fix(main): fix many mainline test issues

1) test_spanner_vector_store's dependency on HNLoader fails
   - use a different loader
2) test_spanner_vector_store's add_document failed with PK size exceeded
   (this is due to 1, the loader now returns slightly longer content)
   - use a different url
3) test_spanner_loader doesn't properly clean up the test so that now
   testing database has too many tables
   - add cleanup for these tests

Author: mtyin

tests/integration/test_spanner_loader.py

@@ -35,9 +35,41 @@ def client() -> Client:
     return Client(project=project_id)
 
 
+@pytest.fixture()
+def cleanupGSQL(client):
+    yield
+
+    print("\nPerforming GSQL cleanup after each test...")
+
+    database = client.instance(instance_id).database(google_database)
+    operation = database.update_ddl(
+        [
+            f"DROP TABLE IF EXISTS {table_name}",
+        ]
+    )
+    operation.result(OPERATION_TIMEOUT_SECONDS)
+
+    # Code to perform teardown after each test goes here
+    print("\nGSQL Cleanup complete.")
+
+
+@pytest.fixture()
+def cleanupPGSQL(client):
+    yield
+
+    print("\nPerforming PGSQL cleanup after each test...")
+
+    database = client.instance(instance_id).database(pg_database)
+    operation = database.update_ddl([f"DROP TABLE IF EXISTS {table_name}"])
+    operation.result(OPERATION_TIMEOUT_SECONDS)
+
+    # Code to perform teardown after each test goes here
+    print("\n PGSQL Cleanup complete.")
+
+
 class TestSpannerDocumentLoaderGoogleSQL:
     @pytest.fixture(autouse=True, scope="class")
-    def setup_database(self, client):
+    def setup_database(self, client, cleanupGSQL):
         database = client.instance(instance_id).database(google_database)
         operation = database.update_ddl([f"DROP TABLE IF EXISTS {table_name}"])
         operation.result(OPERATION_TIMEOUT_SECONDS)
@@ -455,7 +487,7 @@ def test_loader_custom_json_metadata(self, client):
 
 class TestSpannerDocumentLoaderPostgreSQL:
     @pytest.fixture(autouse=True, scope="class")
-    def setup_database(self, client):
+    def setup_database(self, client, cleanupPGSQL):
         database = client.instance(instance_id).database(pg_database)
         operation = database.update_ddl([f"DROP TABLE IF EXISTS {table_name}"])
         operation.result(OPERATION_TIMEOUT_SECONDS)
@@ -872,15 +904,15 @@ def test_loader_custom_json_metadata(self, client):
 
 class TestSpannerDocumentSaver:
     @pytest.fixture(name="google_client")
-    def setup_google_client(self, client) -> Client:
+    def setup_google_client(self, client, cleanupGSQL) -> Client:
         database = client.instance(instance_id).database(google_database)
         operation = database.update_ddl([f"DROP TABLE IF EXISTS {table_name}"])
         print("table dropped")
         operation.result(OPERATION_TIMEOUT_SECONDS)
         yield client
 
     @pytest.fixture(name="pg_client")
-    def setup_pg_client(self, client) -> Client:
+    def setup_pg_client(self, client, cleanupPGSQL) -> Client:
         database = client.instance(instance_id).database(pg_database)
         operation = database.update_ddl([f"DROP TABLE IF EXISTS {table_name}"])
         operation.result(OPERATION_TIMEOUT_SECONDS)

tests/integration/test_spanner_vector_store.py

@@ -20,7 +20,7 @@
 
 import pytest
 from google.cloud.spanner import Client  # type: ignore
-from langchain_community.document_loaders import HNLoader
+from langchain_community.document_loaders import RecursiveUrlLoader
 from langchain_community.embeddings import FakeEmbeddings
 
 from langchain_google_spanner.vector_store import (  # type: ignore
@@ -245,11 +245,13 @@ def setup_database(self, client):
             id_column="row_id",
             metadata_columns=[
                 TableColumn(name="metadata", type="JSON", is_null=True),
-                TableColumn(name="title", type="STRING(MAX)", is_null=False),
+                TableColumn(name="title", type="STRING(MAX)"),
             ],
         )
 
-        loader = HNLoader("https://news.ycombinator.com/item?id=34817881")
+        loader = RecursiveUrlLoader(
+            "https://news.ycombinator.com/item?id=1", max_depth=1
+        )
 
         embeddings = FakeEmbeddings(size=3)
 
@@ -327,7 +329,7 @@ def test_spanner_vector_delete_data(self, setup_database):
 
         docs = loader.load()
 
-        deleted = db.delete(documents=[docs[0], docs[1]])
+        deleted = db.delete(documents=docs)
 
         assert deleted
 
@@ -459,7 +461,9 @@ def setup_database(self, client):
                 ],
             )
 
-        loader = HNLoader("https://news.ycombinator.com/item?id=34817881")
+        loader = RecursiveUrlLoader(
+            "https://news.ycombinator.com/item?id=1", max_depth=1
+        )
         embeddings = FakeEmbeddings(size=title_vector_size)
 
         def cleanup_db():
@@ -677,8 +681,9 @@ def setup_database(self, client):
             ],
         )
 
-        loader = HNLoader("https://news.ycombinator.com/item?id=34817881")
-
+        loader = RecursiveUrlLoader(
+            "https://news.ycombinator.com/item?id=1", max_depth=1
+        )
         embeddings = FakeEmbeddings(size=3)
 
         yield loader, embeddings