[WIP] [Genesis] Add Python Release Test

.github/workflows/python-ec2-genai-test.yml

@@ -0,0 +1,191 @@
+## Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+## SPDX-License-Identifier: Apache-2.0
+
+name: Python EC2 LangChain Service Deployment
+on:
+  workflow_call:
+    inputs:
+      caller-workflow-name:
+        required: true
+        type: string
+      cpu-architecture:
+        description: "Permitted values: x86_64 or arm64"
+        required: false
+        type: string
+        default: "x86_64"
+      staging-wheel-name:
+        required: false
+        default: 'aws-opentelemetry-distro'
+        type: string
+
+permissions:
+  id-token: write
+  contents: read
+
+env:
+  E2E_TEST_AWS_REGION: 'us-west-2'
+  # E2E_TEST_ACCOUNT_ID: ${{ secrets.APPLICATION_SIGNALS_E2E_TEST_ACCOUNT_ID }}
+  # E2E_TEST_ROLE_NAME: ${{ secrets.APPLICATION_SIGNALS_E2E_TEST_ROLE_NAME }}
+  E2E_TEST_ACCOUNT_ID: 571600841604
+  ADOT_WHEEL_NAME: ${{ inputs.staging-wheel-name }}
+  E2E_TEST_ROLE_NAME: github
+  METRIC_NAMESPACE: genesis
+  LOG_GROUP_NAME: test/genesis
+  TEST_RESOURCES_FOLDER: ${GITHUB_WORKSPACE}
+  SAMPLE_APP_ZIP: s3://sigv4perfresults/langchain-service.zip
+
+jobs:
+  python-ec2-adot-genai:
+    runs-on: ubuntu-latest
+    timeout-minutes: 30
+    steps:
+      - uses: actions/checkout@v4
+
+      # - name: Set Get ADOT Wheel command environment variable
+      #   run: |
+      #     if [ "${{ github.event.repository.name }}" = "aws-otel-python-instrumentation" ]; then
+      #       # Reusing the adot-main-build-staging-jar bucket to store the python wheel file
+      #       echo GET_ADOT_WHEEL_COMMAND="aws s3 cp s3://adot-main-build-staging-jar/${{ env.ADOT_WHEEL_NAME }} ./${{ env.ADOT_WHEEL_NAME }} && sudo python${{ env.PYTHON_VERSION }} -m pip install ${{ env.ADOT_WHEEL_NAME }}" >> $GITHUB_ENV
+      #     elif [ "${{ env.OTEL_SOURCE }}" == "pypi" ]; then
+      #       echo GET_ADOT_WHEEL_COMMAND="sudo python${{ env.PYTHON_VERSION }} -m pip install ${{ env.ADOT_WHEEL_NAME }}" >> $GITHUB_ENV
+      #     else
+      #       latest_release_version=$(curl -sL https://github.com/aws-observability/aws-otel-python-instrumentation/releases/latest | grep -oP '/releases/tag/v\K[0-9]+\.[0-9]+\.[0-9]+' | head -n 1)
+      #       echo "The latest version is $latest_release_version"
+      #       echo GET_ADOT_WHEEL_COMMAND="wget -O ${{ env.ADOT_WHEEL_NAME }} https://github.com/aws-observability/aws-otel-python-instrumentation/releases/latest/download/aws_opentelemetry_distro-$latest_release_version-py3-none-any.whl \
+      #       && sudo python${{ env.PYTHON_VERSION }} -m pip install ${{ env.ADOT_WHEEL_NAME }}" >> $GITHUB_ENV
+      #     fi
+
+      - name: Initiate Gradlew Daemon
+        uses: ./.github/workflows/actions/execute_and_retry
+        continue-on-error: true
+        with:
+          command: "./gradlew :validator:build"
+          cleanup: "./gradlew clean"
+          max_retry: 3
+          sleep_time: 60
+
+      - name: Generate testing id
+        run: echo TESTING_ID="${{ github.run_id }}-${{ github.run_number }}-${RANDOM}" >> $GITHUB_ENV
+
+      - name: Generate XRay and W3C trace ID
+        run: |
+          ID_1="$(printf '%08x' $(date +%s))"
+          ID_2="$(openssl rand -hex 12)"
+          W3C_TRACE_ID="${ID_1}${ID_2}"
+          XRAY_TRACE_ID="1-${ID_1}-${ID_2}"
+          echo "XRAY_TRACE_ID=${XRAY_TRACE_ID}" >> $GITHUB_ENV
+          echo "W3C_TRACE_ID=${W3C_TRACE_ID}" >> $GITHUB_ENV
+          echo "Generated XRay Trace ID: ${XRAY_TRACE_ID}"
+          echo "Generated W3C Trace ID: ${W3C_TRACE_ID}"
+
+      - name: Configure AWS Credentials
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          role-to-assume: arn:aws:iam::${{ env.E2E_TEST_ACCOUNT_ID }}:role/${{ env.E2E_TEST_ROLE_NAME }}
+          aws-region: ${{ env.E2E_TEST_AWS_REGION }}
+
+      - name: Set up terraform
+        uses: ./.github/workflows/actions/execute_and_retry
+        with:
+          command: "wget -O- https://apt.releases.hashicorp.com/gpg | sudo gpg --dearmor -o /usr/share/keyrings/hashicorp-archive-keyring.gpg"
+          post-command: 'echo "deb [signed-by=/usr/share/keyrings/hashicorp-archive-keyring.gpg] https://apt.releases.hashicorp.com $(lsb_release -cs) main" | sudo tee /etc/apt/sources.list.d/hashicorp.list
+              && sudo apt update && sudo apt install terraform'
