ci: Updates to Cloud Build NB Testing Scripts (#2039)

Author: holtskinner

.cloud-build/Notebooks.txt

@@ -1,14 +1,2 @@
 generative-ai/gemini/getting-started/intro_gemini_2_0_flash.ipynb
 generative-ai/gemini/getting-started/intro_gemini_2_0_flash_lite.ipynb
-generative-ai/gemini/getting-started/intro_gemini_2_0_image_gen.ipynb
-generative-ai/gemini/getting-started/intro_gemini_2_5_flash.ipynb
-generative-ai/gemini/getting-started/intro_gemini_2_5_pro.ipynb
-generative-ai/gemini/getting-started/intro_gemini_chat.ipynb
-generative-ai/gemini/getting-started/intro_gemini_curl.ipynb
-generative-ai/gemini/code-execution/intro_code_execution.ipynb
-generative-ai/gemini/context-caching/intro_context_caching.ipynb
-generative-ai/gemini/controlled-generation/intro_controlled_generation.ipynb
-generative-ai/gemini/long-context/intro_long_context.ipynb
-generative-ai/gemini/prompts/intro_prompt_design.ipynb
-generative-ai/gemini/orchestration/intro_langchain_gemini.ipynb
-generative-ai/gemini/orchestration/intro_langgraph_gemini.ipynb

.cloud-build/README.md

@@ -13,7 +13,7 @@ The script performs the following actions:
 1. **Reads Output URI variable:**
    - It reads the destination GCS bucket URI from a variable named `OUTPUT_URI` injected from secret manager. This allows for easy configuration of the destination.
 2. **Iterates Through Notebooks:**
-   - It loops through all `.ipynb` files located in the `/workspace/generative-ai/gemini/getting-started/` directory.
+   - It loops through all `.ipynb` files located in the `Notebooks.txt` file.
 3. **Copies Notebooks to GCS:**
    - For each notebook file, it extracts the filename using `basename`.
    - It then uses the `gcloud storage cp` command to copy the notebook file to the specified GCS bucket, maintaining the directory structure.
@@ -40,7 +40,7 @@ Before running this script, ensure you have the following:
 
 2. **Place Notebooks:**
 
-   - Ensure your `.ipynb` files are located in the `/workspace/generative-ai/gemini/getting-started/` directory.
+   - Ensure the names of the `.ipynb` files are located in the `Notebooks.txt` file.
 
 3. **Add the script as a step in your pipeline:**
 

.cloud-build/clone-repo/clone_repo.sh

@@ -1,13 +1,7 @@
 #!/bin/bash
 
-# Reads the destination GCS URI from the OUTPUT_URI file.
-OUTPUT_URI=$(cat OUTPUT_URI)
-
 # Clones the generative-ai repository from GitHub.
 git clone --depth 1 -b main https://github.com/GoogleCloudPlatform/generative-ai.git
 
 # Changes the current directory to the cloned repository.
 cd generative-ai || exit 1
-
-# Copies the specified directory to the destination GCS URI using gsutil.
-gsutil -m rsync -r . $OUTPUT_URI/generative-ai/

.cloud-build/cloudbuild.yaml

@@ -8,41 +8,13 @@ steps:
     args:
       - "-c"
       - |
-        gcloud secrets versions access latest --secret=GCS_BUCKET > OUTPUT_URI
         . .cloud-build/clone-repo/clone_repo.sh
   # [END copy-repo]
-  # [START prepare-data]
-  - name: google/cloud-sdk
-    id: "prepare-data"
-    entrypoint: bash
-    args:
-      - "-c"
-      - |
-        . .cloud-build/prepare-data/prepare_notebooks.sh
-  # [END prepare-data]
-  # [START push-to-gcs]
-  - name: google/cloud-sdk
-    id: "push-to-gcs"
-    entrypoint: bash
-    args:
-      - "-c"
-      - |
-        gcloud secrets versions access latest --secret=GCS_BUCKET > OUTPUT_URI
-        . .cloud-build/gcs/push_to_gcs.sh
-  # [END push-to-gcs]
-  # [START run-lint]
-  - name: python:3.9
-    id: "run-lint"
-    entrypoint: python
-    args:
-      - .cloud-build/linting/lint.py
-  # [END run-lint]
-
   # [START execute-notebooks]
   - name: google/cloud-sdk
     id: "execute-notebooks"
     entrypoint: bash
-    timeout: 7200s #Because this step takes the longest. Avg runtime is 1 hour and 20 minutes.
+    timeout: 7200s # Because this step takes the longest. Avg runtime is 1 hour and 20 minutes.
     args:
       - "-c"
       - |

