Merge branch 'main' into fixes_for_gaudi

Author: Mahathi-Vatsal

.github/ISSUE_TEMPLATE/1_bug_template.yml

@@ -32,6 +32,7 @@ body:
         - Mac
         - BSD
         - Other (Please let us know in description)
+        - N/A
     validations:
       required: true
 
@@ -56,6 +57,7 @@ body:
         - GPU-Nvidia
         - GPU-AMD
         - GPU-other (Please let us know in description)
+        - N/A
     validations:
       required: true
 
@@ -67,6 +69,7 @@ body:
         - label: Pull docker images from hub.docker.com
         - label: Build docker images from source
         - label: Other
+        - label: N/A
     validations:
       required: true
 
@@ -80,6 +83,7 @@ body:
         - label: Kubernetes Helm Charts
         - label: Kubernetes GMC
         - label: Other
+        - label: N/A
     validations:
       required: true
 
@@ -91,6 +95,7 @@ body:
         - Single Node
         - Multiple Nodes
         - Other
+        - N/A
       default: 0
     validations:
       required: true

.github/ISSUE_TEMPLATE/2_feature_template.yml

@@ -32,6 +32,7 @@ body:
         - Mac
         - BSD
         - Other (Please let us know in description)
+        - N/A
     validations:
       required: true
 
@@ -56,6 +57,7 @@ body:
         - GPU-Nvidia
         - GPU-AMD
         - GPU-other (Please let us know in description)
+        - N/A
     validations:
       required: true
 
@@ -67,6 +69,7 @@ body:
         - Single Node
         - Multiple Nodes
         - Other
+        - N/A
       default: 0
     validations:
       required: true

.github/workflows/_helm-e2e.yml

@@ -81,6 +81,10 @@ jobs:
                 if [[ "${{ inputs.hardware }}" == "gaudi" ]]; then
                   value_files="${value_files}\"${filename}\","
                 fi
+              elif [[ "$filename" == *"rocm"* ]]; then
+                if [[ "${{ inputs.hardware }}" == "rocm" ]]; then
+                  value_files="${value_files}\"${filename}\","
+                fi
               elif [[ "$filename" == *"nv"* ]]; then
                 continue
               else

.github/workflows/nightly-docker-build-publish.yml

@@ -5,7 +5,7 @@ name: Nightly build/publish latest docker images
 
 on:
   schedule:
-    - cron: "30 14 * * *" # UTC time
+    - cron: "30 14 * * 1-5" # UTC time
   workflow_dispatch:
 
 env:
@@ -38,30 +38,44 @@ jobs:
     with:
       node: gaudi
 
-  build-and-test:
-    needs: get-build-matrix
+  build-images:
+    needs: [get-build-matrix, build-comps-base]
+    strategy:
+      matrix:
+        example: ${{ fromJSON(needs.get-build-matrix.outputs.examples_json) }}
+      fail-fast: false
+    uses: ./.github/workflows/_build_image.yml
+    with:
+      node: gaudi
+      example: ${{ matrix.example }}
+      inject_commit: true
+    secrets: inherit
+
+  test-example:
+    needs: [get-build-matrix]
     if: ${{ needs.get-build-matrix.outputs.examples_json != '' }}
     strategy:
       matrix:
         example: ${{ fromJSON(needs.get-build-matrix.outputs.examples_json) }}
       fail-fast: false
     uses: ./.github/workflows/_example-workflow.yml
     with:
-      node: gaudi
+      node: xeon
+      build: false
       example: ${{ matrix.example }}
       test_compose: true
       inject_commit: true
     secrets: inherit
 
   get-image-list:
-    needs: get-build-matrix
+    needs: [get-build-matrix]
     uses: ./.github/workflows/_get-image-list.yml
     with:
       examples: ${{ needs.get-build-matrix.outputs.EXAMPLES }}
 
   publish:
-    needs: [get-build-matrix, get-image-list, build-and-test]
-    if: always() && ${{ needs.get-image-list.outputs.matrix != '' }}
+    needs: [get-build-matrix, get-image-list, build-images]
+    if: always()
     strategy:
       matrix:
         image: ${{ fromJSON(needs.get-image-list.outputs.matrix) }}

