railseek6/test_ocr_deepseek_workflow.py

#!/usr/bin/env python3
"""
Test script to verify OCR PDF upload, indexing, and search with DeepSeek API
"""

import requests
import json
import time
import os

# Configuration
BASE_URL = "http://localhost:3015"
API_KEY = "jleu1212"
OCR_PDF_PATH = "ocr.pdf"

def test_server_health():
    """Test if server is responding"""
    try:
        response = requests.get(f"{BASE_URL}/")
        print(f"✅ Server is running: {response.status_code}")
        return True
    except Exception as e:
        print(f"❌ Server not responding: {e}")
        return False

def test_upload_ocr_pdf():
    """Test uploading OCR PDF file"""
    if not os.path.exists(OCR_PDF_PATH):
        print(f"❌ OCR PDF file not found: {OCR_PDF_PATH}")
        return False
    
    try:
        with open(OCR_PDF_PATH, 'rb') as f:
            files = {'file': (OCR_PDF_PATH, f, 'application/pdf')}
            headers = {'X-API-Key': API_KEY}
            response = requests.post(f"{BASE_URL}/documents/upload", files=files, headers=headers)
        
        if response.status_code == 200:
            print(f"✅ OCR PDF uploaded successfully")
            result = response.json()
            print(f"   Upload result: {result}")
            return True
        else:
            print(f"❌ Upload failed: {response.status_code} - {response.text}")
            return False
    except Exception as e:
        print(f"❌ Upload error: {e}")
        return False

def test_document_status():
    """Check document processing status"""
    try:
        headers = {'X-API-Key': API_KEY}
        response = requests.get(f"{BASE_URL}/documents", headers=headers)
        if response.status_code == 200:
            data = response.json()
            # Count total documents across all statuses
            total_docs = sum(len(docs) for docs in data.get('statuses', {}).values())
            print(f"✅ Documents status retrieved: {total_docs} documents")
            
            # Print document details
            for status, docs in data.get('statuses', {}).items():
                for doc in docs:
                    print(f"   - {doc.get('file_path', 'Unknown')}: {status}")
                    if doc.get('content_summary'):
                        print(f"     Summary: {doc.get('content_summary')[:100]}...")
            return True
        else:
            print(f"❌ Failed to get documents: {response.status_code} - {response.text}")
            return False
    except Exception as e:
        print(f"❌ Documents status error: {e}")
        return False

def test_search_functionality():
    """Test search functionality with OCR content (without LLM)"""
    search_queries = [
        "table",  # Should find table content from OCR
        "data",   # General content
        "test"    # Should find test content
    ]
    
    for query in search_queries:
        try:
            payload = {
                "query": query,
                "top_k": 5,
                "use_llm": False  # Disable LLM to avoid region restrictions
            }
            headers = {'X-API-Key': API_KEY}
            response = requests.post(f"{BASE_URL}/search", json=payload, headers=headers)
            
            if response.status_code == 200:
                results = response.json()
                print(f"✅ Search for '{query}': Found {len(results.get('results', []))} results")
                for i, result in enumerate(results.get('results', [])[:2]):
                    print(f"   Result {i+1}: {result.get('text', '')[:100]}...")
            else:
                print(f"❌ Search failed for '{query}': {response.status_code} - {response.text}")
                return False
        except Exception as e:
            print(f"❌ Search error for '{query}': {e}")
            return False
    
    return True

def test_vector_search_only():
    """Test vector search without LLM integration"""
    try:
        payload = {
            "query": "safety precautions",
            "use_llm": False,
            "top_k": 3
        }
        headers = {'X-API-Key': API_KEY}
        response = requests.post(f"{BASE_URL}/search", json=payload, headers=headers)
        
        if response.status_code == 200:
            results = response.json()
            print("✅ Vector search test passed")
            print(f"   Found {len(results.get('results', []))} results")
            for i, result in enumerate(results.get('results', [])):
                print(f"   Result {i+1}: {result.get('text', '')[:150]}...")
            return True
        else:
            print(f"❌ Vector search failed: {response.status_code} - {response.text}")
            return False
    except Exception as e:
        print(f"❌ Vector search error: {e}")
        return False

def main():
    print("🧪 Testing OCR PDF Upload, Indexing, and Search with DeepSeek API")
    print("=" * 70)
    
    # Wait a moment for server to be ready
    print("⏳ Waiting for server to be ready...")
    time.sleep(5)
    
    # Test server health
    if not test_server_health():
        print("❌ Server not available, stopping test")
        return
    
    # Test upload
    print("\n📤 Testing OCR PDF Upload...")
    if test_upload_ocr_pdf():
        print("⏳ Waiting for document processing...")
        time.sleep(10)  # Wait for processing
        
        # Test document status
        print("\n📊 Testing Document Status...")
        test_document_status()
        
        # Test search functionality (without LLM due to region restrictions)
        print("\n🔍 Testing Search Functionality (without LLM)...")
        if test_search_functionality():
            print("\n🔍 Testing Vector Search Only...")
            test_vector_search_only()
        else:
            print("❌ Search functionality failed")
    else:
        print("❌ OCR PDF upload failed")
    
    print("\n" + "=" * 70)
    print("✅ Test completed")

if __name__ == "__main__":
    main()