+
+      - name: Initiate Terraform
+        uses: ./.github/workflows/actions/execute_and_retry
+        with:
+          command: "cd ${{ env.TEST_RESOURCES_FOLDER }}/terraform/python/ec2/adot-genai && terraform init && terraform validate"
+          cleanup: "rm -rf .terraform && rm -rf .terraform.lock.hcl"
+          max_retry: 6
+
+      - name: Deploy service via terraform
+        working-directory: terraform/python/ec2/adot-genai
+        run: |
+          terraform apply -auto-approve \
+            -var="aws_region=${{ env.E2E_TEST_AWS_REGION }}" \
+            -var="test_id=${{ env.TESTING_ID }}" \
+            -var="service_zip_url=${{ env.SAMPLE_APP_ZIP }}"
+
+      - name: Get deployment info
+        working-directory: terraform/python/ec2/adot-genai
+        run: |
+          echo "INSTANCE_IP=$(terraform output langchain_service_public_ip)" >> $GITHUB_ENV
+          echo "INSTANCE_ID=$(terraform output langchain_service_instance_id)" >> $GITHUB_ENV
+
+      - name: Wait for Gen AI Chatbot service to be ready
+        run: |
+          echo "Waiting for service to be ready at http://${{ env.INSTANCE_IP }}:8000"
+          for i in {1..60}; do
+            if curl -f -s "http://${{ env.INSTANCE_IP }}:8000/health" > /dev/null 2>&1; then
+              echo "Service is ready!"
+              break
+            fi
+            echo "Attempt $i: Service not ready yet, waiting 10 seconds..."
+            sleep 10
+          done
+
+          # Final check
+          if ! curl -f -s "http://${{ env.INSTANCE_IP }}:8000/health" > /dev/null 2>&1; then
+            echo "Service failed to become ready after 10 minutes"
+            exit 1
+          fi
+
+      - name: Generate traffic
+        run: |
+          cd sample-apps/traffic-generator/genai
+          chmod +x generate_traffic.sh
+          export SERVER_URL="http://${{ env.INSTANCE_IP }}:8000"
+          export NUM_REQUESTS="5"
+          export DELAY_SECONDS="5"
+          export TIMEOUT="30"
+          export TRACE_ID="Root=${XRAY_TRACE_ID};Parent=$(openssl rand -hex 8);Sampled=1"
+          ./generate_traffic.sh
+
+      - name: Validate generated logs
+        run: ./gradlew validator:run --args='-c python/ec2/adot-genai/log-validation.yml
+          --testing-id ${{ env.TESTING_ID }}
+          --endpoint http://${{ env.INSTANCE_IP }}:8000
+          --region ${{ env.E2E_TEST_AWS_REGION }}
+          --metric-namespace ${{ env.METRIC_NAMESPACE }}
+          --log-group ${{ env.LOG_GROUP_NAME }}
+          --service-name langchain-traceloop-app
+          --instance-id ${{ env.INSTANCE_ID }}
+          --trace-id ${{ env.W3C_TRACE_ID }}'
+
+      - name: Validate generated traces
+        if: (success() || failure()) && !cancelled()
+        run: ./gradlew validator:run --args='-c python/ec2/adot-genai/trace-validation.yml
+          --testing-id ${{ env.TESTING_ID }}
+          --endpoint http://${{ env.INSTANCE_IP }}:8000
+          --region ${{ env.E2E_TEST_AWS_REGION }}
+          --metric-namespace ${{ env.METRIC_NAMESPACE }}
+          --service-name langchain-traceloop-app
+          --instance-id ${{ env.INSTANCE_ID }}
+          --trace-id ${{ env.XRAY_TRACE_ID }}'
+
+      - name: Wait for metrics to be published
+        if: (success() || failure()) && !cancelled()
+        run: |
+          echo "Waiting 60 seconds to ensure EMF metrics are published to CloudWatch"
+          sleep 60
+
+      - name: Validate generated metrics
+        if: (success() || failure()) && !cancelled()
+        run: ./gradlew validator:run --args='-c python/ec2/adot-genai/metric-validation.yml
+          --testing-id ${{ env.TESTING_ID }}
+          --endpoint http://${{ env.INSTANCE_IP }}:8000
+          --region ${{ env.E2E_TEST_AWS_REGION }}
+          --metric-namespace ${{ env.METRIC_NAMESPACE }}
+          --log-group ${{ env.LOG_GROUP_NAME }}
+          --service-name langchain-traceloop-app
+          --instance-id ${{ env.INSTANCE_ID }}'
+
+      - name: Cleanup
+        if: always()
+        continue-on-error: true
+        working-directory: terraform/python/ec2/adot-genai
+        run: |
+          terraform destroy -auto-approve \
+            -var="aws_region=${{ env.E2E_TEST_AWS_REGION }}" \
+            -var="test_id=${{ env.TESTING_ID }}" \
+            -var="service_zip_url=${{ env.SAMPLE_APP_ZIP }}"