.github/workflows/pr-chart-e2e.yml

@@ -46,6 +46,8 @@ jobs:
               example=$(echo "$values_file" | cut -d'/' -f1) # CodeGen
               if [[ "$valuefile" == *"gaudi"* ]]; then
                 hardware="gaudi"
+              elif [[ "$valuefile" == *"rocm"* ]]; then
+                hardware="rocm"
               elif [[ "$valuefile" == *"nv"* ]]; then
                 continue
               else

.github/workflows/weekly-example-test.yml

@@ -0,0 +1,55 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+name: Weekly test all examples on multiple HWs
+
+on:
+  schedule:
+    - cron: "30 2 * * 6" # UTC time
+  workflow_dispatch:
+
+env:
+  EXAMPLES: ${{ vars.NIGHTLY_RELEASE_EXAMPLES }}
+  NODES: "gaudi,xeon,rocm,arc"
+
+jobs:
+  get-test-matrix:
+    runs-on: ubuntu-latest
+    outputs:
+      examples: ${{ steps.get-matrix.outputs.examples }}
+      nodes: ${{ steps.get-matrix.outputs.nodes }}
+    steps:
+      - name: Create Matrix
+        id: get-matrix
+        run: |
+          examples=($(echo ${EXAMPLES} | tr ',' ' '))
+          examples_json=$(printf '%s\n' "${examples[@]}" | sort -u | jq -R '.' | jq -sc '.')
+          echo "examples=$examples_json" >> $GITHUB_OUTPUT
+          nodes=($(echo ${NODES} | tr ',' ' '))
+          nodes_json=$(printf '%s\n' "${nodes[@]}" | sort -u | jq -R '.' | jq -sc '.')
+          echo "nodes=$nodes_json" >> $GITHUB_OUTPUT
+
+  build-comps-base:
+    needs: [get-test-matrix]
+    strategy:
+      matrix:
+        node: ${{ fromJson(needs.get-test-matrix.outputs.nodes) }}
+    uses: ./.github/workflows/_build_comps_base_image.yml
+    with:
+      node: ${{ matrix.node }}
+
+  run-examples:
+    needs: [get-test-matrix, build-comps-base]
+    strategy:
+      matrix:
+        example: ${{ fromJson(needs.get-test-matrix.outputs.examples) }}
+        node: ${{ fromJson(needs.get-test-matrix.outputs.nodes) }}
+      fail-fast: false
+    uses: ./.github/workflows/_example-workflow.yml
+    with:
+      node: ${{ matrix.node }}
+      example: ${{ matrix.example }}
+      build: true
+      test_compose: true
+      test_helmchart: true
+    secrets: inherit

AgentQnA/README.md

@@ -4,7 +4,7 @@
 
 1. [Overview](#overview)
 2. [Deploy with Docker](#deploy-with-docker)
-3. [Launch the UI](#launch-the-ui)
+3. [How to interact with the agent system with UI](#how-to-interact-with-the-agent-system-with-ui)
 4. [Validate Services](#validate-services)
 5. [Register Tools](#how-to-register-other-tools-with-the-ai-agent)
 
@@ -144,21 +144,19 @@ source $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/cpu/xeon/set_env.sh
 
 ### 2. Launch the multi-agent system. </br>
 
-Two options are provided for the `llm_engine` of the agents: 1. open-source LLMs on Gaudi, 2. OpenAI models via API calls.
+We make it convenient to launch the whole system with docker compose, which includes microservices for LLM, agents, UI, retrieval tool, vector database, dataprep, and telemetry. There are 3 docker compose files, which make it easy for users to pick and choose. Users can choose a different retrieval tool other than the `DocIndexRetriever` example provided in our GenAIExamples repo. Users can choose not to launch the telemetry containers.
 
