Add it on merge queue (#2112)

* Github action to run integration tests * Improve * Fix build * Add pull * Fix readiness script * Add IT runner * Add IT runner * Add logs * update * Fix * Fix path * file path * test * fix * fix * fix * test * network * fix * cleanup * fix * test * Fix downgrade * Add OpenAI API key * Add VESPA_HOST * test pulling first * Add API server host * Cache tweak * Fix pull/push settings: * Stop pushing to latest tag * test cache change * test * test * test * remove cache temporarily * Fix * Enable EE * test * Remove duplicate funcs * add back build * Update all * Fix stop cmd * Add to merge queue * Cleanup image tag
2025-09-20 13:05:49 +02:00 · 2024-08-26 00:20:28 -07:00
parent 205c3c3fc8
commit c0e1a02e8e
11 changed files with 300 additions and 58 deletions
--- a/.github/workflows/run-it.yml
+++ b/.github/workflows/run-it.yml
@@ -0,0 +1,172 @@
+name: Run Integration Tests
+concurrency:
+  group: Run-Integration-Tests-${{ github.head_ref }}
+  cancel-in-progress: true
+
+on:
+  merge_group:
+  pull_request:
+    branches: [ main ]
+
+env:
+  OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+
+jobs:
+  integration-tests:
+    runs-on: 
+      group: 'arm64-image-builders'
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
+
+      - name: Build Web Docker image
+        uses: docker/build-push-action@v5
+        with:
+          context: ./web
+          file: ./web/Dockerfile
+          platforms: linux/arm64
+          pull: true
+          push: true
+          load: true
+          tags: danswer/danswer-web-server:it
+          cache-from: type=registry,ref=danswer/danswer-web-server:it
+          cache-to: |
+            type=registry,ref=danswer/danswer-web-server:it,mode=max
+            type=inline
+
+      - name: Build Backend Docker image
+        uses: docker/build-push-action@v5
+        with:
+          context: ./backend
+          file: ./backend/Dockerfile
+          platforms: linux/arm64
+          pull: true
+          push: true
+          load: true
+          tags: danswer/danswer-backend:it
+          cache-from: type=registry,ref=danswer/danswer-backend:it
+          cache-to: |
+            type=registry,ref=danswer/danswer-backend:it,mode=max
+            type=inline
+
+      - name: Build Model Server Docker image
+        uses: docker/build-push-action@v5
+        with:
+          context: ./backend
+          file: ./backend/Dockerfile.model_server
+          platforms: linux/arm64
+          pull: true
+          push: true
+          load: true
+          tags: danswer/danswer-model-server:it
+          cache-from: type=registry,ref=danswer/danswer-model-server:it
+          cache-to: |
+            type=registry,ref=danswer/danswer-model-server:it,mode=max
+            type=inline
+
+      - name: Build integration test Docker image
+        uses: docker/build-push-action@v5
+        with:
+          context: ./backend
+          file: ./backend/tests/integration/Dockerfile
+          platforms: linux/arm64
+          pull: true
+          push: true
+          load: true
+          tags: danswer/integration-test-runner:it
+          cache-from: type=registry,ref=danswer/integration-test-runner:it
+          cache-to: |
+            type=registry,ref=danswer/integration-test-runner:it,mode=max
+            type=inline
+
+      - name: Start Docker containers
+        run: |
+          cd deployment/docker_compose
+          ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
+          IMAGE_TAG=it \
+          docker compose -f docker-compose.dev.yml -p danswer-stack up -d --build
+        id: start_docker
+
+      - name: Wait for service to be ready
+        run: |
+          echo "Starting wait-for-service script..."
+          
+          start_time=$(date +%s)
+          timeout=300  # 5 minutes in seconds
+          
+          while true; do
+            current_time=$(date +%s)
+            elapsed_time=$((current_time - start_time))
+            
+            if [ $elapsed_time -ge $timeout ]; then
+              echo "Timeout reached. Service did not become ready in 5 minutes."
+              exit 1
+            fi
+            
+            # Use curl with error handling to ignore specific exit code 56
+            response=$(curl -s -o /dev/null -w "%{http_code}" http://localhost:8080/health || echo "curl_error")
+            
+            if [ "$response" = "200" ]; then
+              echo "Service is ready!"
+              break
+            elif [ "$response" = "curl_error" ]; then
+              echo "Curl encountered an error, possibly exit code 56. Continuing to retry..."
+            else
+              echo "Service not ready yet (HTTP status $response). Retrying in 5 seconds..."
+            fi
+            
+            sleep 5
+          done
+          echo "Finished waiting for service."
+
+      - name: Run integration tests
+        run: |
+          echo "Running integration tests..."
+          docker run --rm --network danswer-stack_default \
+            -e POSTGRES_HOST=relational_db \
+            -e POSTGRES_USER=postgres \
+            -e POSTGRES_PASSWORD=password \
