Files
railseek6/test_ocr_no_auth.py

58 lines
2.0 KiB
Python

import requests
import os
import json
import time
# Test uploading the ocr.pdf file to server without authentication
base_url = 'http://localhost:3015'
pdf_file = 'ocr.pdf'
# Check if ocr.pdf exists
if not os.path.exists(pdf_file):
print(f"{pdf_file} not found in current directory")
exit(1)
print(f"📄 Found {pdf_file}, size: {os.path.getsize(pdf_file)} bytes")
# Upload ocr.pdf without authentication
print(f"📤 Uploading {pdf_file} (no auth)...")
with open(pdf_file, 'rb') as file:
files = {'file': (pdf_file, file, 'application/pdf')}
upload_response = requests.post(f'{base_url}/documents/upload', files=files)
print(f" Upload Status: {upload_response.status_code}")
if upload_response.status_code == 200:
print('✅ Upload successful')
result = upload_response.json()
print(f" Response: {json.dumps(result, indent=2)}")
# Wait a moment for processing
print("\n⏳ Waiting for document processing...")
time.sleep(5)
# Check document status
print("\n🔍 Checking document status...")
status_response = requests.get(f'{base_url}/documents')
if status_response.status_code == 200:
documents = status_response.json()
print(f" Documents response: {json.dumps(documents, indent=2)}")
else:
print(f"❌ Failed to get documents: {status_response.text}")
# Test search with content from ocr.pdf
print("\n🔍 Testing search functionality...")
query_data = {'query': 'safety precautions minimum safe distance', 'top_k': 5}
search_response = requests.post(f'{base_url}/query', json=query_data)
if search_response.status_code == 200:
results = search_response.json()
print(f"✅ Search successful (type: {type(results)})")
if isinstance(results, dict):
print(f" Response: {results.get('response', 'No response field')}")
else:
print(f" Raw result: {results}")
else:
print(f'❌ Search failed: {search_response.text}')
else:
print(f'❌ Upload failed: {upload_response.text}')