The agent engineering platform.
Python agentsaiai-agentsanthropicchatgptdeepagentsenterpriseframeworkgeminigenerative-ailangchainlanggraphllmmultiagentopen-sourceopenaipydanticpythonragtypescript
docs: add Vertex Feature Store, edit BigQuery Vector Search (#23709)
eliasecchigefb48566d096
diff --git a/docs/docs/integrations/vectorstores/google_bigquery_vector_search.ipynb b/docs/docs/integrations/vectorstores/google_bigquery_vector_search.ipynbindex e7d336d336..8287bb04ca 100644--- a/docs/docs/integrations/vectorstores/google_bigquery_vector_search.ipynb+++ b/docs/docs/integrations/vectorstores/google_bigquery_vector_search.ipynb@@ -8,10 +8,20 @@"source": ["# Google BigQuery Vector Search\n","\n",- "> [Google Cloud BigQuery Vector Search](https://cloud.google.com/bigquery/docs/vector-search-intro) lets you use GoogleSQL to do semantic search, using vector indexes for fast approximate results, or using brute force for exact results.\n",+ "> [Google Cloud BigQuery Vector Search](https://cloud.google.com/bigquery/docs/vector-search-intro) lets you use GoogleSQL to do semantic search, using vector indexes for fast approximate results, or using brute force for exact results. \n","\n",- "\n",- "This tutorial illustrates how to work with an end-to-end data and embedding management system in LangChain, and provide scalable semantic search in BigQuery."+ "This tutorial illustrates how to work with an end-to-end data and embedding management system in LangChain, and provides a scalable semantic search in BigQuery using the`BigQueryVectorStore` class. This class is part of a set of 2 classes capable of providing a unified data storage and flexible vector search in Google Cloud:\n",+ "- **BigQuery Vector Search**: with `BigQueryVectorStore` class, which is ideal for rapid prototyping with no infrastructure setup and batch retrieval.\n",+ "- **Feature Store Online Store**: with `VertexFSVectorStore` class, enables low-latency retrieval with manual or scheduled data sync. Perfect for production-ready user-facing GenAI applications.\n"+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {+ "id": "25a003cd4edc"+ },+ "source": [+ ""]},{@@ -36,16 +46,11 @@"cell_type": "code","execution_count": null,"metadata": {- "colab": {- "base_uri": "https://localhost:8080/",- "height": 1000- },- "id": "0ZITIDE160OD",- "outputId": "e184bc0d-6541-4e0a-82d2-1e216db00a2d"+ "id": "0ZITIDE160OD"},"outputs": [],"source": [- "%pip install --upgrade --quiet langchain langchain-google-vertexai google-cloud-bigquery"+ "%pip install --upgrade --quiet langchain langchain-google-vertexai \"langchain-google-community[featurestore]\""]},{@@ -54,7 +59,7 @@"id": "v40bB_GMcr9f"},"source": [- "**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."+ "To use the newly installed packages in this Jupyter runtime, you must restart the runtime. You can do this by running the cell below, which restarts the current kernel."]},{@@ -65,23 +70,26 @@},"outputs": [],"source": [- "# # Automatically restart kernel after installs so that your environment can access the new packages\n",- "# import IPython\n",+ "import IPython\n","\n",- "# app = IPython.Application.instance()\n",- "# app.kernel.do_shutdown(True)"+ "app = IPython.Application.instance()\n",+ "app.kernel.do_shutdown(True)"]},{"cell_type": "markdown",- "metadata": {},+ "metadata": {+ "id": "be453ee45565"+ },"source": ["## Before you begin"]},{"cell_type": "markdown",- "metadata": {},+ "metadata": {+ "id": "fb8ebc778a77"+ },"source": ["#### Set your project ID\n","\n",@@ -94,10 +102,11 @@{"cell_type": "code","execution_count": null,- "metadata": {},+ "metadata": {+ "id": "3f00771c2519"+ },"outputs": [],"source": [- "# @title Project { display-mode: \"form\" }\n","PROJECT_ID = \"\" # @param {type:\"string\"}\n","\n","# Set the project id\n",@@ -106,7 +115,9 @@},{"cell_type": "markdown",- "metadata": {},+ "metadata": {+ "id": "0c8db9870db1"+ },"source": ["#### Set the region\n","\n",@@ -116,16 +127,19 @@{"cell_type": "code","execution_count": null,- "metadata": {},+ "metadata": {+ "id": "afbc16ea31fc"+ },"outputs": [],"source": [- "# @title Region { display-mode: \"form\" }\n",- "REGION = \"US\" # @param {type: \"string\"}"+ "REGION = \"us-central1\" # @param {type: \"string\"}"]},{"cell_type": "markdown",- "metadata": {},+ "metadata": {+ "id": "1af54eb03565"+ },"source": ["#### Set the dataset and table names\n","\n",@@ -135,17 +149,20 @@{"cell_type": "code","execution_count": null,- "metadata": {},+ "metadata": {+ "id": "259862ba68b1"+ },"outputs": [],"source": [- "# @title Dataset and Table { display-mode: \"form\" }\n","DATASET = \"my_langchain_dataset\" # @param {type: \"string\"}\n","TABLE = \"doc_and_vectors\" # @param {type: \"string\"}"]},{"cell_type": "markdown",- "metadata": {},+ "metadata": {+ "id": "445325c9b3bb"+ },"source": ["### Authenticating your notebook environment\n","\n",@@ -156,12 +173,14 @@{"cell_type": "code","execution_count": null,- "metadata": {},+ "metadata": {+ "id": "d9ff48bb5b3c"+ },"outputs": [],"source": [- "from google.colab import auth as google_auth\n",+ "# from google.colab import auth as google_auth\n","\n",- "google_auth.authenticate_user()"+ "# google_auth.authenticate_user()"]},{@@ -170,12 +189,14 @@"id": "AD3yG49BdLlr"},"source": [- "## Demo: BigQueryVectorSearch"+ "## Demo: BigQueryVectorStore"]},{"cell_type": "markdown",- "metadata": {},+ "metadata": {+ "id": "7b62754dfe6b"+ },"source": ["### Create an embedding class instance\n","\n",@@ -190,11 +211,7 @@"cell_type": "code","execution_count": null,"metadata": {- "colab": {- "base_uri": "https://localhost:8080/"- },- "id": "Vb2RJocV9_LQ",- "outputId": "37f5dc74-2512-47b2-c135-f34c10afdcf4"+ "id": "Vb2RJocV9_LQ"},"outputs": [],"source": [@@ -207,54 +224,39 @@},{"cell_type": "markdown",- "metadata": {},+ "metadata": {+ "id": "76be94ede55d"+ },"source": [- "### Create BigQuery Dataset\n",+ "### Initialize BigQueryVectorStore\n","\n",- "Optional step to create the dataset if it doesn't exist."+ "BigQuery Dataset and Table will be automatically created if they do not exist. See class definition [here](https://github.com/langchain-ai/langchain-google/blob/main/libs/community/langchain_google_community/bq_storage_vectorstores/bigquery.py#L26) for all optional paremeters."]},{"cell_type": "code","execution_count": null,- "metadata": {},- "outputs": [],- "source": [- "from google.cloud import bigquery\n",- "\n",- "client = bigquery.Client(project=PROJECT_ID, location=REGION)\n",- "client.create_dataset(dataset=DATASET, exists_ok=True)"- ]- },- {- "cell_type": "markdown",- "metadata": {},- "source": [- "### Initialize BigQueryVectorSearch Vector Store with an existing BigQuery dataset"- ]- },- {- "cell_type": "code",- "execution_count": null,- "metadata": {},+ "metadata": {+ "id": "14fccb04425d"+ },"outputs": [],"source": [- "from langchain_community.vectorstores import BigQueryVectorSearch\n",- "from langchain_community.vectorstores.utils import DistanceStrategy\n",+ "from langchain_google_community import BigQueryVectorStore\n","\n",- "store = BigQueryVectorSearch(\n",+ "store = BigQueryVectorStore(\n"," project_id=PROJECT_ID,\n"," dataset_name=DATASET,\n"," table_name=TABLE,\n"," location=REGION,\n"," embedding=embedding,\n",- " distance_strategy=DistanceStrategy.EUCLIDEAN_DISTANCE,\n",")"]},{"cell_type": "markdown",- "metadata": {},+ "metadata": {+ "id": "d579f1a26c9a"+ },"source": ["### Add texts"]@@ -262,7 +264,9 @@{"cell_type": "code","execution_count": null,- "metadata": {},+ "metadata": {+ "id": "ebe4f493008b"+ },"outputs": [],"source": ["all_texts = [\"Apples and oranges\", \"Cars and airplanes\", \"Pineapple\", \"Train\", \"Banana\"]\n",@@ -273,7 +277,9 @@},{"cell_type": "markdown",- "metadata": {},+ "metadata": {+ "id": "665e519e68bc"+ },"source": ["### Search for documents"]@@ -281,7 +287,9 @@{"cell_type": "code","execution_count": null,- "metadata": {},+ "metadata": {+ "id": "649e43849f40"+ },"outputs": [],"source": ["query = \"I'd like a fruit.