+            -e POSTGRES_DB=postgres \
+            -e VESPA_HOST=index \
+            -e API_SERVER_HOST=api_server \
+            -e OPENAI_API_KEY=${OPENAI_API_KEY} \
+            danswer/integration-test-runner:it
+        continue-on-error: true
+        id: run_tests
+
+      - name: Check test results
+        run: |
+          if [ ${{ steps.run_tests.outcome }} == 'failure' ]; then
+            echo "Integration tests failed. Exiting with error."
+            exit 1
+          else
+            echo "All integration tests passed successfully."
+          fi
+
+      - name: Save Docker logs
+        if: success() || failure()
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.dev.yml -p danswer-stack logs > docker-compose.log
+          mv docker-compose.log ${{ github.workspace }}/docker-compose.log
+      
+      - name: Upload logs
+        if: success() || failure()
+        uses: actions/upload-artifact@v3
+        with:
+          name: docker-logs
+          path: ${{ github.workspace }}/docker-compose.log
+
+      - name: Stop Docker containers
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.dev.yml -p danswer-stack down -v
--- a/backend/alembic/versions/f17bf3b0d9f1_embedding_provider_by_provider_type.py
+++ b/backend/alembic/versions/f17bf3b0d9f1_embedding_provider_by_provider_type.py
@@ -161,3 +161,12 @@ def downgrade() -> None:
        ["cloud_provider_id"],
        ["id"],
    )
+
+    # Recreate the foreign key constraint in embedding_model table
+    op.create_foreign_key(
+        "fk_embedding_provider_default_model",
+        "embedding_provider",
+        "embedding_model",
+        ["default_model_id"],
+        ["id"],
+    )
--- a/backend/tests/integration/Dockerfile
+++ b/backend/tests/integration/Dockerfile
@@ -0,0 +1,83 @@
+FROM python:3.11.7-slim-bookworm
+# Dockerfile for integration tests
+# Currently needs all dependencies, since the ITs use some of the Danswer
+# backend code.
+
+# Install system dependencies
+# cmake needed for psycopg (postgres)
+# libpq-dev needed for psycopg (postgres)
+# curl included just for users' convenience
+# zip for Vespa step futher down
+# ca-certificates for HTTPS
+RUN apt-get update && \
+    apt-get install -y \
+        cmake \
+        curl \
+        zip \
+        ca-certificates \
+        libgnutls30=3.7.9-2+deb12u3 \
+        libblkid1=2.38.1-5+deb12u1 \
+        libmount1=2.38.1-5+deb12u1 \
+        libsmartcols1=2.38.1-5+deb12u1 \
+        libuuid1=2.38.1-5+deb12u1 \
+        libxmlsec1-dev \
+        pkg-config \
+        gcc && \
+    rm -rf /var/lib/apt/lists/* && \
+    apt-get clean
+
+# Install Python dependencies
+# Remove py which is pulled in by retry, py is not needed and is a CVE
+COPY ./requirements/default.txt /tmp/requirements.txt
+COPY ./requirements/ee.txt /tmp/ee-requirements.txt
+RUN pip install --no-cache-dir --upgrade \
+        -r /tmp/requirements.txt \
+        -r /tmp/ee-requirements.txt && \
+    pip uninstall -y py && \
+    playwright install chromium && \
+    playwright install-deps chromium && \
+    ln -s /usr/local/bin/supervisord /usr/bin/supervisord
+
+# Cleanup for CVEs and size reduction
+# https://github.com/tornadoweb/tornado/issues/3107
+# xserver-common and xvfb included by playwright installation but not needed after
+# perl-base is part of the base Python Debian image but not needed for Danswer functionality
+# perl-base could only be removed with --allow-remove-essential
+RUN apt-get update && \
+    apt-get remove -y --allow-remove-essential \
+        perl-base \
+        xserver-common \
+        xvfb \
+        cmake \
+        libldap-2.5-0 \
+        libxmlsec1-dev \
+        pkg-config \
+        gcc && \
+    apt-get install -y libxmlsec1-openssl && \
+    apt-get autoremove -y && \
+    rm -rf /var/lib/apt/lists/* && \
+    rm -f /usr/local/lib/python3.11/site-packages/tornado/test/test.key
+
+# Set up application files
+WORKDIR /app
+
+# Enterprise Version Files
+COPY ./ee /app/ee
+COPY supervisord.conf /etc/supervisor/conf.d/supervisord.conf
+
+# Set up application files
+COPY ./danswer /app/danswer
+COPY ./shared_configs /app/shared_configs
+COPY ./alembic /app/alembic
+COPY ./alembic.ini /app/alembic.ini
+COPY supervisord.conf /usr/etc/supervisord.conf
+
+# Integration test stuff
+COPY ./requirements/dev.txt /tmp/dev-requirements.txt
+RUN pip install --no-cache-dir --upgrade \
+        -r /tmp/dev-requirements.txt
+COPY ./tests/integration /app/tests/integration
+
+ENV PYTHONPATH /app
+
+CMD ["pytest", "-s", "/app/tests/integration"]
--- a/backend/tests/integration/common_utils/constants.py
+++ b/backend/tests/integration/common_utils/constants.py
@@ -1,2 +1,7 @@
-API_SERVER_URL = "http://localhost:8080"
+import os
+
+API_SERVER_PROTOCOL = os.getenv("API_SERVER_PROTOCOL") or "http"
+API_SERVER_HOST = os.getenv("API_SERVER_HOST") or "localhost"
+API_SERVER_PORT = os.getenv("API_SERVER_PORT") or "8080"
+API_SERVER_URL = f"{API_SERVER_PROTOCOL}://{API_SERVER_HOST}:{API_SERVER_PORT}"
 MAX_DELAY = 30
--- a/backend/tests/integration/tests/document_set/test_syncing.py
+++ b/backend/tests/integration/tests/document_set/test_syncing.py
@@ -1,10 +1,9 @@
 import time

