION_SKU }} |
| 42 | + AZURE_SEARCH_INDEX: ${{ vars.AZURE_SEARCH_INDEX }} |
| 43 | + AZURE_SEARCH_SERVICE: ${{ vars.AZURE_SEARCH_SERVICE }} |
| 44 | + AZURE_SEARCH_SERVICE_RESOURCE_GROUP: ${{ vars.AZURE_SEARCH_SERVICE_RESOURCE_GROUP }} |
| 45 | + AZURE_SEARCH_SERVICE_LOCATION: ${{ vars.AZURE_SEARCH_SERVICE_LOCATION }} |
| 46 | + AZURE_SEARCH_SERVICE_SKU: ${{ vars.AZURE_SEARCH_SERVICE_SKU }} |
| 47 | + AZURE_SEARCH_QUERY_LANGUAGE: ${{ vars.AZURE_SEARCH_QUERY_LANGUAGE }} |
| 48 | + AZURE_SEARCH_QUERY_SPELLER: ${{ vars.AZURE_SEARCH_QUERY_SPELLER }} |
| 49 | + AZURE_SEARCH_SEMANTIC_RANKER: ${{ vars.AZURE_SEARCH_SEMANTIC_RANKER }} |
| 50 | + AZURE_STORAGE_ACCOUNT: ${{ vars.AZURE_STORAGE_ACCOUNT }} |
| 51 | + AZURE_STORAGE_RESOURCE_GROUP: ${{ vars.AZURE_STORAGE_RESOURCE_GROUP }} |
| 52 | + AZURE_STORAGE_SKU: ${{ vars.AZURE_STORAGE_SKU }} |
| 53 | + AZURE_APP_SERVICE_PLAN: ${{ vars.AZURE_APP_SERVICE_PLAN }} |
| 54 | + AZURE_APP_SERVICE_SKU: ${{ vars.AZURE_APP_SERVICE_SKU }} |
| 55 | + AZURE_APP_SERVICE: ${{ vars.AZURE_APP_SERVICE }} |
| 56 | + AZURE_OPENAI_CHATGPT_MODEL: ${{ vars.AZURE_OPENAI_CHATGPT_MODEL }} |
| 57 | + AZURE_OPENAI_CHATGPT_DEPLOYMENT: ${{ vars.AZURE_OPENAI_CHATGPT_DEPLOYMENT }} |
| 58 | + AZURE_OPENAI_CHATGPT_DEPLOYMENT_CAPACITY: ${{ vars.AZURE_OPENAI_CHATGPT_DEPLOYMENT_CAPACITY }} |
| 59 | + AZURE_OPENAI_CHATGPT_DEPLOYMENT_VERSION: ${{ vars.AZURE_OPENAI_CHATGPT_DEPLOYMENT_VERSION }} |
| 60 | + AZURE_OPENAI_EMB_MODEL_NAME: ${{ vars.AZURE_OPENAI_EMB_MODEL_NAME }} |
| 61 | + AZURE_OPENAI_EMB_DEPLOYMENT: ${{ vars.AZURE_OPENAI_EMB_DEPLOYMENT }} |
| 62 | + AZURE_OPENAI_EMB_DEPLOYMENT_CAPACITY: ${{ vars.AZURE_OPENAI_EMB_DEPLOYMENT_CAPACITY }} |
| 63 | + AZURE_OPENAI_EMB_DEPLOYMENT_VERSION: ${{ vars.AZURE_OPENAI_EMB_DEPLOYMENT_VERSION }} |
| 64 | + AZURE_OPENAI_EMB_DIMENSIONS: ${{ vars.AZURE_OPENAI_EMB_DIMENSIONS }} |
| 65 | + AZURE_OPENAI_GPT4V_MODEL: ${{ vars.AZURE_OPENAI_GPT4V_MODEL }} |
| 66 | + AZURE_OPENAI_GPT4V_DEPLOYMENT: ${{ vars.AZURE_OPENAI_GPT4V_DEPLOYMENT }} |
| 67 | + AZURE_OPENAI_GPT4V_DEPLOYMENT_CAPACITY: ${{ vars.AZURE_OPENAI_GPT4V_DEPLOYMENT_CAPACITY }} |
| 68 | + AZURE_OPENAI_GPT4V_DEPLOYMENT_VERSION: ${{ vars.AZURE_OPENAI_GPT4V_DEPLOYMENT_VERSION }} |
| 69 | + AZURE_OPENAI_GPT4V_DEPLOYMENT_SKU: ${{ vars.AZURE_OPENAI_GPT4V_DEPLOYMENT_SKU }} |
| 70 | + USE_EVAL: ${{ vars.USE_EVAL }} |
| 71 | + AZURE_OPENAI_EVAL_MODEL: ${{ vars.AZURE_OPENAI_EVAL_MODEL }} |
| 72 | + AZURE_OPENAI_EVAL_MODEL_VERSION: ${{ vars.AZURE_OPENAI_EVAL_MODEL_VERSION }} |
| 73 | + AZURE_OPENAI_EVAL_DEPLOYMENT: ${{ vars.AZURE_OPENAI_EVAL_DEPLOYMENT }} |
| 74 | + AZURE_OPENAI_EVAL_DEPLOYMENT_SKU: ${{ vars.AZURE_OPENAI_EVAL_DEPLOYMENT_SKU }} |