\"\n",@@ -291,7 +299,9 @@},{"cell_type": "markdown",- "metadata": {},+ "metadata": {+ "id": "390820e4b286"+ },"source": ["### Search for documents by vector"]@@ -299,7 +309,9 @@{"cell_type": "code","execution_count": null,- "metadata": {},+ "metadata": {+ "id": "78485da9655c"+ },"outputs": [],"source": ["query_vector = embedding.embed_query(query)\n",@@ -309,7 +321,9 @@},{"cell_type": "markdown",- "metadata": {},+ "metadata": {+ "id": "20cf6074081b"+ },"source": ["### Search for documents with metadata filter"]@@ -317,7 +331,9 @@{"cell_type": "code","execution_count": null,- "metadata": {},+ "metadata": {+ "id": "5062f853c455"+ },"outputs": [],"source": ["# This should only return \"Banana\" document.\n",@@ -327,26 +343,83 @@},{"cell_type": "markdown",- "metadata": {},+ "metadata": {+ "id": "b0308d680ee4"+ },"source": [- "### Explore job satistics with BigQuery Job Id"+ "### Batch search\n",+ "BigQueryVectorStore offers a `batch_search` method for scalable Vector similarity search.\n"]},{"cell_type": "code","execution_count": null,- "metadata": {},+ "metadata": {+ "id": "2790964dbc41"+ },+ "outputs": [],+ "source": [+ "results = store.batch_search(\n",+ " embeddings=None, # can pass embeddings or\n",+ " queries=[\"search_query\", \"search_query\"], # can pass queries\n",+ ")"+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {+ "id": "266a68de0e06"+ },+ "source": [+ "### Add text with embeddings\n",+ "\n",+ "You can also bring your own embeddings with the `add_texts_with_embeddings` method.\n",+ "This is particularly useful for multimodal data which might require custom preprocessing before the embedding generation."+ ]+ },+ {+ "cell_type": "code",+ "execution_count": null,+ "metadata": {+ "id": "1b9e2f593813"+ },+ "outputs": [],+ "source": [+ "items = [\"some text\"]\n",+ "embs = embedding.embed(items)\n",+ "\n",+ "ids = store.add_texts_with_embeddings(\n",+ " texts=[\"some text\"], embs=embs, metadatas=[{\"len\": 1}]\n",+ ")"+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {+ "id": "f6867d68e057"+ },+ "source": [+ "### Low-latency serving with Feature Store\n",+ "You can simply use the method `.to_vertex_fs_vector_store()` to get a VertexFSVectorStore object, which offers low latency for online use cases. All mandatory parameters will be automatically transferred from the existing BigQueryVectorStore class. See the [class definition](https://github.com/langchain-ai/langchain-google/blob/main/libs/community/langchain_google_community/bq_storage_vectorstores/featurestore.py#L33) for all the other parameters you can use.\n",+ "\n",+ "Moving back to BigQueryVectorStore is equivalently easy with the `.to_bq_vector_store()` method."+ ]+ },+ {+ "cell_type": "code",+ "execution_count": null,+ "metadata": {+ "id": "1d2d3f17dfde"+ },"outputs": [],"source": [- "job_id = \"\" # @param {type:\"string\"}\n",- "# Debug and explore the job statistics with a BigQuery Job id.