up

.github/workflows/integration-test-workflow-debian.yml

@@ -1,14 +1,9 @@
-name: R2R CLI Integration (ubuntu latest)
+name: R2R CLI Integration and Regression Test
 
 on:
-  pull_request:
-    branches:
-      - 'dev*'
-      - 'dev-minor*'
   push:
-    branches:
-      - 'dev*'
-      - 'dev-minor*'
+    branches: ['**']
+  workflow_dispatch:
 
 jobs:
   build-and-test:
@@ -20,24 +15,37 @@ jobs:
     env:
       OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
       TELEMETRY_ENABLED: false
-      POSTGRES_HOST: localhost
-      POSTGRES_DBNAME: postgres
-      POSTGRES_PORT: 5432
-      POSTGRES_PASSWORD: postgres
-      POSTGRES_USER: postgres
+      POSTGRES_USER: ${{ secrets.POSTGRES_USER }}
+      POSTGRES_PASSWORD: ${{ secrets.POSTGRES_PASSWORD }}
+      POSTGRES_DBNAME: ${{ secrets.POSTGRES_DBNAME }}
+      POSTGRES_HOST: ${{ secrets.POSTGRES_HOST }}
+      POSTGRES_PORT: ${{ secrets.POSTGRES_PORT }}
+      R2R_PROJECT_NAME: ${{ secrets.R2R_PROJECT_NAME }}
 
     steps:
-      - name: Install and configure PostgreSQL
-        run: |
-          sudo apt-get update
-          sudo apt-get install -y postgresql
-          sudo systemctl start postgresql.service
-          sudo -u postgres psql -c "ALTER USER postgres PASSWORD 'postgres';"
+    - uses: actions/checkout@v4
+    - uses: actions/setup-python@v4
+      with:
+        python-version: '3.x'
 
-      # Add your other steps here
+    - name: Install Poetry and dependencies
+      run: |
+        curl -sSL https://install.python-poetry.org | python3 -
+        cd py && poetry install -E core -E ingestion-bundle
 
-      - name: Cleanup PostgreSQL
-        if: always()  # Run this step even if the job fails
-        run: |
-          sudo systemctl stop postgresql.service
-          sudo rm -rf /var/lib/postgresql/          
+    - name: Start R2R server
+      working-directory: ./py
+      run: |
+        poetry run r2r serve &
+        echo "Waiting for services to start..."
+        sleep 30
+
+    - name: Run integration tests
+      working-directory: ./py
+      run: |
+        python tests/integration/r2r_integration_tests.py test_ingest_sample_files_cli
+        python tests/integration/r2r_integration_tests.py test_document_ingestion_cli
+
+    - name: Stop R2R server
+      if: always()
+      run: pkill -f "r2r serve"

py/tests/integration/runner.py

@@ -0,0 +1,78 @@
+# File: tests/integration/r2r_integration_tests.py
+
+import json
+import subprocess
+import sys
+
+
+def run_command(command):
+    result = subprocess.run(
+        command, shell=True, capture_output=True, text=True
+    )
+    if result.returncode != 0:
+        print(f"Command failed: {command}")
+        print(f"Error: {result.stderr}")
+        sys.exit(1)
+    return result.stdout
+
+
+def test_ingest_sample_files_cli():
+    print("Testing: Ingest sample files")
+    run_command("poetry run r2r ingest-sample-files")
+    print("Ingestion successful")
+
+
+def test_document_ingestion_cli():
+    print("Testing: Document ingestion")
+    output = run_command("poetry run r2r documents-overview")
+    documents = json.loads(output)
+
+    expected_document = {
+        "id": "9fbe403b-c11c-5aae-8ade-ef22980c3ad1",
+        "title": "aristotle.txt",
+        "type": "txt",
+        "ingestion_status": "success",
+        "kg_extraction_status": "success",
+        "version": "v0",
+        "metadata": {"title": "aristotle.txt", "version": "v0"},
+    }
+
+    if not any(
+        all(doc.get(k) == v for k, v in expected_document.items())
+        for doc in documents
+    ):
+        print("Document ingestion test failed")
+        print(f"Expected document not found in output: {output}")
+        sys.exit(1)
+    print("Document ingestion test passed")
+
+
+def test_vector_search_cli():
+    print("Testing: Vector search")
+    output = run_command(
+        "poetry run r2r search --query='What was Uber's profit in 2020?'"
+    )
+    results = json.loads(output)
+    if not results.get("results"):
+        print("Vector search test failed: No results returned")
+        sys.exit(1)
+    print("Vector search test passed")
+
+
+def test_rag_query_cli():
+    print("Testing: RAG query")
+    output = run_command("poetry run r2r rag --query='Who was Aristotle?'")
+    response = json.loads(output)
+    if not response.get("answer"):
+        print("RAG query test failed: No answer returned")
+        sys.exit(1)
+    print("RAG query test passed")
+
+
+if __name__ == "__main__":
+    if len(sys.argv) < 2:
+        print("Please specify a test function to run")
+        sys.exit(1)
+
+    test_function = sys.argv[1]
+    globals()[test_function]()