| 75 | + AZURE_OPENAI_EVAL_DEPLOYMENT_CAPACITY: ${{ vars.AZURE_OPENAI_EVAL_DEPLOYMENT_CAPACITY }} |
| 76 | + AZURE_OPENAI_DISABLE_KEYS: ${{ vars.AZURE_OPENAI_DISABLE_KEYS }} |
| 77 | + OPENAI_HOST: ${{ vars.OPENAI_HOST }} |
| 78 | + OPENAI_API_KEY: ${{ vars.OPENAI_API_KEY }} |
| 79 | + OPENAI_ORGANIZATION: ${{ vars.OPENAI_ORGANIZATION }} |
| 80 | + AZURE_USE_APPLICATION_INSIGHTS: ${{ vars.AZURE_USE_APPLICATION_INSIGHTS }} |
| 81 | + AZURE_APPLICATION_INSIGHTS: ${{ vars.AZURE_APPLICATION_INSIGHTS }} |
| 82 | + AZURE_APPLICATION_INSIGHTS_DASHBOARD: ${{ vars.AZURE_APPLICATION_INSIGHTS_DASHBOARD }} |
| 83 | + AZURE_LOG_ANALYTICS: ${{ vars.AZURE_LOG_ANALYTICS }} |
| 84 | + USE_VECTORS: ${{ vars.USE_VECTORS }} |
| 85 | + USE_GPT4V: ${{ vars.USE_GPT4V }} |
| 86 | + AZURE_VISION_ENDPOINT: ${{ vars.AZURE_VISION_ENDPOINT }} |
| 87 | + VISION_SECRET_NAME: ${{ vars.VISION_SECRET_NAME }} |
| 88 | + ENABLE_LANGUAGE_PICKER: ${{ vars.ENABLE_LANGUAGE_PICKER }} |
| 89 | + USE_SPEECH_INPUT_BROWSER: ${{ vars.USE_SPEECH_INPUT_BROWSER }} |
| 90 | + USE_SPEECH_OUTPUT_BROWSER: ${{ vars.USE_SPEECH_OUTPUT_BROWSER }} |
| 91 | + USE_SPEECH_OUTPUT_AZURE: ${{ vars.USE_SPEECH_OUTPUT_AZURE }} |
| 92 | + AZURE_SPEECH_SERVICE: ${{ vars.AZURE_SPEECH_SERVICE }} |
| 93 | + AZURE_SPEECH_SERVICE_RESOURCE_GROUP: ${{ vars.AZURE_SPEECH_RESOURCE_GROUP }} |
| 94 | + AZURE_SPEECH_SERVICE_LOCATION: ${{ vars.AZURE_SPEECH_SERVICE_LOCATION }} |
| 95 | + AZURE_SPEECH_SERVICE_SKU: ${{ vars.AZURE_SPEECH_SERVICE_SKU }} |
| 96 | + AZURE_SPEECH_SERVICE_VOICE: ${{ vars.AZURE_SPEECH_SERVICE_VOICE }} |
| 97 | + AZURE_KEY_VAULT_NAME: ${{ vars.AZURE_KEY_VAULT_NAME }} |
| 98 | + AZURE_USE_AUTHENTICATION: ${{ vars.AZURE_USE_AUTHENTICATION }} |
| 99 | + AZURE_ENFORCE_ACCESS_CONTROL: ${{ vars.AZURE_ENFORCE_ACCESS_CONTROL }} |
| 100 | + AZURE_ENABLE_GLOBAL_DOCUMENT_ACCESS: ${{ vars.AZURE_ENABLE_GLOBAL_DOCUMENT_ACCESS }} |
| 101 | + AZURE_ENABLE_UNAUTHENTICATED_ACCESS: ${{ vars.AZURE_ENABLE_UNAUTHENTICATED_ACCESS }} |
| 102 | + AZURE_AUTH_TENANT_ID: ${{ vars.AZURE_AUTH_TENANT_ID }} |
| 103 | + AZURE_SERVER_APP_ID: ${{ vars.AZURE_SERVER_APP_ID }} |
| 104 | + AZURE_CLIENT_APP_ID: ${{ vars.AZURE_CLIENT_APP_ID }} |
| 105 | + ALLOWED_ORIGIN: ${{ vars.ALLOWED_ORIGIN }} |
| 106 | + AZURE_ADLS_GEN2_STORAGE_ACCOUNT: ${{ vars.AZURE_ADLS_GEN2_STORAGE_ACCOUNT }} |
| 107 | + AZURE_ADLS_GEN2_FILESYSTEM_PATH: ${{ vars.AZURE_ADLS_GEN2_FILESYSTEM_PATH }} |
| 108 | + AZURE_ADLS_GEN2_FILESYSTEM: ${{ vars.AZURE_ADLS_GEN2_FILESYSTEM }} |
| 109 | + DEPLOYMENT_TARGET: ${{ vars.DEPLOYMENT_TARGET }} |
| 110 | + AZURE_CONTAINER_APPS_WORKLOAD_PROFILE: ${{ vars.AZURE_CONTAINER_APPS_WORKLOAD_PROFILE }} |
