langchain-postgres 0.0.18__tar.gz → 0.0.19__tar.gz

{langchain_postgres-0.0.18 → langchain_postgres-0.0.19}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: langchain-postgres
-Version: 0.0.18
+Version: 0.0.19
 Summary: An integration package connecting Postgres and LangChain
 License-Expression: MIT
 License-File: LICENSE
@@ -85,7 +85,7 @@ store = PGVectorStore.create_sync(
 docs = [
     Document(page_content="Apples and oranges"),
     Document(page_content="Cars and airplanes"),
-    Document(page_content="Train")
+    Document(page_content="Train"),
 ]
 
 store.add_documents(docs)
@@ -107,9 +107,7 @@ vs = PGVectorStore.create_sync(
     engine=engine,
     table_name=TABLE_NAME,
     embedding_service=embedding,
-    hybrid_search_config=HybridSearchConfig(
-      fusion_function=reciprocal_rank_fusion
-    ),
+    hybrid_search_config=HybridSearchConfig(fusion_function=reciprocal_rank_fusion),
 )
 hybrid_docs = vector_store.similarity_search("products", k=5)
 ```
@@ -138,7 +136,7 @@ import psycopg
 
 # Establish a synchronous connection to the database
 # (or use psycopg.AsyncConnection for async)
-conn_info = ... # Fill in with your connection info
+conn_info = ...  # Fill in with your connection info
 sync_connection = psycopg.connect(conn_info)
 
 # Create the table schema (only needs to be done once)
@@ -149,17 +147,17 @@ session_id = str(uuid.uuid4())
 
 # Initialize the chat history manager
 chat_history = PostgresChatMessageHistory(
-    table_name,
-    session_id,
-    sync_connection=sync_connection
+    table_name, session_id, sync_connection=sync_connection
 )
 
 # Add messages to the chat history
-chat_history.add_messages([
-    SystemMessage(content="Meow"),
-    AIMessage(content="woof"),
-    HumanMessage(content="bark"),
-])
+chat_history.add_messages(
+    [
+        SystemMessage(content="Meow"),
+        AIMessage(content="woof"),
+        HumanMessage(content="bark"),
+    ]
+)
 
 print(chat_history.messages)
 ```

{langchain_postgres-0.0.18 → langchain_postgres-0.0.19}/README.md

@@ -69,7 +69,7 @@ store = PGVectorStore.create_sync(
 docs = [
     Document(page_content="Apples and oranges"),
     Document(page_content="Cars and airplanes"),
-    Document(page_content="Train")
+    Document(page_content="Train"),
 ]
 
 store.add_documents(docs)
@@ -91,9 +91,7 @@ vs = PGVectorStore.create_sync(
     engine=engine,
     table_name=TABLE_NAME,
     embedding_service=embedding,
-    hybrid_search_config=HybridSearchConfig(
-      fusion_function=reciprocal_rank_fusion
-    ),
+    hybrid_search_config=HybridSearchConfig(fusion_function=reciprocal_rank_fusion),
 )
 hybrid_docs = vector_store.similarity_search("products", k=5)
 ```
@@ -122,7 +120,7 @@ import psycopg
 
 # Establish a synchronous connection to the database
 # (or use psycopg.AsyncConnection for async)
-conn_info = ... # Fill in with your connection info
+conn_info = ...  # Fill in with your connection info
 sync_connection = psycopg.connect(conn_info)
 
 # Create the table schema (only needs to be done once)
@@ -133,17 +131,17 @@ session_id = str(uuid.uuid4())
 
 # Initialize the chat history manager
 chat_history = PostgresChatMessageHistory(
-    table_name,
-    session_id,
-    sync_connection=sync_connection
+    table_name, session_id, sync_connection=sync_connection
 )
 
 # Add messages to the chat history
-chat_history.add_messages([
-    SystemMessage(content="Meow"),
-    AIMessage(content="woof"),
-    HumanMessage(content="bark"),
-])
+chat_history.add_messages(
+    [
+        SystemMessage(content="Meow"),
+        AIMessage(content="woof"),
+        HumanMessage(content="bark"),
+    ]
+)
 
 print(chat_history.messages)
 ```