sample-apps/python/genai_service/ec2-requirements.txt

@@ -0,0 +1,15 @@
+langchain
+langchain-community
+langchain_aws
+opentelemetry-sdk
+openinference-instrumentation-langchain
+opentelemetry-api
+opentelemetry-semantic-conventions
+python-dotenv
+openlit
+botocore
+setuptools
+boto3
+aws_opentelemetry_distro_genai_beta
+fastapi
+uvicorn[standard]

sample-apps/python/genai_service/server.py

@@ -0,0 +1,114 @@
+import os
+from typing import Dict, List
+from dotenv import load_dotenv
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+from langchain_aws import ChatBedrock
+from langchain.prompts import ChatPromptTemplate
+from langchain.chains import LLMChain
+from opentelemetry import trace
+from opentelemetry.sdk.trace import TracerProvider
+from opentelemetry.sdk.trace.export import BatchSpanProcessor, ConsoleSpanExporter
+from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
+from openinference.instrumentation.langchain import LangChainInstrumentor
+
+# Load environment variables
+load_dotenv()
+
+# Set up OpenTelemetry with BOTH exporters
+tracer_provider = TracerProvider()
+
+# Add Console exporter
+console_exporter = ConsoleSpanExporter()
+console_processor = BatchSpanProcessor(console_exporter)
+tracer_provider.add_span_processor(console_processor)
+
+# Add OTLP exporter
+otlp_exporter = OTLPSpanExporter(endpoint="http://localhost:4318/v1/traces")
+otlp_processor = BatchSpanProcessor(otlp_exporter)
+tracer_provider.add_span_processor(otlp_processor)
+
+# Set as global provider
+trace.set_tracer_provider(tracer_provider)
+
+# Instrument LangChain with OpenInference
+LangChainInstrumentor().instrument(tracer_provider=tracer_provider)
+
+# Initialize FastAPI app
+app = FastAPI(title="LangChain Bedrock OpenInference API", version="1.0.0")
+
+# Initialize the LLM with AWS Bedrock
+llm = ChatBedrock(
+    model_id="anthropic.claude-3-haiku-20240307-v1:0",
+    model_kwargs={
+        "temperature": 0.7,
+        "max_tokens": 500
+    },
+    region_name=os.getenv("AWS_DEFAULT_REGION", "us-west-2")
+)
+
+# Create a prompt template
+prompt = ChatPromptTemplate.from_template(
+    "You are a helpful assistant. The user says: {input}. Provide a helpful response."
+)
+
+# Create a chain
+chain = LLMChain(llm=llm, prompt=prompt)
+
+# Request models
+class ChatRequest(BaseModel):
+    message: str
+
+class BatchChatRequest(BaseModel):
+    messages: List[str]
+
+class ChatResponse(BaseModel):
+    response: str
+
+class BatchChatResponse(BaseModel):
+    responses: List[Dict[str, str]]
+
+# Sample prompts for testing
+SAMPLE_PROMPTS = [
+    "What is the capital of France?",
+    "How do I make a cup of coffee?",
+    "What are the benefits of exercise?",
+    "Explain quantum computing in simple terms",
+    "What's the best way to learn programming?"
+]
+
+@app.get("/")
+async def root():
+    return {
+        "message": "LangChain Bedrock OpenInference API is running!",
+        "endpoints": {
+            "/ai-chat": "Single message chat endpoint",
+            "/hello": "Simple hello endpoint"
+        }
+    }
+
+@app.post("/ai-chat", response_model=ChatResponse)
+async def chat(request: ChatRequest):
+    """
+    Chat endpoint that processes a single user message through AWS Bedrock
+    """
+    try:
+        # Process the input through the chain
+        result = await chain.ainvoke({"input": request.message})
+        return ChatResponse(response=result["text"])
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+@app.get("/health")
+async def health():
+    """Health check endpoint"""
+    return {"status": "healthy", "llm": "AWS Bedrock Claude 3 Haiku"}
+
+if __name__ == "__main__":
+    import uvicorn
+    print("Starting FastAPI server with AWS Bedrock and OpenInference instrumentation...")
+    print("Make sure AWS credentials are configured")
+    print("Server will run on http://localhost:8000")
+    print("API docs available at http://localhost:8000/docs")
+
+    uvicorn.run(app, host="0.0.0.0", port=8000)