Skip to main content

Google Spanner

Spanner is a highly scalable database that combines unlimited scalability with relational semantics, such as secondary indexes, strong consistency, schemas, and SQL providing 99.999% availability in one easy solution.

This notebook goes over how to use Spanner for Vector Search with SpannerVectorStore class.

Learn more about the package on GitHub.

Open In Colab

Before You Begin

To run this notebook, you will need to do the following:

🦜🔗 Library Installation

The integration lives in its own langchain-google-spanner package, so we need to install it.

%pip install --upgrade --quiet langchain-google-spanner
Note: you may need to restart the kernel to use updated packages.

Colab only: Uncomment the following cell to restart the kernel or use the button to restart the kernel. For Vertex AI Workbench you can restart the terminal using the button on top.

# # Automatically restart kernel after installs so that your environment can access the new packages
# import IPython

# app = IPython.Application.instance()
# app.kernel.do_shutdown(True)

🔐 Authentication

Authenticate to Google Cloud as the IAM user logged into this notebook in order to access your Google Cloud Project.

  • If you are using Colab to run this notebook, use the cell below and continue.
  • If you are using Vertex AI Workbench, check out the setup instructions here.
from google.colab import auth


☁ Set Your Google Cloud Project

Set your Google Cloud project so that you can leverage Google Cloud resources within this notebook.

If you don't know your project ID, try the following:

# @markdown Please fill in the value below with your Google Cloud project ID and then run the cell.

PROJECT_ID = "my-project-id" # @param {type:"string"}

# Set the project id
!gcloud config set project {PROJECT_ID}

💡 API Enablement

The langchain-google-spanner package requires that you enable the Spanner API in your Google Cloud Project.

# enable Spanner API
!gcloud services enable

Basic Usage

Set Spanner database values

Find your database values, in the Spanner Instances page.

# @title Set Your Values Here { display-mode: "form" }
INSTANCE = "my-instance" # @param {type: "string"}
DATABASE = "my-database" # @param {type: "string"}
TABLE_NAME = "vectors_search_data" # @param {type: "string"}

Initialize a table

The SpannerVectorStore class instance requires a database table with id, content and embeddings columns.

The helper method init_vector_store_table() that can be used to create a table with the proper schema for you.

from langchain_google_spanner import SecondaryIndex, SpannerVectorStore, TableColumn

TableColumn(name="metadata", type="JSON", is_null=True),
TableColumn(name="title", type="STRING(MAX)", is_null=False),
SecondaryIndex(index_name="row_id_and_title", columns=["row_id", "title"])

Create an embedding class instance

You can use any LangChain embeddings model. You may need to enable Vertex AI API to use VertexAIEmbeddings. We recommend setting the embedding model's version for production, learn more about the Text embeddings models.

# enable Vertex AI API
!gcloud services enable
from langchain_google_vertexai import VertexAIEmbeddings

embeddings = VertexAIEmbeddings(
model_name="textembedding-gecko@latest", project=PROJECT_ID


To initialize the SpannerVectorStore class you need to provide 4 required arguments and other arguments are optional and only need to pass if it's different from default ones

  1. instance_id - The name of the Spanner instance
  2. database_id - The name of the Spanner database
  3. table_name - The name of the table within the database to store the documents & their embeddings.
  4. embedding_service - The Embeddings implementation which is used to generate the embeddings.
db = SpannerVectorStore(

🔐 Add Documents

To add documents in the vector store.

import uuid

from langchain_community.document_loaders import HNLoader

loader = HNLoader("")

documents = loader.load()
ids = [str(uuid.uuid4()) for _ in range(len(documents))]

API Reference:

🔐 Search Documents

To search documents in the vector store with similarity search.

db.similarity_search(query="Explain me vector store?", k=3)

🔐 Search Documents

To search documents in the vector store with max marginal relevance search.

db.max_marginal_relevance_search("Testing the langchain integration with spanner", k=3)

🔐 Delete Documents

To remove documents from the vector store, use the IDs that correspond to the values in the `row_id`` column when initializing the VectorStore.

db.delete(ids=["id1", "id2"])

🔐 Delete Documents

To remove documents from the vector store, you can utilize the documents themselves. The content column and metadata columns provided during VectorStore initialization will be used to find out the rows corresponding to the documents. Any matching rows will then be deleted.

db.delete(documents=[documents[0], documents[1]])

Help us out by providing feedback on this documentation page: