Merge branch 'main' into multiple-model-with-remote-service

.github/code_spell_ignore.txt

@@ -0,0 +1,2 @@
+ModelIn
+modelin

.github/workflows/_example-workflow.yml

@@ -77,6 +77,10 @@ jobs:
               git clone https://github.com/vllm-project/vllm.git
               cd vllm && git rev-parse HEAD && cd ../
           fi
+          if [[ $(grep -c "vllm-hpu:" ${docker_compose_path}) != 0 ]]; then
+               git clone https://github.com/HabanaAI/vllm-fork.git
+               cd vllm-fork && git rev-parse HEAD && cd ../
+          fi
           git clone https://github.com/opea-project/GenAIComps.git
           cd GenAIComps && git checkout ${{ inputs.opea_branch }} && git rev-parse HEAD && cd ../
 

.github/workflows/check-online-doc-build.yml

@@ -0,0 +1,35 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+name: Check Online Document Building
+permissions: {}
+
+on:
+  pull_request:
+    branches: [main]
+    paths:
+      - "**.md"
+      - "**.rst"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+
+    - name: Checkout
+      uses: actions/checkout@v4
+      with:
+        path: GenAIExamples
+
+    - name: Checkout docs
+      uses: actions/checkout@v4
+      with:
+        repository: opea-project/docs
+        path: docs
+
+    - name: Build Online Document
+      shell: bash
+      run: |
+        echo "build online doc"
+        cd docs
+        bash scripts/build.sh

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

@@ -42,7 +42,6 @@ jobs:
     with:
       node: gaudi
       example: ${{ matrix.example }}
-      inject_commit: true
     secrets: inherit
 
   get-image-list:

.github/workflows/pr-path-detection.yml

@@ -61,14 +61,14 @@ jobs:
           changed_files="$(git diff --name-status --diff-filter=ARM ${{ github.event.pull_request.base.sha }} ${merged_commit} | awk '/\.md$/ {print $NF}')"
           if  [ -n "$changed_files" ]; then
             for changed_file in $changed_files; do
-              echo $changed_file
+              # echo $changed_file
               url_lines=$(grep -H -Eo '\]\(http[s]?://[^)]+\)' "$changed_file" | grep -Ev 'GenAIExamples/blob/main') || true
               if [ -n "$url_lines" ]; then
                 for url_line in $url_lines; do
-                  echo $url_line
+                  # echo $url_line
                   url=$(echo "$url_line"|cut -d '(' -f2 | cut -d ')' -f1|sed 's/\.git$//')
                   path=$(echo "$url_line"|cut -d':' -f1 | cut -d'/' -f2-)
-                  response=$(curl -L -s -o /dev/null -w "%{http_code}" "$url")
+                  response=$(curl -L -s -o /dev/null -w "%{http_code}" "$url")|| true
                   if [ "$response" -ne 200 ]; then
                     echo "**********Validation failed, try again**********"
                     response_retry=$(curl -s -o /dev/null -w "%{http_code}" "$url")