 from danswer.server.features.document_set.models import DocumentSetCreationRequest
+from tests.integration.common_utils.document_sets import DocumentSetClient
 from tests.integration.common_utils.seed_documents import TestDocumentClient
 from tests.integration.common_utils.vespa import TestVespaClient
-from tests.integration.tests.document_set.utils import create_document_set
-from tests.integration.tests.document_set.utils import fetch_document_sets


 def test_multiple_document_sets_syncing_same_connnector(
@@ -15,7 +14,7 @@ def test_multiple_document_sets_syncing_same_connnector(
    cc_pair_id = seed_result.cc_pair_id

    # Create first document set
-    doc_set_1_id = create_document_set(
+    doc_set_1_id = DocumentSetClient.create_document_set(
        DocumentSetCreationRequest(
            name="Test Document Set 1",
            description="First test document set",
@@ -26,7 +25,7 @@ def test_multiple_document_sets_syncing_same_connnector(
        )
    )

-    doc_set_2_id = create_document_set(
+    doc_set_2_id = DocumentSetClient.create_document_set(
        DocumentSetCreationRequest(
            name="Test Document Set 2",
            description="Second test document set",
@@ -41,7 +40,7 @@ def test_multiple_document_sets_syncing_same_connnector(
    max_delay = 45
    start = time.time()
    while True:
-        doc_sets = fetch_document_sets()
+        doc_sets = DocumentSetClient.fetch_document_sets()
        doc_set_1 = next(
            (doc_set for doc_set in doc_sets if doc_set.id == doc_set_1_id), None
        )
@@ -64,7 +63,7 @@ def test_multiple_document_sets_syncing_same_connnector(
        time.sleep(2)

    # get names so we can compare to what is in vespa
-    doc_sets = fetch_document_sets()
+    doc_sets = DocumentSetClient.fetch_document_sets()
    doc_set_names = {doc_set.name for doc_set in doc_sets}