{langchain_postgres-0.0.18 → langchain_postgres-0.0.19}/langchain_postgres/v2/async_vectorstore.py

@@ -119,6 +119,15 @@ class AsyncPGVectorStore(VectorStore):
                 "Only create class through 'create' or 'create_sync' methods!"
             )
 
+        if hasattr(embedding_service, "embed_query_inline") and not hasattr(
+            embedding_service, "embed_query_inline_template"
+        ):
+            raise ValueError(
+                "The provided embedding_service is using an outdated inline embedding implementation "
+                "that is susceptible to SQL injection. Please update your package "
+                "to a version that supports 'embed_query_inline_template'."
+            )
+
         self.engine = engine
         self.embedding_service = embedding_service
         self.table_name = table_name
@@ -295,8 +304,7 @@ class AsyncPGVectorStore(VectorStore):
             self.embedding_service, "embed_query_inline_template", None
         )
         can_inline_embed_template = callable(inline_template_func)
-        inline_embed_func = getattr(self.embedding_service, "embed_query_inline", None)
-        can_inline_embed = callable(inline_embed_func)
+
         # Insert embeddings
         for id, content, embedding, metadata in zip(ids, texts, embeddings, metadatas):
             metadata_col_names = (
@@ -319,8 +327,6 @@ class AsyncPGVectorStore(VectorStore):
 
             if not embedding and can_inline_embed_template:
                 values_stmt = f"VALUES (:langchain_id, :content, {inline_template_func(':content')}"  # type: ignore
-            elif not embedding and can_inline_embed:
-                values_stmt = f"VALUES (:langchain_id, :content, {self.embedding_service.embed_query_inline(content)}"  # type: ignore
 
             if self.hybrid_search_config and self.hybrid_search_config.tsv_column:
                 lang = (
@@ -392,8 +398,7 @@ class AsyncPGVectorStore(VectorStore):
         inline_template_func = getattr(
             self.embedding_service, "embed_query_inline_template", None
         )
-        inline_embed_func = getattr(self.embedding_service, "embed_query_inline", None)
-        if callable(inline_template_func) or callable(inline_embed_func):
+        if callable(inline_template_func):
             embeddings: list[list[float]] = [[] for _ in list(texts)]
         else:
             embeddings = await self.embedding_service.aembed_documents(list(texts))
@@ -676,15 +681,10 @@ class AsyncPGVectorStore(VectorStore):
         inline_template_func = getattr(
             self.embedding_service, "embed_query_inline_template", None
         )
-        inline_embed_func = getattr(self.embedding_service, "embed_query_inline", None)
         param_dict: dict[str, Any] = {"dense_limit": dense_limit}
         if not embedding and callable(inline_template_func) and "query" in kwargs:
             embedding_data_string = inline_template_func(":query_text")
             param_dict["query_text"] = kwargs["query"]
-        elif not embedding and callable(inline_embed_func) and "query" in kwargs:
-            query_embedding = self.embedding_service.embed_query_inline(kwargs["query"])  # type: ignore
-            embedding_data_string = f"{query_embedding}"
-            param_dict["query_embedding"] = query_embedding
         else:
             query_embedding = f"{[float(dimension) for dimension in embedding]}"
             embedding_data_string = ":query_embedding"
@@ -789,10 +789,9 @@ class AsyncPGVectorStore(VectorStore):
         inline_template_func = getattr(
             self.embedding_service, "embed_query_inline_template", None
         )
-        inline_embed_func = getattr(self.embedding_service, "embed_query_inline", None)
         embedding = (
             []
-            if callable(inline_template_func) or callable(inline_embed_func)
+            if callable(inline_template_func)
             else await self.embedding_service.aembed_query(text=query)
         )
         kwargs["query"] = query
@@ -831,10 +830,9 @@ class AsyncPGVectorStore(VectorStore):
         inline_template_func = getattr(
             self.embedding_service, "embed_query_inline_template", None
         )
-        inline_embed_func = getattr(self.embedding_service, "embed_query_inline", None)
         embedding = (
             []
-            if callable(inline_template_func) or callable(inline_embed_func)
+            if callable(inline_template_func)
             else await self.embedding_service.aembed_query(text=query)
         )
         kwargs["query"] = query

