Pass Standard Tests (#35)

* Make changes to pass standard tests

* Add standard tests

* Version change

* Use values clause in MERGE and add more comments

* Add new versions

* Fix error handling

* Add error messages for input length mismatch

* Increase minor version

* Update versions

Author: fileames

libs/oracledb/langchain_oracledb/vectorstores/oraclevs.py

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langchain-oracledb"
-version = "1.0.2"
+version = "1.1.0"
 description = "An integration package connecting Oracle Database and LangChain"
 authors = []
 readme = "README.md"
@@ -12,7 +12,10 @@ license = "UPL"
 
 [tool.poetry.dependencies]
 python = ">=3.9,<4.0"
-langchain-core = ">=0.3.15,<0.4"
+langchain-core = [
+ { version = "^0.3.15", python = "<3.10" },
+ { version = "^1.0.0", python = ">=3.10" }
+]
 langchain-community = ">=0.3.0"
 oracledb = ">=2.2.0"
 pydantic = ">=2,<3"
@@ -28,6 +31,10 @@ syrupy = "^4.0.2"
 pytest-asyncio = "^0.23.2"
 pytest-watcher = "^0.3.4"
 sentence-transformers = "^5.0.0"
+langchain-tests = [
+ { version = "^0.3.21", python = "<3.10" },
+ { version = "^1.0.0", python = ">=3.10" }
+]
 
 [tool.poetry.group.codespell]
 optional = true

libs/oracledb/poetry.lock

@@ -0,0 +1,2 @@
+# Copyright (c) 2025 Oracle and/or its affiliates.
+# Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/

libs/oracledb/pyproject.toml

@@ -0,0 +1,32 @@
+from typing import Type
+
+import oracledb
+import pytest
+from langchain_tests.integration_tests import EmbeddingsIntegrationTests
+
+from langchain_oracledb import OracleEmbeddings
+
+username = ""
+password = ""
+dsn = ""
+
+try:
+    oracledb.connect(user=username, password=password, dsn=dsn)
+except Exception as e:
+    pytest.skip(
+        allow_module_level=True,
+        reason=f"Database connection failed: {e}, skipping tests.",
+    )
+
+
+class TestOracleEmbeddingsModelIntegration(EmbeddingsIntegrationTests):
+    @property
+    def embeddings_class(self) -> Type[OracleEmbeddings]:
+        # Return the embeddings model class to test here
+        return OracleEmbeddings
+
+    @property
+    def embedding_model_params(self) -> dict:
+        # Return initialization parameters for the model.
+        conn = oracledb.connect(user=username, password=password, dsn=dsn)
+        return {"conn": conn, "params": {"provider": "database", "model": "allminilm"}}

libs/oracledb/tests/integration_tests/embeddings/__init__.py

@@ -14,13 +14,15 @@
 import threading
 from typing import Union
 
+import numpy as np
 import oracledb
 import pytest
 from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain_community.vectorstores.utils import DistanceStrategy
 
 from langchain_oracledb.embeddings import OracleEmbeddings
 from langchain_oracledb.vectorstores.oraclevs import (
+    INTERNAL_ID_KEY,
     OracleVS,
     _acreate_table,
     _aindex_exists,
@@ -1165,6 +1167,7 @@ def test_add_texts_test() -> None:
     vs_obj = OracleVS(connection, model, "TB7", DistanceStrategy.EUCLIDEAN_DISTANCE)
     ids6 = ['"Good afternoon"', '"India"']
     vs_obj.add_texts(texts2, ids=ids6)
+    assert len(vs_obj.add_texts(texts2, ids=ids6)) == 0
     drop_table_purge(connection, "TB7")
 
     # 4. Add records with ids and metadatas
@@ -1208,30 +1211,6 @@ def add(val: str) -> None:
     thread_2.join()
     drop_table_purge(connection, "TB10")
 
-    # 7. Add 2 same record concurrently
-    # Expectation:Successful, For one of the insert,get primary key violation error
-    def add1(val: str) -> None:
-        model = HuggingFaceEmbeddings(
-            model_name="sentence-transformers/all-mpnet-base-v2"
-        )
-        vs_obj = OracleVS(
-            connection, model, "TB11", DistanceStrategy.EUCLIDEAN_DISTANCE
-        )
-        texts = [val]
-        ids10 = texts
-        vs_obj.add_texts(texts, ids=ids10)
-
-    try:
-        thread_1 = threading.Thread(target=add1, args=("Sri Ram"))
-        thread_2 = threading.Thread(target=add1, args=("Sri Ram"))
-        thread_1.start()
-        thread_2.start()
-        thread_1.join()
-        thread_2.join()
-    except Exception:
-        pass
-    drop_table_purge(connection, "TB11")
-
     # 8. create object with table name of type <schema_name.table_name>
     # Expectation:U1 does not exist
     with pytest.raises(RuntimeError):
@@ -1317,6 +1296,7 @@ async def test_add_texts_test_async() -> None:
     )
     ids6 = ['"Good afternoon"', '"India"']
     await vs_obj.aadd_texts(texts2, ids=ids6)
+    assert len(await vs_obj.aadd_texts(texts2, ids=ids6)) == 0
     await adrop_table_purge(connection, "TB7")
 
     # 4. Add records with ids and metadatas
@@ -1362,26 +1342,6 @@ async def add(val: str) -> None:
     await asyncio.gather(task_1, task_2)
     await adrop_table_purge(connection, "TB10")
 
-    # 7. Add 2 same record concurrently
-    # Expectation:Successful, For one of the insert,get primary key violation error
-    async def add1(val: str) -> None:
-        model = HuggingFaceEmbeddings(
-            model_name="sentence-transformers/all-mpnet-base-v2"
-        )
-        vs_obj = await OracleVS.acreate(
-            connection, model, "TB11", DistanceStrategy.EUCLIDEAN_DISTANCE
-        )
-        texts = [val]
-        ids10 = texts
-        await vs_obj.aadd_texts(texts, ids=ids10)
-
-    with pytest.raises(RuntimeError):
-        task_1 = asyncio.create_task(add1("Sri Ram"))
-        task_2 = asyncio.create_task(add1("Sri Ram"))
-        await asyncio.gather(task_1, task_2)
-
-    await adrop_table_purge(connection, "TB11")
-
     # 8. create object with table name of type <schema_name.table_name>
     # Expectation:U1 does not exist
     with pytest.raises(RuntimeError):
@@ -1695,7 +1655,9 @@ def test_perform_search_test() -> None:
         vs.similarity_search(query, 2, filter=db_filter)
 
         # Similarity search with relevance score
-        vs.similarity_search_with_score(query, 2)
+        res = vs.similarity_search_with_score(query, 2)
+        assert all(isinstance(_r[1], float) for _r in res)
+        assert res[0][1] <= res[1][1]
 
         # Similarity search with relevance score with filter
         vs.similarity_search_with_score(query, 2, filter=db_filter)
@@ -1787,7 +1749,9 @@ async def test_perform_search_test_async() -> None:
         await vs.asimilarity_search(query, 2, filter=db_filter)
 
         # Similarity search with relevance score
-        await vs.asimilarity_search_with_score(query, 2)
+        res = await vs.asimilarity_search_with_score(query, 2)
+        assert all(isinstance(_r[1], float) for _r in res)
+        assert res[0][1] <= res[1][1]
 
         # Similarity search with relevance score with filter
         await vs.asimilarity_search_with_score(query, 2, filter=db_filter)
@@ -2518,6 +2482,14 @@ def test_oracle_embeddings() -> None:
     res = vs_obj.similarity_search("database", 1)
 
     assert "Database" in res[0].page_content
+    assert "100" == res[0].id
+
+    embedding = model.embed_query("Database Document")
+    res = vs_obj.similarity_search_by_vector_returning_embeddings(embedding, 1)  # type: ignore
+
+    # distance
+    assert all(np.isclose([res[0][1]], [0]))  # type: ignore
+    assert all(np.isclose(res[0][2], embedding))  # type: ignore
 
     drop_table_purge(connection, "TB1")
 
@@ -2556,6 +2528,14 @@ async def test_oracle_embeddings_async(caplog: pytest.LogCaptureFixture) -> None
     res = await vs_obj.asimilarity_search("database", 1)
 
     assert "Database" in res[0].page_content
+    assert "100" == res[0].id
+
+    embedding = model.embed_query("Database Document")
+    res = await vs_obj.asimilarity_search_by_vector_returning_embeddings(embedding, 1)  # type: ignore
+
+    # distance
+    assert all(np.isclose([res[0][1]], [0]))  # type: ignore
+    assert all(np.isclose(res[0][2], embedding))  # type: ignore
 
     await adrop_table_purge(connection, "TB1")
 
@@ -2987,3 +2967,75 @@ def model1(_) -> list[float]:  # type: ignore[no-untyped-def]
         result = await vs.asimilarity_search("Hello", k=3, filter=_f)
 
     await adrop_table_purge(connection, "TB10")
+
+
+##################################
+####### test_reserved  ######
+##################################
+
+
+def test_reserved() -> None:
+    try:
+        connection = oracledb.connect(user=username, password=password, dsn=dsn)
+    except Exception:
+        sys.exit(1)
+
+    drop_table_purge(connection, "TB1")
+
+    embedder_params = {"provider": "database", "model": "allminilm"}
+    proxy = ""
+
+    # instance
+    model = OracleEmbeddings(conn=connection, params=embedder_params, proxy=proxy)
+
+    vs_obj = OracleVS(connection, model, "TB1", DistanceStrategy.EUCLIDEAN_DISTANCE)
+
+    texts = ["Database Document", "Code Document"]
+    metadata = [
+        {"id": "100", "link": "Document Example Test 1", INTERNAL_ID_KEY: "my_temp_id"},
+        {"id": "101", "link": "Document Example Test 2"},
+    ]
+
+    with pytest.raises(ValueError, match="reserved"):
+        vs_obj.add_texts(texts, metadata, ids=["1", "2"])
+
+    drop_table_purge(connection, "TB1")
+
+    connection.close()
+
+
+@pytest.mark.asyncio
+async def test_reserved_async() -> None:
+    try:
+        connection = await oracledb.connect_async(
+            user=username, password=password, dsn=dsn
+        )
+
+        connection_sync = oracledb.connect(user=username, password=password, dsn=dsn)
+    except Exception:
+        sys.exit(1)
+
+    await adrop_table_purge(connection, "TB1")
+
+    embedder_params = {"provider": "database", "model": "allminilm"}
+    proxy = ""
+
+    # instance
+    model = OracleEmbeddings(conn=connection_sync, params=embedder_params, proxy=proxy)
+
+    vs_obj = await OracleVS.acreate(
+        connection, model, "TB1", DistanceStrategy.EUCLIDEAN_DISTANCE
+    )
+
+    texts = ["Database Document", "Code Document"]
+    metadata = [
+        {"id": "100", "link": "Document Example Test 1", INTERNAL_ID_KEY: "my_temp_id"},
+        {"id": "101", "link": "Document Example Test 2"},
+    ]
+
+    with pytest.raises(ValueError, match="reserved"):
+        await vs_obj.aadd_texts(texts, metadata, ids=["1", "2"])
+
+    await adrop_table_purge(connection, "TB1")
+
+    connection.close()