| 111 | + USE_CHAT_HISTORY_BROWSER: ${{ vars.USE_CHAT_HISTORY_BROWSER }} |
| 112 | + USE_MEDIA_DESCRIBER_AZURE_CU: ${{ vars.USE_MEDIA_DESCRIBER_AZURE_CU }} |
| 113 | + USE_AI_PROJECT: ${{ vars.USE_AI_PROJECT }} |
| 114 | + steps: |
| 115 | + |
| 116 | + - name: Comment on pull request |
| 117 | + uses: actions/github-script@v7 |
| 118 | + with: |
| 119 | + script: | |
| 120 | + github.rest.issues.createComment({ |
| 121 | + issue_number: context.issue.number, |
| 122 | + owner: context.repo.owner, |
| 123 | + repo: context.repo.repo, |
| 124 | + body: "Starting evaluation! Check the Actions tab for progress, or wait for a comment with the results." |
| 125 | + }) |
| 126 | +
|
| 127 | + - name: Checkout pull request |
| 128 | + uses: actions/checkout@v4 |
| 129 | + with: |
| 130 | + ref: refs/pull/${{ github.event.issue.number }}/head |
| 131 | + |
| 132 | + - name: Install uv |
| 133 | + uses: astral-sh/setup-uv@v6 |
| 134 | + with: |
| 135 | + enable-cache: true |
| 136 | + version: "0.4.20" |
| 137 | + cache-dependency-glob: "requirements**.txt" |
| 138 | + python-version: "3.11" |
| 139 | + |
| 140 | + - name: Setup node |
| 141 | + uses: actions/setup-node@v4 |
| 142 | + with: |
| 143 | + node-version: 18 |
| 144 | + |
| 145 | + - name: Install azd |
| 146 | + |
| 147 | + |
| 148 | + - name: Login to Azure with az CLI |
| 149 | + uses: azure/login@v2 |
| 150 | + with: |
| 151 | + client-id: ${{ env.AZURE_CLIENT_ID }} |
| 152 | + tenant-id: ${{ env.AZURE_TENANT_ID }} |
| 153 | + subscription-id: ${{ env.AZURE_SUBSCRIPTION_ID }} |
| 154 | + |
| 155 | + - name: Set az account |
| 156 | + uses: azure/CLI@v2 |
| 157 | + with: |
| 158 | + inlineScript: | |
| 159 | + az account set --subscription ${{env.AZURE_SUBSCRIPTION_ID}} |
| 160 | +
|
| 161 | + - name: Login to with Azure with azd (Federated Credentials) |
| 162 | + if: ${{ env.AZURE_CLIENT_ID != '' }} |
| 163 | + run: | |
| 164 | + azd auth login ` |
| 165 | + --client-id "$Env:AZURE_CLIENT_ID" ` |
| 166 | + --federated-credential-provider "github" ` |
| 167 | + --tenant-id "$Env:AZURE_TENANT_ID" |
| 168 | + shell: pwsh |
| 169 | + |
| 170 | + - name: Refresh azd environment variables |
| 171 | + run: | |
| 172 | + azd env refresh -e $AZURE_ENV_NAME --no-prompt |
| 173 | + env: |
| 174 | + AZD_INITIAL_ENVIRONMENT_CONFIG: ${{ secrets.AZD_INITIAL_ENVIRONMENT_CONFIG }} |
| 175 | + |
| 176 | + - name: Build frontend |
| 177 | + run: | |
| 178 | + cd ./app/frontend |
| 179 | + npm install |
| 180 | + npm run build |
| 181 | +
|
| 182 | + - name: Install dependencies |
| 183 | + run: | |
| 184 | + uv pip install -r requirements-dev.txt |