\n",- "store.explore_job_stats(job_id)"+ "store.to_vertex_fs_vector_store() # pass optional VertexFSVectorStore parameters as arguments"]}],"metadata": {"colab": {- "provenance": [],+ "name": "google_bigquery_vector_search.ipynb","toc_visible": true},"kernelspec": {@@ -364,7 +437,7 @@"name": "python","nbconvert_exporter": "python","pygments_lexer": "ipython3",- "version": "3.10.12"+ "version": "3.10.9"}},"nbformat": 4,diff --git a/docs/docs/integrations/vectorstores/google_vertex_ai_feature_store.ipynb b/docs/docs/integrations/vectorstores/google_vertex_ai_feature_store.ipynbnew file mode 100644index 0000000000..905a71f47c--- /dev/null+++ b/docs/docs/integrations/vectorstores/google_vertex_ai_feature_store.ipynb@@ -0,0 +1,459 @@+{+ "cells": [+ {+ "cell_type": "markdown",+ "metadata": {+ "id": "E_RJy7C1bpCT"+ },+ "source": [+ "# Google Vertex AI Feature Store\n",+ "\n",+ "> [Google Cloud Vertex Feature Store](https://cloud.google.com/vertex-ai/docs/featurestore/latest/overview) streamlines your ML feature management and online serving processes by letting you serve at low-latency your data in [Google Cloud BigQuery](https://cloud.google.com/bigquery?hl=en), including the capacity to perform approximate neighbor retrieval for embeddings\n",+ "\n",+ "\n",+ "This tutorial shows you how to easily perform low-latency vector search and approximate nearest neighbor retrieval directly from your BigQuery data, enabling powerful ML applications with minimal setup. We will do that using the `VertexFSVectorStore` class. \n",+ "\n",+ "This class is part of a set of 2 classes capable of providing a unified data storage and flexible vector search in Google Cloud:\n",+ "- **BigQuery Vector Search**: with `BigQueryVectorStore` class, which is ideal for rapid prototyping with no infrastructure setup and batch retrieval.\n",+ "- **Feature Store Online Store**: with `VertexFSVectorStore` class, enables low-latency retrieval with manual or scheduled data sync. Perfect for production-ready user-facing GenAI applications.\n"+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {+ "id": "25a003cd4edc"+ },+ "source": [+ ""+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {+ "id": "EmPJkpOCckyh"+ },+ "source": [+ "## Getting started\n"+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {+ "id": "IR54BmgvdHT_"+ },+ "source": [+ "### Install the library"+ ]+ },+ {+ "cell_type": "code",+ "execution_count": null,+ "metadata": {+ "id": "0ZITIDE160OD"+ },+ "outputs": [],+ "source": [+ "%pip install --upgrade --quiet langchain langchain-google-vertexai \"langchain-google-community[featurestore]\""+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {+ "id": "v40bB_GMcr9f"+ },+ "source": [+ "To use the newly installed packages in this Jupyter runtime, you must restart the runtime. You can do this by running the cell below, which restarts the current kernel."+ ]+ },+ {+ "cell_type": "code",+ "execution_count": null,+ "metadata": {+ "id": "6o0iGVIdDD6K"+ },+ "outputs": [],+ "source": [+ "import IPython\n",+ "\n",+ "app = IPython.Application.instance()\n",+ "app.kernel.do_shutdown(True)"+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {+ "id": "be453ee45565"+ },+ "source": [+ "## Before you begin"+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {+ "id": "fb8ebc778a77"+ },+ "source": [+ "#### Set your project ID\n",+ "\n",+ "If you don't know your project ID, try the following:\n",+ "* Run `gcloud config list`.\n",+ "* Run `gcloud projects list`.\n",+ "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)."+ ]+ },+ {+ "cell_type": "code",+ "execution_count": null,+ "metadata": {+ "id": "3f00771c2519"+ },+ "outputs": [],+ "source": [+ "PROJECT_ID = \"\" # @param {type:\"string\"}\n",+ "\n",+ "# Set the project id\n",+ "! gcloud config set project {PROJECT_ID}"+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {+ "id": "0c8db9870db1"+ },+ "source": [+ "#### Set the region\n",+ "\n",+ "You can also change the `REGION` variable used by BigQuery. Learn more about [BigQuery regions](https://cloud.google.com/bigquery/docs/locations#supported_locations)."