ChatQnA/benchmark/performance/kubernetes/intel/gaudi/README.md

@@ -0,0 +1,204 @@
+# ChatQnA Benchmarking
+
+This folder contains a collection of Kubernetes manifest files for deploying the ChatQnA service across scalable nodes. It includes a comprehensive [benchmarking tool](https://github.com/opea-project/GenAIEval/blob/main/evals/benchmark/README.md) that enables throughput analysis to assess inference performance.
+
+By following this guide, you can run benchmarks on your deployment and share the results with the OPEA community.
+
+## Purpose
+
+We aim to run these benchmarks and share them with the OPEA community for three primary reasons:
+
+- To offer insights on inference throughput in real-world scenarios, helping you choose the best service or deployment for your needs.
+- To establish a baseline for validating optimization solutions across different implementations, providing clear guidance on which methods are most effective for your use case.
+- To inspire the community to build upon our benchmarks, allowing us to better quantify new solutions in conjunction with current leading llms, serving frameworks etc.
+
+## Metrics
+
+The benchmark will report the below metrics, including:
+
+- Number of Concurrent Requests
+- End-to-End Latency: P50, P90, P99 (in milliseconds)
+- End-to-End First Token Latency: P50, P90, P99 (in milliseconds)
+- Average Next Token Latency (in milliseconds)
+- Average Token Latency (in milliseconds)
+- Requests Per Second (RPS)
+- Output Tokens Per Second
+- Input Tokens Per Second
+
+Results will be displayed in the terminal and saved as CSV file named `1_stats.csv` for easy export to spreadsheets.
+
+## Table of Contents
+
+- [Deployment](#deployment)
+  - [Prerequisites](#prerequisites)
+  - [Deployment Scenarios](#deployment-scenarios)
+    - [Case 1: Baseline Deployment with Rerank](#case-1-baseline-deployment-with-rerank)
+    - [Case 2: Baseline Deployment without Rerank](#case-2-baseline-deployment-without-rerank)
+    - [Case 3: Tuned Deployment with Rerank](#case-3-tuned-deployment-with-rerank)
+- [Benchmark](#benchmark)
+  - [Test Configurations](#test-configurations)
+  - [Test Steps](#test-steps)
+    - [Upload Retrieval File](#upload-retrieval-file)
+    - [Run Benchmark Test](#run-benchmark-test)
+    - [Data collection](#data-collection)
+- [Teardown](#teardown)
+
+## Deployment
+
+### Prerequisites
+
+- Kubernetes installation: Use [kubespray](https://github.com/opea-project/docs/blob/main/guide/installation/k8s_install/k8s_install_kubespray.md) or other official Kubernetes installation guides.
+- Helm installation: Follow the [Helm documentation](https://helm.sh/docs/intro/install/#helm) to install Helm.
+- Setup Hugging Face Token
+
+  To access models and APIs from Hugging Face, set your token as environment variable.
+  ```bash
+  export HF_TOKEN="insert-your-huggingface-token-here"
+  ```
+- Prepare Shared Models (Optional but Strongly Recommended)
+
+  Downloading models simultaneously to multiple nodes in your cluster can overload resources such as network bandwidth, memory and storage. To prevent resource exhaustion, it's recommended to preload the models in advance.
+  ```bash
+  pip install -U "huggingface_hub[cli]"
+  sudo mkdir -p /mnt/models
+  sudo chmod 777 /mnt/models
+  huggingface-cli download --cache-dir /mnt/models Intel/neural-chat-7b-v3-3
+  export MODEL_DIR=/mnt/models
+  ```
+  Once the models are downloaded, you can consider the following methods for sharing them across nodes:
+  - Persistent Volume Claim (PVC): This is the recommended approach for production setups. For more details on using PVC, refer to [PVC](https://github.com/opea-project/GenAIInfra/blob/main/helm-charts/README.md#using-persistent-volume).
+  - Local Host Path: For simpler testing, ensure that each node involved in the deployment follows the steps above to locally prepare the models. After preparing the models, use `--set global.modelUseHostPath=${MODELDIR}` in the deployment command.
+
+- Add OPEA Helm Repository:
+  ```bash
+  python deploy.py --add-repo
+  ```
+- Label Nodes
+  ```base
+  python deploy.py --add-label --num-nodes 2
+  ```
+
+### Deployment Scenarios
+
+The example below are based on a two-node setup. You can adjust the number of nodes by using the `--num-nodes` option.
+
+By default, these commands use the `default` namespace. To specify a different namespace, use the `--namespace` flag with deploy, uninstall, and kubernetes command. Additionally, update the `namespace` field in `benchmark.yaml` before running the benchmark test.
+
+For additional configuration options, run `python deploy.py --help`
+
+#### Case 1: Baseline Deployment with Rerank
+
+Deploy Command (with node number, Hugging Face token, model directory specified):
+```bash
+python deploy.py --hf-token $HF_TOKEN --model-dir $MODEL_DIR --num-nodes 2 --with-rerank
+```
+Uninstall Command:
+```bash
+python deploy.py --uninstall
+```
+
+#### Case 2: Baseline Deployment without Rerank
+
+```bash
+python deploy.py --hftoken $HFTOKEN --modeldir $MODELDIR --num-nodes 2
+```
+#### Case 3: Tuned Deployment with Rerank
+
+```bash
+python deploy.py --hftoken $HFTOKEN --modeldir $MODELDIR --num-nodes 2 --with-rerank --tuned
+```
+
+## Benchmark
+
+### Test Configurations
+
+| Key      | Value   |
+| -------- | ------- |
+| Workload | ChatQnA |
+| Tag      | V1.1    |
+
+Models configuration
+| Key | Value |
+| ---------- | ------------------ |
+| Embedding | BAAI/bge-base-en-v1.5 |
+| Reranking | BAAI/bge-reranker-base |
+| Inference | Intel/neural-chat-7b-v3-3 |
+
+Benchmark parameters
+| Key | Value |
+| ---------- | ------------------ |
+| LLM input tokens | 1024 |
+| LLM output tokens | 128 |
+
+Number of test requests for different scheduled node number:
+| Node count | Concurrency | Query number |
+| ----- | -------- | -------- |
+| 1 | 128 | 640 |
+| 2 | 256 | 1280 |
+| 4 | 512 | 2560 |
+
+More detailed configuration can be found in configuration file [benchmark.yaml](./benchmark.yaml).
+
+### Test Steps
+
+Use `kubectl get pods` to confirm that all pods are `READY` before starting the test.
+
+#### Upload Retrieval File
+
+Before testing, upload a specified file to make sure the llm input have the token length of 1k.
+
+Get files:
+
+```bash
+wget https://github.com/opea-project/GenAIEval/tree/main/evals/benchmark/data/upload_file_no_rerank.txt
+wget https://github.com/opea-project/GenAIEval/tree/main/evals/benchmark/data/upload_file.txt
+```
+
+Retrieve the `ClusterIP` of the `chatqna-data-prep` service.
+
+```bash
+kubectl get svc
+```
+Expected output:
+```log
+chatqna-data-prep         ClusterIP   xx.xx.xx.xx    <none>        6007/TCP            51m
+```
+
+Use the following `cURL` command to upload file:
+
+```bash
+cd GenAIEval/evals/benchmark/data
+# RAG with Rerank
+curl -X POST "http://${cluster_ip}:6007/v1/dataprep" \
+     -H "Content-Type: multipart/form-data" \
+     -F "files=@./upload_file.txt"
+# RAG without Rerank
+curl -X POST "http://${cluster_ip}:6007/v1/dataprep" \
+     -H "Content-Type: multipart/form-data" \
+     -F "files=@./upload_file_no_rerank.txt"
+```
+
+#### Run Benchmark Test
+
+Run the benchmark test using:
+```bash
+bash benchmark.sh -n 2
+```
+The `-n` argument specifies the number of test nodes. Required dependencies will be automatically installed when running the benchmark for the first time.
+
+#### Data collection
+
+All the test results will come to the folder `GenAIEval/evals/benchmark/benchmark_output`.
+
+## Teardown
+
+After completing the benchmark, use the following commands to clean up the environment:
+
+Remove Node Labels:
+```base
+python deploy.py --delete-label
+```
+Delete the OPEA Helm Repository:
+```bash
+python deploy.py --delete-repo
+```

