Added the tests and renamed the files

Signed-off-by: Pallavi Jaini <[email protected]>

ChatQnA/docker/xeon/README_pinecone.md

@@ -148,7 +148,7 @@ Then run the command `docker images`, you will have the following 7 Docker Image
 
 ### Setup Environment Variables
 
-Since the `docker_compose_pinecone.yaml` will consume some environment variables, you need to setup them in advance as below.
+Since the `compose_pinecone.yaml` will consume some environment variables, you need to setup them in advance as below.
 
 **Export the value of the public IP address of your Xeon server to the `host_ip` environment variable**
 
@@ -212,7 +212,7 @@ Note: Please replace with `host_ip` with you external IP address, do not use loc
 
 ```bash
 cd GenAIExamples/ChatQnA/docker/xeon/
-docker compose -f docker_compose_pinecone.yaml up -d
+docker compose -f compose_pinecone.yaml up -d
 ```
 
 ### Validate Microservices
@@ -330,7 +330,7 @@ curl -X POST "http://${host_ip}:6008/v1/dataprep/get_file" \
 
 ## Enable LangSmith for Monotoring Application (Optional)
 
-LangSmith offers tools to debug, evaluate, and monitor language models and intelligent agents. It can be used to assess benchmark data for each microservice. Before launching your services with `docker compose -f docker_compose_pinecone.yaml up -d`, you need to enable LangSmith tracing by setting the `LANGCHAIN_TRACING_V2` environment variable to true and configuring your LangChain API key.
+LangSmith offers tools to debug, evaluate, and monitor language models and intelligent agents. It can be used to assess benchmark data for each microservice. Before launching your services with `docker compose -f compose_pinecone.yaml up -d`, you need to enable LangSmith tracing by setting the `LANGCHAIN_TRACING_V2` environment variable to true and configuring your LangChain API key.
 
 Here's how you can do it:
 