| 185 | +
|
| 186 | + - name: Run local server in background |
| 187 | + run: | |
| 188 | + cd app/backend |
| 189 | + RUNNER_TRACKING_ID="" && (nohup python3 -m quart --app main:app run --port 50505 > serverlogs.out 2> serverlogs.err &) |
| 190 | + cd ../.. |
| 191 | +
|
| 192 | + - name: Install evaluate dependencies |
| 193 | + run: | |
| 194 | + uv pip install -r evals/requirements.txt |
| 195 | +
|
| 196 | + - name: Evaluate local RAG flow |
| 197 | + run: | |
| 198 | + python evals/evaluate.py --targeturl=http://127.0.0.1:50505/chat --resultsdir=evals/results/pr${{ github.event.issue.number }} |
| 199 | +
|
| 200 | + - name: Upload eval results as build artifact |
| 201 | + if: ${{ success() }} |
| 202 | + uses: actions/upload-artifact@v4 |
| 203 | + with: |
| 204 | + name: eval_result |
| 205 | + path: ./evals/results/pr${{ github.event.issue.number }} |
| 206 | + |
| 207 | + - name: Upload server logs as build artifact |
| 208 | + uses: actions/upload-artifact@v4 |
| 209 | + with: |
| 210 | + name: server_logs |
| 211 | + path: ./app/backend/serverlogs.out |
| 212 | + |
| 213 | + - name: Upload server error logs as build artifact |
| 214 | + uses: actions/upload-artifact@v4 |
| 215 | + with: |
| 216 | + name: server_error_logs |
| 217 | + path: ./app/backend/serverlogs.err |
| 218 | + |
| 219 | + - name: Summarize results |
| 220 | + if: ${{ success() }} |
| 221 | + run: | |
| 222 | + echo "## Evaluation results" >> eval-summary.md |
| 223 | + python -m evaltools summary evals/results --output=markdown >> eval-summary.md |
| 224 | + echo "## Answer differences across runs" >> run-diff.md |
| 225 | + python -m evaltools diff evals/results/baseline evals/results/pr${{ github.event.issue.number }} --output=markdown >> run-diff.md |
| 226 | + cat eval-summary.md >> $GITHUB_STEP_SUMMARY |
| 227 | + cat run-diff.md >> $GITHUB_STEP_SUMMARY |
| 228 | +
|
| 229 | + - name: Comment on pull request |
| 230 | + uses: actions/github-script@v7 |
| 231 | + with: |
| 232 | + script: | |
| 233 | + const fs = require('fs'); |
| 234 | + const summaryPath = "eval-summary.md"; |
| 235 | + const summary = fs.readFileSync(summaryPath, 'utf8'); |
| 236 | + const runId = process.env.GITHUB_RUN_ID; |
| 237 | + const repo = process.env.GITHUB_REPOSITORY; |
| 238 | + const actionsUrl = `https://github.com/${repo}/actions/runs/${runId}`; |
| 239 | + github.rest.issues.createComment({ |
| 240 | + issue_number: context.issue.number, |
| 241 | + owner: context.repo.owner, |
| 242 | + repo: context.repo.repo, |
| 243 | + body: `${summary}\n\n[Check the workflow run for more details](${actionsUrl}).` |
| 244 | + }) |
0 commit comments