ChatQnA/benchmark/performance/kubernetes/intel/gaudi/benchmark.sh

@@ -0,0 +1,99 @@
+#!/bin/bash
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+deployment_type="k8s"
+node_number=1
+service_port=8888
+query_per_node=640
+
+benchmark_tool_path="$(pwd)/GenAIEval"
+
+usage() {
+    echo "Usage: $0 [-d deployment_type] [-n node_number] [-i service_ip] [-p service_port]"
+    echo "  -d deployment_type    ChatQnA deployment type, select between k8s and docker (default: k8s)"
+    echo "  -n node_number        Test node number, required only for k8s deployment_type, (default: 1)"
+    echo "  -i service_ip         chatqna service ip, required only for docker deployment_type"
+    echo "  -p service_port       chatqna service port, required only for docker deployment_type, (default: 8888)"
+    exit 1
+}
+
+while getopts ":d:n:i:p:" opt; do
+    case ${opt} in
+        d )
+            deployment_type=$OPTARG
+            ;;
+        n )
+            node_number=$OPTARG
+            ;;
+        i )
+            service_ip=$OPTARG
+            ;;
+        p )
+            service_port=$OPTARG
+            ;;
+        \? )
+            echo "Invalid option: -$OPTARG" 1>&2
+            usage
+            ;;
+        : )
+            echo "Invalid option: -$OPTARG requires an argument" 1>&2
+            usage
+            ;;
+    esac
+done
+
+if [[ "$deployment_type" == "docker" && -z "$service_ip" ]]; then
+    echo "Error: service_ip is required for docker deployment_type" 1>&2
+    usage
+fi
+
+if [[ "$deployment_type" == "k8s" && ( -n "$service_ip" || -n "$service_port" ) ]]; then
+    echo "Warning: service_ip and service_port are ignored for k8s deployment_type" 1>&2
+fi
+
+function main() {
+    if [[ ! -d ${benchmark_tool_path} ]]; then
+        echo "Benchmark tool not found, setting up..."
+        setup_env
+    fi
+    run_benchmark
+}
+
+function setup_env() {
+    git clone https://github.com/opea-project/GenAIEval.git
+    pushd ${benchmark_tool_path}
+    python3 -m venv stress_venv
+    source stress_venv/bin/activate
+    pip install -r requirements.txt
+    popd
+}
+
+function run_benchmark() {
+    source ${benchmark_tool_path}/stress_venv/bin/activate
+    export DEPLOYMENT_TYPE=${deployment_type}
+    export SERVICE_IP=${service_ip:-"None"}
+    export SERVICE_PORT=${service_port:-"None"}
+    if [[ -z $USER_QUERIES ]]; then
+        user_query=$((query_per_node*node_number))
+        export USER_QUERIES="[${user_query}, ${user_query}, ${user_query}, ${user_query}]"
+        echo "USER_QUERIES not configured, setting to: ${USER_QUERIES}."
+    fi
+    export WARMUP=$(echo $USER_QUERIES | sed -e 's/[][]//g' -e 's/,.*//')
+    if [[ -z $WARMUP ]]; then export WARMUP=0; fi
+    if [[ -z $TEST_OUTPUT_DIR ]]; then
+        if [[ $DEPLOYMENT_TYPE == "k8s" ]]; then
+            export TEST_OUTPUT_DIR="${benchmark_tool_path}/evals/benchmark/benchmark_output/node_${node_number}"
+        else
+            export TEST_OUTPUT_DIR="${benchmark_tool_path}/evals/benchmark/benchmark_output/docker"
+        fi
+        echo "TEST_OUTPUT_DIR not configured, setting to: ${TEST_OUTPUT_DIR}."
+    fi
+
+    envsubst < ./benchmark.yaml > ${benchmark_tool_path}/evals/benchmark/benchmark.yaml
+    cd ${benchmark_tool_path}/evals/benchmark
+    python benchmark.py
+}
+
+main