ChatQnA/tests/_test_chatqna_pinecone_on_xeon.sh

@@ -0,0 +1,232 @@
+#!/bin/bash
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+set -e
+echo "IMAGE_REPO=${IMAGE_REPO}"
+
+WORKPATH=$(dirname "$PWD")
+LOG_PATH="$WORKPATH/tests"
+ip_address=$(hostname -I | awk '{print $1}')
+
+function build_docker_images() {
+    cd $WORKPATH
+    git clone https://github.com/opea-project/GenAIComps.git
+    cd GenAIComps
+
+    docker build -t opea/embedding-tei:latest -f comps/embeddings/langchain/docker/Dockerfile .
+    docker build -t opea/retriever-pinecone:latest -f comps/retrievers/langchain/pinecone/docker/Dockerfile .
+    docker build -t opea/reranking-tei:latest -f comps/reranks/tei/docker/Dockerfile .
+    docker build -t opea/llm-tgi:latest -f comps/llms/text-generation/tgi/Dockerfile .
+    docker build -t opea/dataprep-pinecone:latest -f comps/dataprep/pinecone/docker/Dockerfile .
+
+    cd $WORKPATH/docker
+    docker build --no-cache -t opea/chatqna:latest -f Dockerfile .
+
+    cd $WORKPATH/docker/ui
+    docker build --no-cache -t opea/chatqna-ui:latest -f docker/Dockerfile .
+
+    docker images
+}
+
+function start_services() {
+    cd $WORKPATH/docker/xeon
+
+    export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
+    export RERANK_MODEL_ID="BAAI/bge-reranker-base"
+    export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
+    export TEI_EMBEDDING_ENDPOINT="http://${ip_address}:6006"
+    export TEI_RERANKING_ENDPOINT="http://${ip_address}:8808"
+    export TGI_LLM_ENDPOINT="http://${ip_address}:9009"
+    export PINECONE_API_KEY=${PINECONE_KEY}
+    export PINECONE_INDEX_NAME="langchain-test"
+    export INDEX_NAME="langchain-test"
+    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    export MEGA_SERVICE_HOST_IP=${ip_address}
+    export EMBEDDING_SERVICE_HOST_IP=${ip_address}
+    export RETRIEVER_SERVICE_HOST_IP=${ip_address}
+    export RERANK_SERVICE_HOST_IP=${ip_address}
+    export LLM_SERVICE_HOST_IP=${ip_address}
+    export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:8888/v1/chatqna"
+    export DATAPREP_SERVICE_ENDPOINT="http://${ip_address}:6007/v1/dataprep"
+    export DATAPREP_GET_FILE_ENDPOINT="http://${ip_address}:6007/v1/dataprep/get_file"
+    export DATAPREP_DELETE_FILE_ENDPOINT="http://${ip_address}:6007/v1/dataprep/delete_file"
+
+    sed -i "s/backend_address/$ip_address/g" $WORKPATH/docker/ui/svelte/.env
+
+    if [[ "$IMAGE_REPO" != "" ]]; then
+        # Replace the container name with a test-specific name
+        echo "using image repository $IMAGE_REPO and image tag $IMAGE_TAG"
+        sed -i "s#image: opea/chatqna:latest#image: opea/chatqna:${IMAGE_TAG}#g" compose_pinecone.yaml
+        sed -i "s#image: opea/chatqna-ui:latest#image: opea/chatqna-ui:${IMAGE_TAG}#g" compose_pinecone.yaml
+        sed -i "s#image: opea/chatqna-conversation-ui:latest#image: opea/chatqna-conversation-ui:${IMAGE_TAG}#g" compose_pinecone.yaml
+        sed -i "s#image: opea/*#image: ${IMAGE_REPO}opea/#g" compose_pinecone.yaml
+        cat compose_pinecone.yaml
+    fi
+
+    # Start Docker Containers
+    docker compose -f compose_pinecone.yaml up -d
+    n=0
+    until [[ "$n" -ge 200 ]]; do
+        docker logs tgi-service > tgi_service_start.log
+        if grep -q Connected tgi_service_start.log; then
+            break
+        fi
+        sleep 1s
+        n=$((n+1))
+    done
+}
+
+function validate_services() {
+    local URL="$1"
+    local EXPECTED_RESULT="$2"
+    local SERVICE_NAME="$3"
+    local DOCKER_NAME="$4"
+    local INPUT_DATA="$5"
+
+    local HTTP_STATUS=$(curl -s -o /dev/null -w "%{http_code}" -X POST -d "$INPUT_DATA" -H 'Content-Type: application/json' "$URL")
+    if [ "$HTTP_STATUS" -eq 200 ]; then
+        echo "[ $SERVICE_NAME ] HTTP status is 200. Checking content..."
+
+        local CONTENT=$(curl -s -X POST -d "$INPUT_DATA" -H 'Content-Type: application/json' "$URL" | tee ${LOG_PATH}/${SERVICE_NAME}.log)
+
+        if echo "$CONTENT" | grep -q "$EXPECTED_RESULT"; then
+            echo "[ $SERVICE_NAME ] Content is as expected."
+        else
+            echo "[ $SERVICE_NAME ] Content does not match the expected result: $CONTENT"
+            docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log
+            exit 1
+        fi
+    else
+        echo "[ $SERVICE_NAME ] HTTP status is not 200. Received status was $HTTP_STATUS"
+        docker logs ${DOCKER_NAME} >> ${LOG_PATH}/${SERVICE_NAME}.log
+        exit 1
+    fi
+    sleep 1s
+}
+
+function validate_microservices() {
+    # Check if the microservices are running correctly.
+
+    # tei for embedding service
+    validate_services \
+        "${ip_address}:6006/embed" \
+        "\[\[" \
+        "tei-embedding" \
+        "tei-embedding-server" \
+        '{"inputs":"What is Deep Learning?"}'
+
+    # embedding microservice
+    validate_services \
+        "${ip_address}:6000/v1/embeddings" \
+        '"text":"What is Deep Learning?","embedding":\[' \
+        "embedding" \
+        "embedding-tei-server" \
+        '{"text":"What is Deep Learning?"}'
+
+    sleep 1m # retrieval can't curl as expected, try to wait for more time
+
+    # retrieval microservice
+    test_embedding=$(python3 -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
+    validate_services \
+        "${ip_address}:7000/v1/retrieval" \
+        " " \
+        "retrieval" \
+        "retriever-pinecone-server" \
+        "{\"text\":\"What is the revenue of Nike in 2023?\",\"embedding\":${test_embedding}}"
+
+    # tei for rerank microservice
+    validate_services \
+        "${ip_address}:8808/rerank" \
+        '{"index":1,"score":' \
+        "tei-rerank" \
+        "tei-reranking-server" \
+        '{"query":"What is Deep Learning?", "texts": ["Deep Learning is not...", "Deep learning is..."]}'
+
+    # rerank microservice
+    validate_services \
+        "${ip_address}:8000/v1/reranking" \
+        "Deep learning is..." \
+        "rerank" \
+        "reranking-tei-xeon-server" \
+        '{"initial_query":"What is Deep Learning?", "retrieved_docs": [{"text":"Deep Learning is not..."}, {"text":"Deep learning is..."}]}'
+
+    # tgi for llm service
+    validate_services \
+        "${ip_address}:9009/generate" \
+        "generated_text" \
+        "tgi-llm" \
+        "tgi-service" \
+        '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17, "do_sample": true}}'
+
+    # llm microservice
+    validate_services \
+        "${ip_address}:9000/v1/chat/completions" \
+        "data: " \
+        "llm" \
+        "llm-tgi-server" \
+        '{"query":"What is Deep Learning?"}'
+
+}
+
+function validate_megaservice() {
+    # Curl the Mega Service
+    validate_services \
+        "${ip_address}:8888/v1/chatqna" \
+        "billion" \
+        "mega-chatqna" \
+        "chatqna-xeon-backend-server" \
+        '{"messages": "What is the revenue of Nike in 2023?"}'
+
+}
+
+function validate_frontend() {
+    cd $WORKPATH/docker/ui/svelte
+    local conda_env_name="OPEA_e2e"
+    export PATH=${HOME}/miniforge3/bin/:$PATH
+#    conda remove -n ${conda_env_name} --all -y
+#    conda create -n ${conda_env_name} python=3.12 -y
+    source activate ${conda_env_name}
+
+    sed -i "s/localhost/$ip_address/g" playwright.config.ts
+
+#    conda install -c conda-forge nodejs -y
+    npm install && npm ci && npx playwright install --with-deps
+    node -v && npm -v && pip list
+
+    exit_status=0
+    npx playwright test || exit_status=$?
+
+    if [ $exit_status -ne 0 ]; then
+        echo "[TEST INFO]: ---------frontend test failed---------"
+        exit $exit_status
+    else
+        echo "[TEST INFO]: ---------frontend test passed---------"
+    fi
+}
+
+function stop_docker() {
+    cd $WORKPATH/docker/xeon
+    docker compose stop && docker compose rm -f
+}
+
+function main() {
+
+    stop_docker
+    if [[ "$IMAGE_REPO" == "" ]]; then build_docker_images; fi
+    start_time=$(date +%s)
+    start_services
+    end_time=$(date +%s)
+    duration=$((end_time-start_time))
+    echo "Mega service start duration is $duration s" && sleep 1s
+
+    validate_microservices
+    validate_megaservice
+    validate_frontend
+
+    stop_docker
+    echo y | docker system prune
+
+}
+
+main