File size: 3,960 Bytes
ed91833 654e910 ed91833 654e910 ed91833 999f24c ed91833 1ef298a ed91833 999f24c 1ef298a ed91833 999f24c ed91833 999f24c ed91833 999f24c 1ef298a 999f24c ed91833 999f24c ed91833 1ef298a 999f24c 1ef298a 999f24c 654e910 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 |
import os
import socket
import pytest
import requests
from langchain.schema import Document
from backend.app.vectorstore import get_vector_db, _get_qdrant_client
def test_directory_creation():
get_vector_db()
assert os.path.exists("static/data")
assert os.path.exists("static/data/langchain_rag_tutorial.html")
# TODO remove this test when data ingrestion layer is implemented
def test_html_content():
with open("static/data/langchain_rag_tutorial.html", "r", encoding="utf-8") as f:
content = f.read()
# Check for some expected content from the LangChain RAG tutorial
assert "RAG" in content
assert "LangChain" in content
def test_vector_store_similarity_search():
"""Test that the vector store can perform similarity search"""
# Test query
query = "What is RAG?"
# Get vector db instance and perform similarity search
vector_db = get_vector_db()
results = vector_db.similarity_search(query, k=2)
# Verify we get results
assert len(results) == 2
assert isinstance(results[0], Document)
# Verify the results contain relevant content
combined_content = " ".join([doc.page_content for doc in results]).lower()
assert "rag" in combined_content
assert "retrieval" in combined_content
def test_vector_db_singleton():
"""Test that get_vector_db returns the same instance each time"""
# Get two instances
instance1 = get_vector_db()
instance2 = get_vector_db()
assert instance1 is instance2
def test_qdrant_cloud_connection():
"""Test basic connectivity to Qdrant Cloud"""
# Skip test if not configured for cloud
if not os.environ.get("QDRANT_URL") or not os.environ.get("QDRANT_API_KEY"):
pytest.skip("Qdrant Cloud credentials not configured")
try:
# Print URL for debugging (excluding any path components)
qdrant_url = os.environ.get("QDRANT_URL", "")
print(f"Attempting to connect to Qdrant at: {qdrant_url}")
# Try to parse the URL components
from urllib.parse import urlparse
parsed_url = urlparse(qdrant_url)
print(f"Scheme: {parsed_url.scheme}")
print(f"Hostname: {parsed_url.hostname}")
print(f"Port: {parsed_url.port}")
print(f"Path: {parsed_url.path}")
client = _get_qdrant_client()
client.get_collections()
assert True, "Connection successful"
except Exception as e:
assert False, f"Failed to connect to Qdrant Cloud: {str(e)}"
def test_external_connectivity():
"""Test basic external connectivity and DNS resolution.
Test needed since Docker gave an issue with this before. Couldn't resolve Qdrant host.
"""
# Skip test if not configured for cloud
if not os.environ.get("QDRANT_URL") or not os.environ.get("QDRANT_API_KEY"):
pytest.skip("Qdrant Cloud credentials not configured")
# Test DNS resolution first
try:
# Try to resolve google.com
google_ip = socket.gethostbyname("google.com")
print(f"Successfully resolved google.com to {google_ip}")
# If we have Qdrant URL, try to resolve that too
qdrant_url = os.environ.get("QDRANT_URL", "")
if qdrant_url:
qdrant_host = (
qdrant_url.replace("https://", "").replace("http://", "").split("/")[0]
)
print(f"Qdrant host: {qdrant_host}")
qdrant_ip = socket.gethostbyname(qdrant_host)
print(f"Successfully resolved Qdrant host {qdrant_host}")
except socket.gaierror as e:
assert False, f"DNS resolution failed: {str(e)}"
# Test HTTP connectivity
try:
response = requests.get("https://www.google.com", timeout=5)
assert (
response.status_code == 200
), "Expected successful response from google.com"
except requests.exceptions.RequestException as e:
assert False, f"Failed to connect to google.com: {str(e)}"
|