+ ]+ },+ {+ "cell_type": "code",+ "execution_count": null,+ "metadata": {+ "id": "afbc16ea31fc"+ },+ "outputs": [],+ "source": [+ "REGION = \"us-central1\" # @param {type: \"string\"}"+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {+ "id": "1af54eb03565"+ },+ "source": [+ "#### Set the dataset and table names\n",+ "\n",+ "They will be your BigQuery Vector Store."+ ]+ },+ {+ "cell_type": "code",+ "execution_count": null,+ "metadata": {+ "id": "259862ba68b1"+ },+ "outputs": [],+ "source": [+ "DATASET = \"my_langchain_dataset\" # @param {type: \"string\"}\n",+ "TABLE = \"doc_and_vectors\" # @param {type: \"string\"}"+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {+ "id": "445325c9b3bb"+ },+ "source": [+ "### Authenticating your notebook environment\n",+ "\n",+ "- If you are using **Colab** to run this notebook, uncomment the cell below and continue.\n",+ "- If you are using **Vertex AI Workbench**, check out the setup instructions [here](https://github.com/GoogleCloudPlatform/generative-ai/tree/main/setup-env)."+ ]+ },+ {+ "cell_type": "code",+ "execution_count": null,+ "metadata": {+ "id": "d9ff48bb5b3c"+ },+ "outputs": [],+ "source": [+ "# from google.colab import auth as google_auth\n",+ "\n",+ "# google_auth.authenticate_user()"+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {+ "id": "AD3yG49BdLlr"+ },+ "source": [+ "## Demo: VertexFSVectorStore"+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {+ "id": "7b62754dfe6b"+ },+ "source": [+ "### Create an embedding class instance\n",+ "\n",+ "You may need to enable Vertex AI API in your project by running\n",+ "`gcloud services enable aiplatform.googleapis.com --project {PROJECT_ID}`\n",+ "(replace `{PROJECT_ID}` with the name of your project).\n",+ "\n",+ "You can use any [LangChain embeddings model](/docs/integrations/text_embedding/)."+ ]+ },+ {+ "cell_type": "code",+ "execution_count": null,+ "metadata": {+ "id": "Vb2RJocV9_LQ"+ },+ "outputs": [],+ "source": [+ "from langchain_google_vertexai import VertexAIEmbeddings\n",+ "\n",+ "embedding = VertexAIEmbeddings(\n",+ " model_name=\"textembedding-gecko@latest\", project=PROJECT_ID\n",+ ")"+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {+ "id": "ee602c76f7e6"+ },+ "source": [+ "### Initialize VertexFSVectorStore\n",+ "\n",+ "BigQuery Dataset and Table will be automatically created if they do not exist. See class definition [here](https://github.com/langchain-ai/langchain-google/blob/main/libs/community/langchain_google_community/bq_storage_vectorstores/featurestore.py#L33) for all optional paremeters."+ ]+ },+ {+ "cell_type": "code",+ "execution_count": null,+ "metadata": {+ "id": "9db48a734ad8"+ },+ "outputs": [],+ "source": [+ "from langchain_google_community import VertexFSVectorStore\n",+ "\n",+ "store = VertexFSVectorStore(\n",+ " project_id=PROJECT_ID,\n",+ " dataset_name=DATASET,\n",+ " table_name=TABLE,\n",+ " location=REGION,\n",+ " embedding=embedding,\n",+ ")"+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {+ "id": "0017a81d6a85"+ },+ "source": [+ "### Add texts\n",+ "\n",+ "> Note: The first synchronization process will take around ~20 minutes because of Feature Online Store creation."+ ]+ },+ {+ "cell_type": "code",+ "execution_count": null,+ "metadata": {+ "id": "ebe4f493008b"+ },+ "outputs": [],+ "source": [+ "all_texts = [\"Apples and oranges\", \"Cars and airplanes\", \"Pineapple\", \"Train\", \"Banana\"]\n",+ "metadatas = [{\"len\": len(t)} for t in all_texts]\n",+ "\n",+ "store.add_texts(all_texts, metadatas=metadatas)"+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {+ "id": "524cf1357bf3"+ },+ "source": [+ "You can also start a sync on demand by executing the `sync_data` method."