    # make sure documents are as expected
--- a/backend/tests/integration/tests/document_set/utils.py
+++ b/backend/tests/integration/tests/document_set/utils.py
@@ -1,26 +0,0 @@
-from typing import cast
-
-import requests
-
-from danswer.server.features.document_set.models import DocumentSet
-from danswer.server.features.document_set.models import DocumentSetCreationRequest
-from tests.integration.common_utils.constants import API_SERVER_URL
-
-
-def create_document_set(doc_set_creation_request: DocumentSetCreationRequest) -> int:
-    response = requests.post(
-        f"{API_SERVER_URL}/manage/admin/document-set",
-        json=doc_set_creation_request.dict(),
-    )
-    response.raise_for_status()
-    return cast(int, response.json())
-
-
-def fetch_document_sets() -> list[DocumentSet]:
-    response = requests.get(f"{API_SERVER_URL}/manage/admin/document-set")
-    response.raise_for_status()
-
-    document_sets = [
-        DocumentSet.parse_obj(doc_set_data) for doc_set_data in response.json()
-    ]
-    return document_sets
--- a/deployment/docker_compose/docker-compose.dev.yml
+++ b/deployment/docker_compose/docker-compose.dev.yml
@@ -1,7 +1,7 @@
 version: '3'
 services:
  api_server:
-    image: danswer/danswer-backend:latest
+    image: danswer/danswer-backend:${IMAGE_TAG:-latest}
    build:
      context: ../../backend
      dockerfile: Dockerfile
@@ -106,7 +106,7 @@ services:
        max-file: "6"

  background:
-    image: danswer/danswer-backend:latest
+    image: danswer/danswer-backend:${IMAGE_TAG:-latest}
    build:
      context: ../../backend
      dockerfile: Dockerfile
@@ -207,7 +207,7 @@ services:
        max-file: "6"

  web_server:
-    image: danswer/danswer-web-server:latest
+    image: danswer/danswer-web-server:${IMAGE_TAG:-latest}
    build:
      context: ../../web
      dockerfile: Dockerfile
@@ -236,7 +236,7 @@ services:
      - ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=${ENABLE_PAID_ENTERPRISE_EDITION_FEATURES:-false}

  inference_model_server:
-    image: danswer/danswer-model-server:latest
+    image: danswer/danswer-model-server:${IMAGE_TAG:-latest}
    build:
      context: ../../backend
      dockerfile: Dockerfile.model_server
@@ -262,7 +262,7 @@ services:
        max-file: "6"

  indexing_model_server:
-    image: danswer/danswer-model-server:latest
+    image: danswer/danswer-model-server:${IMAGE_TAG:-latest}
    build:
      context: ../../backend
      dockerfile: Dockerfile.model_server
--- a/deployment/docker_compose/docker-compose.gpu-dev.yml
+++ b/deployment/docker_compose/docker-compose.gpu-dev.yml
@@ -1,7 +1,7 @@
 version: '3'
 services:
  api_server:
-    image: danswer/danswer-backend:latest
+    image: danswer/danswer-backend:${IMAGE_TAG:-latest}
    build:
      context: ../../backend
      dockerfile: Dockerfile
@@ -98,7 +98,7 @@ services:


  background:
-    image: danswer/danswer-backend:latest
+    image: danswer/danswer-backend:${IMAGE_TAG:-latest}
    build:
      context: ../../backend
      dockerfile: Dockerfile
@@ -201,7 +201,7 @@ services:


  web_server:
-    image: danswer/danswer-web-server:latest
+    image: danswer/danswer-web-server:${IMAGE_TAG:-latest}
    build:
      context: ../../web
      dockerfile: Dockerfile
@@ -226,7 +226,7 @@ services:


  inference_model_server:
-    image: danswer/danswer-model-server:latest
+    image: danswer/danswer-model-server:${IMAGE_TAG:-latest}
    # for GPU support, please read installation guidelines in the README.md
    # bare minimum to get this working is to install nvidia-container-toolkit
    deploy:
@@ -262,7 +262,7 @@ services:


  indexing_model_server:
-    image: danswer/danswer-model-server:latest
+    image: danswer/danswer-model-server:${IMAGE_TAG:-latest}
    build:
      context: ../../backend
      dockerfile: Dockerfile.model_server
--- a/deployment/docker_compose/docker-compose.prod-no-letsencrypt.yml
+++ b/deployment/docker_compose/docker-compose.prod-no-letsencrypt.yml
@@ -1,7 +1,7 @@
 version: '3'
 services:
  api_server:
-    image: danswer/danswer-backend:latest
+    image: danswer/danswer-backend:${IMAGE_TAG:-latest}
    build:
      context: ../../backend
      dockerfile: Dockerfile
@@ -31,7 +31,7 @@ services:


