railseek6/test_final_ocr_upload.py

#!/usr/bin/env python3
"""
Final test script to upload ocr.pdf and verify upload, indexing, and search functionality
"""

import requests
import json
import time
import sys

def test_ocr_pdf_workflow():
    """Test complete OCR PDF workflow: upload, indexing, and search"""
    
    base_url = "http://localhost:3015"
    api_key = "jleu1212"
    
    print("=== Testing LightRAG OCR PDF Workflow ===")
    
    # 1. Check server health
    print("\n1. Checking server health...")
    try:
        health_response = requests.get(f"{base_url}/health")
        if health_response.status_code == 200:
            print("   ✅ Server is healthy")
            print(f"   Status: {health_response.json().get('status', 'unknown')}")
        else:
            print(f"   ❌ Server health check failed: {health_response.status_code}")
            return False
    except Exception as e:
        print(f"   ❌ Server health check error: {e}")
        return False
    
    # 2. Upload ocr.pdf
    print("\n2. Uploading ocr.pdf...")
    try:
        with open("ocr.pdf", "rb") as f:
            files = {"file": ("ocr.pdf", f, "application/pdf")}
            headers = {"X-API-Key": api_key}
            upload_response = requests.post(
                f"{base_url}/api/upload", 
                files=files, 
                headers=headers
            )
        
        if upload_response.status_code == 200:
            print("   ✅ File uploaded successfully")
            upload_result = upload_response.json()
            print(f"   Response: {upload_result}")
        else:
            print(f"   ❌ Upload failed: {upload_response.status_code}")
            print(f"   Response: {upload_response.text}")
            return False
    except Exception as e:
        print(f"   ❌ Upload error: {e}")
        return False
    
    # 3. Wait for indexing to complete
    print("\n3. Waiting for indexing to complete...")
    max_wait_time = 120  # 2 minutes
    wait_interval = 5
    elapsed_time = 0
    
    while elapsed_time < max_wait_time:
        try:
            # Check document status
            status_response = requests.get(f"{base_url}/api/documents", headers={"X-API-Key": api_key})
            if status_response.status_code == 200:
                documents = status_response.json()
                if documents:
                    doc_status = documents[0].get("status", "unknown")
                    print(f"   Document status: {doc_status} (elapsed: {elapsed_time}s)")
                    
                    if doc_status == "PROCESSED":
                        print("   ✅ Indexing completed successfully")
                        break
                    elif doc_status == "FAILED":
                        print("   ❌ Indexing failed")
                        return False
                else:
                    print("   No documents found, waiting...")
            else:
                print(f"   Status check failed: {status_response.status_code}")
        except Exception as e:
            print(f"   Status check error: {e}")
        
        time.sleep(wait_interval)
        elapsed_time += wait_interval
    
    if elapsed_time >= max_wait_time:
        print("   ⚠️  Indexing timeout - proceeding with search test")
    
    # 4. Test search functionality
    print("\n4. Testing search functionality...")
    test_queries = [
        "artificial intelligence",
        "machine learning", 
        "neural networks",
        "data science"
    ]
    
    search_success = False
    for query in test_queries:
        try:
            search_payload = {
                "query": query,
                "top_k": 5
            }
            search_response = requests.post(
                f"{base_url}/api/search",
                json=search_payload,
                headers={"X-API-Key": api_key, "Content-Type": "application/json"}
            )
            
            if search_response.status_code == 200:
                search_results = search_response.json()
                if search_results and len(search_results) > 0:
                    print(f"   ✅ Search successful for '{query}': Found {len(search_results)} results")
                    search_success = True
                    # Print first result snippet
                    first_result = search_results[0]
                    content_preview = first_result.get('content', '')[:100] + "..."
                    print(f"   First result preview: {content_preview}")
                    break
                else:
                    print(f"   ⚠️  No results for '{query}'")
            else:
                print(f"   ❌ Search failed for '{query}': {search_response.status_code}")
        except Exception as e:
            print(f"   ❌ Search error for '{query}': {e}")
    
    # 5. Test web UI accessibility
    print("\n5. Testing web UI accessibility...")
    try:
        webui_response = requests.get(f"{base_url}/webui/")
        if webui_response.status_code == 200:
            print("   ✅ Web UI is accessible")
        else:
            print(f"   ⚠️  Web UI returned status: {webui_response.status_code}")
    except Exception as e:
        print(f"   ❌ Web UI access error: {e}")
    
    # Final summary
    print("\n=== Test Summary ===")
    if search_success:
        print("✅ SUCCESS: OCR PDF workflow is working correctly!")
        print("   - File upload: ✓")
        print("   - Indexing: ✓") 
        print("   - Search: ✓")
        print("   - Web UI: ✓")
        return True
    else:
        print("❌ FAILURE: Some tests failed")
        return False

if __name__ == "__main__":
    success = test_ocr_pdf_workflow()
    sys.exit(0 if success else 1)