chore(deps): update dependency langchain-core to v1 [security]

.flake8

@@ -0,0 +1,4 @@
+[flake8]
+max-line-length = 88
+extend-ignore = E203, W503, E501, E741, E731
+exclude = .git,.venv,.nox,build,dist

.github/sync-repo-settings.yaml

@@ -27,10 +27,10 @@ branchProtectionRules:
     requiredStatusCheckContexts:
       - "cla/google"
       - "lint"
-      - "integration-test-pr-py39 (langchain-spanner-testing)"
       - "integration-test-pr-py310 (langchain-spanner-testing)"
       - "integration-test-pr-py311 (langchain-spanner-testing)"
       - "integration-test-pr-py312 (langchain-spanner-testing)"
+      - "integration-test-pr-py313 (langchain-spanner-testing)"
       - "conventionalcommits.org"
       - "header-check"
     # - Add required status checks like presubmit tests

DEVELOPER.md

@@ -34,11 +34,11 @@ These tests are registered as required tests in `.github/sync-repo-settings.yaml
 
 #### Trigger Setup
 
-Cloud Build triggers (for Python versions 3.9 to 3.11) were created with the following specs:
+Cloud Build triggers (for Python versions 3.10 to 3.13) were created with the following specs:
 
 ```YAML
 name: integration-test-pr-py39
-description: Run integration tests on PR for Python 3.9
+description: Run integration tests on PR for Python 3.10
 filename: integration.cloudbuild.yaml
 github:
   name: langchain-google-spanner-python
@@ -55,7 +55,7 @@ substitutions:
   _INSTANCE_ID: <ADD_VALUE>
   _PG_DATABASE: <ADD_VALUE>
   _GOOGLE_DATABASE: <ADD_VALUE>
-  _VERSION: "3.9"
+  _VERSION: "3.10"
 ```
 
 Use `gcloud builds triggers import --source=trigger.yaml` to create triggers via the command line

README.rst

@@ -44,7 +44,7 @@ With `virtualenv`_, it’s possible to install this library without needing syst
 Supported Python Versions
 ^^^^^^^^^^^^^^^^^^^^^^^^^
 
-Python >= 3.9
+Python >= 3.10
 
 Mac/Linux
 ^^^^^^^^^
@@ -73,15 +73,19 @@ Use a vector store to store embedded data and perform vector search.
 
 .. code-block:: python
 
-    from langchain_google_spanner import SpannerVectorstore
-    from langchain.embeddings import VertexAIEmbeddings
+    from langchain_google_spanner import SpannerVectorStore
+    from langchain_google_genai import GoogleGenerativeAIEmbeddings
 
-    embeddings_service = VertexAIEmbeddings(model_name="textembedding-gecko@003")
+    embeddings_service = GoogleGenerativeAIEmbeddings(
+        model="textembedding-gecko@003",
+        project="my-project",
+        vertexai=True,
+    )
     vectorstore = SpannerVectorStore(
         instance_id="my-instance",
         database_id="my-database",
         table_name="my-table",
-        embeddings=embedding_service
+        embeddings=embeddings_service
     )
 
 See the full `Vector Store`_ tutorial.
@@ -159,15 +163,15 @@ Use ``SpannerGraphQAChain`` for question answering over a graph stored in Spanne
 .. code:: python
 
     from langchain_google_spanner import SpannerGraphStore, SpannerGraphQAChain
-    from langchain_google_vertexai import ChatVertexAI
+    from langchain_google_genai import ChatGoogleGenerativeAI
 
 
     graph = SpannerGraphStore(
         instance_id="my-instance",
         database_id="my-database",
         graph_name="my_graph",
     )
-    llm = ChatVertexAI()
+    llm = ChatGoogleGenerativeAI()
     chain = SpannerGraphQAChain.from_llm(
         llm,
         graph=graph,
@@ -187,15 +191,15 @@ Use ``SpannerGraphTextToGQLRetriever`` to translate natural language question to
 .. code:: python
 
     from langchain_google_spanner import SpannerGraphStore, SpannerGraphTextToGQLRetriever
-    from langchain_google_vertexai import ChatVertexAI
+    from langchain_google_genai import ChatGoogleGenerativeAI
 
 
     graph = SpannerGraphStore(
         instance_id="my-instance",
         database_id="my-database",
         graph_name="my_graph",
     )
-    llm = ChatVertexAI()
+    llm = ChatGoogleGenerativeAI()
     retriever = SpannerGraphTextToGQLRetriever.from_params(
         graph_store=graph,
         llm=llm
@@ -207,15 +211,19 @@ Use ``SpannerGraphVectorContextRetriever`` to perform vector search on embedding
 .. code:: python
 
     from langchain_google_spanner import SpannerGraphStore, SpannerGraphVectorContextRetriever
-    from langchain_google_vertexai import ChatVertexAI, VertexAIEmbeddings
+    from langchain_google_genai import GoogleGenerativeAIEmbeddings
 
 
     graph = SpannerGraphStore(
         instance_id="my-instance",
         database_id="my-database",
         graph_name="my_graph",
     )
-    embedding_service = VertexAIEmbeddings(model_name="text-embedding-004")
+    embedding_service = GoogleGenerativeAIEmbeddings(
+        model="gemini-embedding-2",
+        project="my-project",
+        vertexai=True,
+    )
     retriever = SpannerGraphVectorContextRetriever.from_params(
             graph_store=graph,
             embedding_service=embedding_service,

docs/graph_qa_chain.ipynb

@@ -273,7 +273,7 @@
     "# @title Extract Nodes and Edges from text snippets\n",
     "from langchain_core.documents import Document\n",
     "from langchain_experimental.graph_transformers import LLMGraphTransformer\n",
-    "from langchain_google_vertexai import ChatVertexAI\n",
+    "from langchain_google_genai import ChatGoogleGenerativeAI\n",
     "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
     "\n",
     "text_snippets = [\n",
@@ -333,7 +333,7 @@
     "documents = [Document(page_content=t) for t in text_snippets]\n",
     "text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)\n",
     "splits = text_splitter.split_documents(documents)\n",
-    "llm = ChatVertexAI(model=\"gemini-1.5-flash\", temperature=0)\n",
+    "llm = ChatGoogleGenerativeAI(model=\"gemini-1.5-flash\", temperature=0)\n",
     "llm_transformer = LLMGraphTransformer(\n",
     "    llm=llm,\n",
     "    allowed_nodes=[\"College\", \"Deparatment\", \"Person\", \"Year\", \"Company\"],\n",
@@ -495,11 +495,11 @@
    "source": [
     "from google.cloud import spanner\n",
     "from langchain_google_spanner import SpannerGraphQAChain\n",
-    "from langchain_google_vertexai import ChatVertexAI\n",
+    "from langchain_google_genai import ChatGoogleGenerativeAI\n",
     "from IPython.core.display import HTML\n",
     "\n",
     "# Initialize llm object\n",
-    "llm = ChatVertexAI(model=\"gemini-2.0-flash-001\", temperature=0)\n",
+    "llm = ChatGoogleGenerativeAI(model=\"gemini-3.1-flash-lite\", temperature=0)\n",
     "\n",
     "# Initialize GraphQAChain\n",
     "chain = SpannerGraphQAChain.from_llm(\n",