{langchain_postgres-0.0.18 → langchain_postgres-0.0.19}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "langchain-postgres"
-version = "0.0.18"
+version = "0.0.19"
 description = "An integration package connecting Postgres and LangChain"
 authors = []
 readme = "README.md"

{langchain_postgres-0.0.18 → langchain_postgres-0.0.19}/tests/unit_tests/v2/test_async_pg_vectorstore.py

@@ -572,36 +572,6 @@ class TestVectorStore:
         assert ":content, embedding('model_id', :content)::vector" in sql_text
         assert params["content"] == "hello world"
 
-    async def test_aadd_embeddings_with_legacy_inline(self) -> None:
-        class LegacyEmbeddings(Embeddings):
-            def embed_documents(self, texts: list[str]) -> list[list[float]]:
-                return []
-
-            def embed_query(self, text: str) -> list[float]:
-                return []
-
-            def embed_query_inline(self, query: str) -> str:
-                return f"embedding('model_id', '{query}')::vector"
-
-        mock_conn = AsyncMock()
-        mock_engine = MagicMock()
-        mock_engine.connect.return_value.__aenter__.return_value = mock_conn
-        mock_engine.connect.return_value.__aexit__.return_value = None
-
-        create_key = getattr(AsyncPGVectorStore, "_AsyncPGVectorStore__create_key")
-        vs = AsyncPGVectorStore(
-            create_key,
-            engine=mock_engine,
-            embedding_service=LegacyEmbeddings(),
-            table_name="test_table",
-        )
-        await vs.aadd_embeddings(texts=["hello world"], embeddings=[[]])
-        call_args = mock_conn.execute.call_args
-        sql_text = str(call_args[0][0])
-        params = call_args[0][1]
-        assert "embedding('model_id', 'hello world')::vector" in sql_text
-        assert params["content"] == "hello world"
-
     async def test_asimilarity_search_with_inline_template(self) -> None:
         class TemplateEmbeddings(Embeddings):
             def embed_documents(self, texts: list[str]) -> list[list[float]]:
@@ -638,8 +608,8 @@ class TestVectorStore:
         assert "embedding('model_id', :query_text)::vector" in sql_text
         assert params["query_text"] == "search query"
 
-    async def test_asimilarity_search_with_legacy_inline(self) -> None:
-        class LegacyEmbeddings(Embeddings):
+    async def test_init_raises_for_outdated_inline_embedding(self) -> None:
+        class OutdatedAlloyDBEmbeddings(Embeddings):
             def embed_documents(self, texts: list[str]) -> list[list[float]]:
                 return []
 
@@ -649,30 +619,14 @@ class TestVectorStore:
             def embed_query_inline(self, query: str) -> str:
                 return f"embedding('model_id', '{query}')::vector"
 
-        mock_conn = AsyncMock()
-        mock_result = MagicMock()
-        mock_result.mappings.return_value.fetchall.return_value = []
-        mock_conn.execute.return_value = mock_result
-
-        mock_engine = MagicMock()
-        mock_engine.connect.return_value.__aenter__.return_value = mock_conn
-        mock_engine.connect.return_value.__aexit__.return_value = None
-
         create_key = getattr(AsyncPGVectorStore, "_AsyncPGVectorStore__create_key")
-        vs = AsyncPGVectorStore(
-            create_key,
-            engine=mock_engine,
-            embedding_service=LegacyEmbeddings(),
-            table_name="test_table",
-        )
-        await vs.asimilarity_search_with_score_by_vector(
-            embedding=[], query="legacy search"
-        )
-        call_args = mock_conn.execute.call_args
-        sql_text = str(call_args[0][0])
-        params = call_args[0][1]
-        assert "embedding('model_id', 'legacy search')::vector" in sql_text
-        assert (
-            params["query_embedding"]
-            == "embedding('model_id', 'legacy search')::vector"
-        )
+
+        with pytest.raises(
+            ValueError, match="outdated inline embedding implementation"
+        ):
+            AsyncPGVectorStore(
+                create_key,
+                engine=None,  # type: ignore
+                embedding_service=OutdatedAlloyDBEmbeddings(),
+                table_name="test_table",
+            )

