chore: Updating documentation and adding exception handling for Vector Stores in RAG Tool and updating inference to use openai and updating memory implementation to use existing libraries

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>

.github/actions/run-and-record-tests/action.yml

@@ -5,21 +5,22 @@ inputs:
   stack-config:
     description: 'Stack configuration to use'
     required: true
-  provider:
-    description: 'Provider to use for tests'
-    required: true
+  setup:
+    description: 'Setup to use for tests (e.g., ollama, gpt, vllm)'
+    required: false
+    default: ''
   inference-mode:
     description: 'Inference mode (record or replay)'
     required: true
-  test-suite:
+  suite:
     description: 'Test suite to use: base, responses, vision, etc.'
     required: false
     default: ''
-  test-subdirs:
-    description: 'Comma-separated list of test subdirectories to run; overrides test-suite'
+  subdirs:
+    description: 'Comma-separated list of test subdirectories to run; overrides suite'
     required: false
     default: ''
-  test-pattern:
+  pattern:
     description: 'Regex pattern to pass to pytest -k'
     required: false
     default: ''
@@ -37,14 +38,23 @@ runs:
     - name: Run Integration Tests
       shell: bash
       run: |
-        uv run --no-sync ./scripts/integration-tests.sh \
-          --stack-config '${{ inputs.stack-config }}' \
-          --provider '${{ inputs.provider }}' \
-          --test-subdirs '${{ inputs.test-subdirs }}' \
-          --test-pattern '${{ inputs.test-pattern }}' \
-          --inference-mode '${{ inputs.inference-mode }}' \
-          --test-suite '${{ inputs.test-suite }}' \
-          | tee pytest-${{ inputs.inference-mode }}.log
+        SCRIPT_ARGS="--stack-config ${{ inputs.stack-config }} --inference-mode ${{ inputs.inference-mode }}"
+
+        # Add optional arguments only if they are provided
+        if [ -n '${{ inputs.setup }}' ]; then
+          SCRIPT_ARGS="$SCRIPT_ARGS --setup ${{ inputs.setup }}"
+        fi
+        if [ -n '${{ inputs.suite }}' ]; then
+          SCRIPT_ARGS="$SCRIPT_ARGS --suite ${{ inputs.suite }}"
+        fi
+        if [ -n '${{ inputs.subdirs }}' ]; then
+          SCRIPT_ARGS="$SCRIPT_ARGS --subdirs ${{ inputs.subdirs }}"
+        fi
+        if [ -n '${{ inputs.pattern }}' ]; then
+          SCRIPT_ARGS="$SCRIPT_ARGS --pattern ${{ inputs.pattern }}"
+        fi
+
+        uv run --no-sync ./scripts/integration-tests.sh $SCRIPT_ARGS | tee pytest-${{ inputs.inference-mode }}.log
 
 
     - name: Commit and push recordings
@@ -58,7 +68,7 @@ runs:
           echo "New recordings detected, committing and pushing"
           git add tests/integration/recordings/
 
-          git commit -m "Recordings update from CI (test-suite: ${{ inputs.test-suite }})"
+          git commit -m "Recordings update from CI (suite: ${{ inputs.suite }})"
           git fetch origin ${{ github.ref_name }}
           git rebase origin/${{ github.ref_name }}
           echo "Rebased successfully"

.github/actions/setup-ollama/action.yml

@@ -1,7 +1,7 @@
 name: Setup Ollama
 description: Start Ollama
 inputs:
-  test-suite:
+  suite:
     description: 'Test suite to use: base, responses, vision, etc.'
     required: false
     default: ''
@@ -11,7 +11,7 @@ runs:
     - name: Start Ollama
       shell: bash
       run: |
-        if [ "${{ inputs.test-suite }}" == "vision" ]; then
+        if [ "${{ inputs.suite }}" == "vision" ]; then
           image="ollama-with-vision-model"
         else
           image="ollama-with-models"

.github/actions/setup-test-environment/action.yml

@@ -8,11 +8,11 @@ inputs:
   client-version:
     description: 'Client version (latest or published)'
     required: true
-  provider:
-    description: 'Provider to setup (ollama or vllm)'
-    required: true
+  setup:
+    description: 'Setup to configure (ollama, vllm, gpt, etc.)'
+    required: false
     default: 'ollama'
-  test-suite:
+  suite:
     description: 'Test suite to use: base, responses, vision, etc.'
     required: false
     default: ''
@@ -30,13 +30,13 @@ runs:
         client-version: ${{ inputs.client-version }}
 
     - name: Setup ollama
-      if: ${{ inputs.provider == 'ollama' && inputs.inference-mode == 'record' }}
+      if: ${{ (inputs.setup == 'ollama' || inputs.setup == 'ollama-vision') && inputs.inference-mode == 'record' }}
       uses: ./.github/actions/setup-ollama
       with:
-        test-suite: ${{ inputs.test-suite }}
+        suite: ${{ inputs.suite }}
 
     - name: Setup vllm
-      if: ${{ inputs.provider == 'vllm' && inputs.inference-mode == 'record' }}
+      if: ${{ inputs.setup == 'vllm' && inputs.inference-mode == 'record' }}
       uses: ./.github/actions/setup-vllm
 
     - name: Build Llama Stack

.github/workflows/integration-tests.yml

@@ -28,8 +28,8 @@ on:
         description: 'Test against both the latest and published versions'
         type: boolean
         default: false
-      test-provider:
-        description: 'Test against a specific provider'
+      test-setup:
+        description: 'Test against a specific setup'
         type: string
         default: 'ollama'
 