+ ]+ },+ {+ "cell_type": "code",+ "execution_count": null,+ "metadata": {+ "id": "a8126ade72c1"+ },+ "outputs": [],+ "source": [+ "store.sync_data()"+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {+ "id": "3ddb1e1a5083"+ },+ "source": [+ "When in a production environment, you can also use `cron_schedule` class parameter to setup an automatic scheduled synchronization. \n",+ "For example:\n",+ "```python\n",+ "store = VertexFSVectorStore(cron_schedule=\"TZ=America/Los_Angeles 00 13 11 8 *\", ...)\n",+ "```"+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {+ "id": "42d2e7e6a71d"+ },+ "source": [+ "### Search for documents"+ ]+ },+ {+ "cell_type": "code",+ "execution_count": null,+ "metadata": {+ "id": "54785b0aa3e2"+ },+ "outputs": [],+ "source": [+ "query = \"I'd like a fruit.\"\n",+ "docs = store.similarity_search(query)\n",+ "print(docs)"+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {+ "id": "bfcdbc4d3e01"+ },+ "source": [+ "### Search for documents by vector"+ ]+ },+ {+ "cell_type": "code",+ "execution_count": null,+ "metadata": {+ "id": "3d0749a5919f"+ },+ "outputs": [],+ "source": [+ "query_vector = embedding.embed_query(query)\n",+ "docs = store.similarity_search_by_vector(query_vector, k=2)\n",+ "print(docs)"+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {+ "id": "40ae268fe9f0"+ },+ "source": [+ "### Search for documents with metadata filter"+ ]+ },+ {+ "cell_type": "code",+ "execution_count": null,+ "metadata": {+ "id": "8f65b86ada37"+ },+ "outputs": [],+ "source": [+ "# This should only return \"Banana\" document.\n",+ "docs = store.similarity_search_by_vector(query_vector, filter={\"len\": 6})\n",+ "print(docs)"+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {+ "id": "0fc8bfef534e"+ },+ "source": [+ "### Add text with embeddings\n",+ "\n",+ "You can also bring your own embeddings with the`add_texts_with_embeddings` method.\n",+ "This is particularly useful for multimodal data which might require custom preprocessing before the embedding generation."+ ]+ },+ {+ "cell_type": "code",+ "execution_count": null,+ "metadata": {+ "id": "fa2f749e91d2"+ },+ "outputs": [],+ "source": [+ "items = [\"some text\"]\n",+ "embs = embedding.embed(items)\n",+ "\n",+ "ids = store.add_texts_with_embeddings(\n",+ " texts=[\"some text\"], embs=embs, metadatas=[{\"len\": 1}]\n",+ ")"+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {+ "id": "82a5d2842835"+ },+ "source": [+ "### Batch serving with BigQuery\n",+ "You can simply use the method `.to_bq_vector_store()` to get a BigQueryVectorStore object, which offers optimized performances for batch use cases. All mandatory parameters will be automatically transferred from the existing class. See the [class definition](https://github.com/langchain-ai/langchain-google/blob/main/libs/community/langchain_google_community/bq_storage_vectorstores/bigquery.py#L26) for all the parameters you can use.\n",+ "\n",+ "Moving back to BigQueryVectorStore is equivalently easy with the `.to_vertex_fs_vector_store()` method."+ ]+ },+ {+ "cell_type": "code",+ "execution_count": null,+ "metadata": {+ "id": "2d7997776d40"+ },+ "outputs": [],+ "source": [+ "store.to_bq_vector_store() # pass optional VertexFSVectorStore parameters as arguments"+ ]+ }+ ],+ "metadata": {+ "colab": {+ "name": "google_vertex_ai_feature_store.ipynb",+ "toc_visible": true+ },+ "kernelspec": {+ "display_name": "Python 3 (ipykernel)",+ "language": "python",+ "name": "python3"+ },+ "language_info": {+ "codemirror_mode": {+ "name": "ipython",+ "version": 3+ },+ "file_extension": ".py",+ "mimetype": "text/x-python",+ "name": "python",+ "nbconvert_exporter": "python",+ "pygments_lexer": "ipython3",+ "version": "3.10.9"+ }+ },+ "nbformat": 4,+ "nbformat_minor": 4+}