-#### Gaudi
+#### Launch on Gaudi
 
-On Gaudi, `meta-llama/Meta-Llama-3.1-70B-Instruct` will be served using vllm.
-By default, both the RAG agent and SQL agent will be launched to support the React Agent.  
-The React Agent requires the DocIndexRetriever's [`compose.yaml`](../DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml) file, so two `compose.yaml` files need to be run with docker compose to start the multi-agent system.
-
-> **Note**: To enable the web search tool, skip this step and proceed to the "[Optional] Web Search Tool Support" section.
+On Gaudi, `meta-llama/Meta-Llama-3.3-70B-Instruct` will be served using vllm. The command below will launch the multi-agent system with the `DocIndexRetriever` as the retrieval tool for the Worker RAG agent.
 
 ```bash
 cd $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/hpu/gaudi/
 docker compose -f $WORKDIR/GenAIExamples/DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml -f compose.yaml up -d
 ```
 
+> **Note**: To enable the web search tool, skip this step and proceed to the "[Optional] Web Search Tool Support" section.
+
 To enable Open Telemetry Tracing, compose.telemetry.yaml file need to be merged along with default compose.yaml file.
 Gaudi example with Open Telemetry feature:
 
@@ -183,11 +181,9 @@ docker compose -f $WORKDIR/GenAIExamples/DocIndexRetriever/docker_compose/intel/
 
 </details>
 
-#### Xeon
+#### Launch on Xeon
 
-On Xeon, only OpenAI models are supported.
-By default, both the RAG Agent and SQL Agent will be launched to support the React Agent.  
-The React Agent requires the DocIndexRetriever's [`compose.yaml`](../DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml) file, so two `compose yaml` files need to be run with docker compose to start the multi-agent system.
+On Xeon, only OpenAI models are supported. The command below will launch the multi-agent system with the `DocIndexRetriever` as the retrieval tool for the Worker RAG agent.
 
 ```bash
 export OPENAI_API_KEY=<your-openai-key>
@@ -206,9 +202,10 @@ bash run_ingest_data.sh
 
 > **Note**: This is a one-time operation.
 
-## Launch the UI
+## How to interact with the agent system with UI
 
-Open a web browser to http://localhost:5173 to access the UI.
+The UI microservice is launched in the previous step with the other microservices.
+To see the UI, open a web browser to `http://${ip_address}:5173` to access the UI. Note the `ip_address` here is the host IP of the UI microservice.
 
 1. `create Admin Account` with a random value
 2. add opea agent endpoint `http://$ip_address:9090/v1` which is a openai compatible api

AgentQnA/docker_compose/intel/hpu/gaudi/compose.yaml

@@ -104,7 +104,7 @@ services:
       - "8080:8000"
     ipc: host
   agent-ui:
-    image: opea/agent-ui
+    image: opea/agent-ui:latest
     container_name: agent-ui
     environment:
       host_ip: ${host_ip}
@@ -138,4 +138,4 @@ services:
     cap_add:
       - SYS_NICE
     ipc: host
-    command: --model $LLM_MODEL_ID --tensor-parallel-size 4 --host 0.0.0.0 --port 8000 --block-size 128 --max-num-seqs 256 --max-seq_len-to-capture 16384
+    command: --model $LLM_MODEL_ID --tensor-parallel-size 4 --host 0.0.0.0 --port 8000 --block-size 128 --max-num-seqs 256 --max-seq-len-to-capture 16384

AgentQnA/kubernetes/helm/cpu-values.yaml

@@ -6,7 +6,7 @@ tgi:
 vllm:
   enabled: true
   LLM_MODEL_ID: "meta-llama/Meta-Llama-3-8B-Instruct"
-  extraCmdArgs: ["--max-seq_len-to-capture", "16384", "--enable-auto-tool-choice", "--tool-call-parser", "llama3_json"]
+  extraCmdArgs: ["--max-seq-len-to-capture", "16384", "--enable-auto-tool-choice", "--tool-call-parser", "llama3_json"]
 
 supervisor:
   llm_endpoint_url: http://{{ .Release.Name }}-vllm

AgentQnA/kubernetes/helm/gaudi-values.yaml

@@ -19,7 +19,7 @@ vllm:
   PT_HPU_ENABLE_LAZY_COLLECTIVES: true
   VLLM_SKIP_WARMUP: true
   shmSize: 16Gi
-  extraCmdArgs: ["--tensor-parallel-size", "4", "--max-seq_len-to-capture", "16384", "--enable-auto-tool-choice", "--tool-call-parser", "llama3_json"]
+  extraCmdArgs: ["--tensor-parallel-size", "4", "--max-seq-len-to-capture", "16384", "--enable-auto-tool-choice", "--tool-call-parser", "llama3_json"]
 
 supervisor:
   llm_endpoint_url: http://{{ .Release.Name }}-vllm