@@ -42,18 +42,18 @@ jobs:
 
   run-replay-mode-tests:
     runs-on: ubuntu-latest
-    name: ${{ format('Integration Tests ({0}, {1}, {2}, client={3}, {4})', matrix.client-type, matrix.provider, matrix.python-version, matrix.client-version, matrix.test-suite) }}
+    name: ${{ format('Integration Tests ({0}, {1}, {2}, client={3}, {4})', matrix.client-type, matrix.setup, matrix.python-version, matrix.client-version, matrix.suite) }}
 
     strategy:
       fail-fast: false
       matrix:
         client-type: [library, server]
-        # Use vllm on weekly schedule, otherwise use test-provider input (defaults to ollama)
-        provider: ${{ (github.event.schedule == '1 0 * * 0') && fromJSON('["vllm"]') || fromJSON(format('["{0}"]', github.event.inputs.test-provider || 'ollama')) }}
+        # Use vllm on weekly schedule, otherwise use test-setup input (defaults to ollama)
+        setup: ${{ (github.event.schedule == '1 0 * * 0') && fromJSON('["vllm"]') || fromJSON(format('["{0}"]', github.event.inputs.test-setup || 'ollama')) }}
         # Use Python 3.13 only on nightly schedule (daily latest client test), otherwise use 3.12
         python-version: ${{ github.event.schedule == '0 0 * * *' && fromJSON('["3.12", "3.13"]') || fromJSON('["3.12"]') }}
         client-version: ${{ (github.event.schedule == '0 0 * * *' || github.event.inputs.test-all-client-versions == 'true') && fromJSON('["published", "latest"]') || fromJSON('["latest"]') }}
-        test-suite: [base, vision]
+        suite: [base, vision]
 
     steps:
       - name: Checkout repository
@@ -64,14 +64,14 @@ jobs:
         with:
           python-version: ${{ matrix.python-version }}
           client-version: ${{ matrix.client-version }}
-          provider: ${{ matrix.provider }}
-          test-suite: ${{ matrix.test-suite }}
+          setup: ${{ matrix.setup }}
+          suite: ${{ matrix.suite }}
           inference-mode: 'replay'
 
       - name: Run tests
         uses: ./.github/actions/run-and-record-tests
         with:
           stack-config: ${{ matrix.client-type == 'library' && 'ci-tests' || 'server:ci-tests' }}
-          provider: ${{ matrix.provider }}
+          setup: ${{ matrix.setup }}
           inference-mode: 'replay'
-          test-suite: ${{ matrix.test-suite }}
+          suite: ${{ matrix.suite }}

.github/workflows/pre-commit.yml

@@ -48,7 +48,6 @@ jobs:
         working-directory: llama_stack/ui
 
       - uses: pre-commit/action@2c7b3805fd2a0fd8c1884dcaebf91fc102a13ecd # v3.0.1
-        continue-on-error: true
         env:
           SKIP: no-commit-to-branch
           RUFF_OUTPUT_FORMAT: github

.github/workflows/record-integration-tests.yml

@@ -10,19 +10,19 @@ run-name: Run the integration test suite from tests/integration
 on:
   workflow_dispatch:
     inputs:
-      test-provider:
-        description: 'Test against a specific provider'
+      test-setup:
+        description: 'Test against a specific setup'
         type: string
         default: 'ollama'
-      test-suite:
+      suite:
         description: 'Test suite to use: base, responses, vision, etc.'
         type: string
         default: ''
-      test-subdirs:
-        description: 'Comma-separated list of test subdirectories to run; overrides test-suite'
+      subdirs:
+        description: 'Comma-separated list of test subdirectories to run; overrides suite'
         type: string
         default: ''
-      test-pattern:
+      pattern:
         description: 'Regex pattern to pass to pytest -k'
         type: string
         default: ''
@@ -39,10 +39,10 @@ jobs:
         run: |
           echo "::group::Workflow Inputs"
           echo "branch: ${{ github.ref_name }}"
-          echo "test-provider: ${{ inputs.test-provider }}"
-          echo "test-suite: ${{ inputs.test-suite }}"
-          echo "test-subdirs: ${{ inputs.test-subdirs }}"
-          echo "test-pattern: ${{ inputs.test-pattern }}"
+          echo "test-setup: ${{ inputs.test-setup }}"
+          echo "suite: ${{ inputs.suite }}"
+          echo "subdirs: ${{ inputs.subdirs }}"
+          echo "pattern: ${{ inputs.pattern }}"
           echo "::endgroup::"
 
       - name: Checkout repository
@@ -55,16 +55,16 @@ jobs:
         with:
           python-version: "3.12"  # Use single Python version for recording
           client-version: "latest"
-          provider: ${{ inputs.test-provider || 'ollama' }}
-          test-suite: ${{ inputs.test-suite }}
+          setup: ${{ inputs.test-setup || 'ollama' }}
+          suite: ${{ inputs.suite }}
           inference-mode: 'record'
 
       - name: Run and record tests
         uses: ./.github/actions/run-and-record-tests
         with:
           stack-config: 'server:ci-tests'  # recording must be done with server since more tests are run
-          provider: ${{ inputs.test-provider || 'ollama' }}
+          setup: ${{ inputs.test-setup || 'ollama' }}
           inference-mode: 'record'
-          test-suite: ${{ inputs.test-suite }}
-          test-subdirs: ${{ inputs.test-subdirs }}
-          test-pattern: ${{ inputs.test-pattern }}
+          suite: ${{ inputs.suite }}
+          subdirs: ${{ inputs.subdirs }}
+          pattern: ${{ inputs.pattern }}