.cloud-build/executor/test_notebooks.sh

@@ -23,14 +23,16 @@ successful_count=0
 
 for x in $TARGET; do
   total_count=$((total_count + 1))
-  DISPLAY_NAME="${x##*/}-$current_date-$current_time"
-  echo "Starting execution for ${x##*/}"
+  # Use the full path from the repository for display name
+  DISPLAY_NAME="${x##generative-ai/}"
+  DISPLAY_NAME="${DISPLAY_NAME%.ipynb}-$current_date-$current_time"
+  echo "Starting execution for ${x}"
 
   # Execute and get the operation ID
   OPERATION_ID=$(gcloud colab executions create \
     --display-name="$DISPLAY_NAME" \
     --notebook-runtime-template="$NOTEBOOK_RUNTIME_TEMPLATE" \
-    --gcs-notebook-uri="$OUTPUT_URI/$x" \
+    --direct-content="$x" \
     --gcs-output-uri="$OUTPUT_URI" \
     --project="$PROJECT_ID" \
     --region="$REGION" \
@@ -45,24 +47,24 @@ for x in $TARGET; do
   # check job status
   echo "Waiting for execution to complete..."
   if ! EXECUTION_DETAILS=$(gcloud colab executions describe "$TRUNCATED_OPERATION_ID" --region="$REGION"); then
-    echo "Error describing execution for ${x##*/}. See logs for details."
+    echo "Error describing execution for ${x}. See logs for details."
     failed_count=$((failed_count + 1))
-    failed_notebooks+=("${x##*/}")
+    failed_notebooks+=("${x}")
     continue
   else
-    echo "Execution completed for ${x##*/}"
+    echo "Execution completed for ${x}"
   fi
 
   # Check the jobState
   JOB_STATE=$(echo "$EXECUTION_DETAILS" | grep "jobState:" | awk '{print $2}')
   if [[ "$JOB_STATE" == "JOB_STATE_SUCCEEDED" ]]; then
     echo "Notebook execution succeeded."
     successful_count=$((successful_count + 1))
-    successful_notebooks+=("${x##*/}")
+    successful_notebooks+=("${x}")
   else
-    echo "Notebook execution failed. Job state: $JOB_STATE. Please use id $TRUNCATED_OPERATION_ID to troubleshoot notebook ${x##*/}. See log for details."
+    echo "Notebook execution failed. Job state: $JOB_STATE. Please use id $TRUNCATED_OPERATION_ID to troubleshoot notebook ${x}. See log for details."
     failed_count=$((failed_count + 1))
-    failed_notebooks+=("${x##*/}")
+    failed_notebooks+=("${x}")
     continue
   fi
 

.cloud-build/gcs/README.md

@@ -2,9 +2,9 @@
 
 ISSUE_TITLE="Failed automated Notebook Testing"
 ISSUE_LABELS="bug"
-ISSUE_ASSIGNEES="CadillacBurgess1"
-REPO_OWNER="CadillacBurgess1"
-REPO_NAME="example-notebook-testing-repo"
+# ISSUE_ASSIGNEES="CadillacBurgess1"
+REPO_OWNER="GoogleCloudPlatform"
+REPO_NAME="generative-ai"
 FAILURE_FILE="/workspace/Failure.txt"
 
 if [ -f "$FAILURE_FILE" ]; then