{langchain_postgres-0.0.18 → langchain_postgres-0.0.19}/uv.lock

@@ -21,17 +21,16 @@ wheels = [
 
 [[package]]
 name = "anyio"
-version = "4.11.0"
+version = "4.14.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "exceptiongroup", marker = "python_full_version < '3.11'" },
     { name = "idna" },
-    { name = "sniffio" },
     { name = "typing-extensions", marker = "python_full_version < '3.13'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/c6/78/7d432127c41b50bccba979505f272c16cbcadcc33645d5fa3a738110ae75/anyio-4.11.0.tar.gz", hash = "sha256:82a8d0b81e318cc5ce71a5f1f8b5c4e63619620b63141ef8c995fa0db95a57c4", size = 219094, upload-time = "2025-09-23T09:19:12.58Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/61/cc/a381afa6efea9f496eff839d4a6a1aed3bfafc7b3ab4b0d1b243a12573dd/anyio-4.14.2.tar.gz", hash = "sha256:cfa139f3ed1a23ee8f88a145ddb5ac7605b8bbfd8592baacd7ce3d8bb4313c7f", size = 260176, upload-time = "2026-07-12T20:29:07.082Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/15/b3/9b1a8074496371342ec1e796a96f99c82c945a339cd81a8e73de28b4cf9e/anyio-4.11.0-py3-none-any.whl", hash = "sha256:0287e96f4d26d4149305414d4e3bc32f0dcd0862365a4bddea19d7a1ec38c4fc", size = 109097, upload-time = "2025-09-23T09:19:10.601Z" },
+    { url = "https://files.pythonhosted.org/packages/da/35/f2287558c17e29fafc8ef3daf819bb9834061cfa43bff8014f7df7f63bdc/anyio-4.14.2-py3-none-any.whl", hash = "sha256:9f505dda5ac9f0c8309b5e8bd445a8c2bf7246f3ce950121e45ea15bc41d1494", size = 125813, upload-time = "2026-07-12T20:29:05.763Z" },
 ]
 
 [[package]]
@@ -568,7 +567,7 @@ wheels = [
 
 [[package]]
 name = "langchain-postgres"
-version = "0.0.17"
+version = "0.0.19"
 source = { editable = "." }
 dependencies = [
     { name = "asyncpg" },
@@ -1511,15 +1510,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/b8/81/4b6387be7014858d924b843530e1b2a8e531846807516e9bea2ee0936bf7/ruff-0.14.1-py3-none-win_arm64.whl", hash = "sha256:e3b443c4c9f16ae850906b8d0a707b2a4c16f8d2f0a7fe65c475c5886665ce44", size = 12436636, upload-time = "2025-10-16T18:05:38.995Z" },
 ]
 
-[[package]]
-name = "sniffio"
-version = "1.3.1"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/a2/87/a6771e1546d97e7e041b6ae58d80074f81b7d5121207425c964ddf5cfdbd/sniffio-1.3.1.tar.gz", hash = "sha256:f4324edc670a0f49750a81b895f35c3adb843cca46f0530f79fc1babb23789dc", size = 20372, upload-time = "2024-02-25T23:20:04.057Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/e9/44/75a9c9421471a6c4805dbf2356f7c181a29c1879239abab1ea2cc8f38b40/sniffio-1.3.1-py3-none-any.whl", hash = "sha256:2f6da418d1f1e0fddd844478f41680e794e6051915791a034ff65e5f100525a2", size = 10235, upload-time = "2024-02-25T23:20:01.196Z" },
-]
-
 [[package]]
 name = "sqlalchemy"
 version = "2.0.44"