  background:
-    image: danswer/danswer-backend:latest
+    image: danswer/danswer-backend:${IMAGE_TAG:-latest}
    build:
      context: ../../backend
      dockerfile: Dockerfile
@@ -60,7 +60,7 @@ services:


  web_server:
-    image: danswer/danswer-web-server:latest
+    image: danswer/danswer-web-server:${IMAGE_TAG:-latest}
    build:
      context: ../../web
      dockerfile: Dockerfile
@@ -87,7 +87,7 @@ services:


  inference_model_server:
-    image: danswer/danswer-model-server:latest
+    image: danswer/danswer-model-server:${IMAGE_TAG:-latest}
    build:
      context: ../../backend
      dockerfile: Dockerfile.model_server
@@ -114,7 +114,7 @@ services:


  indexing_model_server:
-    image: danswer/danswer-model-server:latest
+    image: danswer/danswer-model-server:${IMAGE_TAG:-latest}
    build:
      context: ../../backend
      dockerfile: Dockerfile.model_server
--- a/deployment/docker_compose/docker-compose.prod.yml
+++ b/deployment/docker_compose/docker-compose.prod.yml
@@ -1,7 +1,7 @@
 version: '3'
 services:
  api_server:
-    image: danswer/danswer-backend:latest
+    image: danswer/danswer-backend:${IMAGE_TAG:-latest}
    build:
      context: ../../backend
      dockerfile: Dockerfile
@@ -31,7 +31,7 @@ services:


  background:
-    image: danswer/danswer-backend:latest
+    image: danswer/danswer-backend:${IMAGE_TAG:-latest}
    build:
      context: ../../backend
      dockerfile: Dockerfile
@@ -59,7 +59,7 @@ services:
        max-file: "6"

  web_server:
-    image: danswer/danswer-web-server:latest
+    image: danswer/danswer-web-server:${IMAGE_TAG:-latest}
    build:
      context: ../../web
      dockerfile: Dockerfile
@@ -101,7 +101,7 @@ services:


  inference_model_server:
-    image: danswer/danswer-model-server:latest
+    image: danswer/danswer-model-server:${IMAGE_TAG:-latest}
    build:
      context: ../../backend
      dockerfile: Dockerfile.model_server
@@ -128,7 +128,7 @@ services:


  indexing_model_server:
-    image: danswer/danswer-model-server:latest
+    image: danswer/danswer-model-server:${IMAGE_TAG:-latest}
    build:
      context: ../../backend
      dockerfile: Dockerfile.model_server
--- a/deployment/docker_compose/docker-compose.search-testing.yml
+++ b/deployment/docker_compose/docker-compose.search-testing.yml
@@ -1,7 +1,7 @@
 version: '3'
 services:
  api_server:
-    image: danswer/danswer-backend:latest
+    image: danswer/danswer-backend:${IMAGE_TAG:-latest}
    build:
      context: ../../backend
      dockerfile: Dockerfile
@@ -35,7 +35,7 @@ services:


  background:
-    image: danswer/danswer-backend:latest
+    image: danswer/danswer-backend:${IMAGE_TAG:-latest}
    build:
      context: ../../backend
      dockerfile: Dockerfile
@@ -65,7 +65,7 @@ services:


  web_server:
-    image: danswer/danswer-web-server:latest
+    image: danswer/danswer-web-server:${IMAGE_TAG:-latest}
    build:
      context: ../../web
      dockerfile: Dockerfile
@@ -94,7 +94,7 @@ services:


  inference_model_server:
-    image: danswer/danswer-model-server:latest
+    image: danswer/danswer-model-server:${IMAGE_TAG:-latest}
    build:
      context: ../../backend
      dockerfile: Dockerfile.model_server
@@ -118,7 +118,7 @@ services:


  indexing_model_server:
-    image: danswer/danswer-model-server:latest
+    image: danswer/danswer-model-server:${IMAGE_TAG:-latest}
    build:
      context: ../../backend
      dockerfile: Dockerfile.model_server