Google AlloyDB for PostgreSQL - AlloyDBDocumentStore
& AlloyDBIndexStore
Ā¶
AlloyDB is a fully managed relational database service that offers high performance, seamless integration, and impressive scalability. AlloyDB is 100% compatible with PostgreSQL. Extend your database application to build AI-powered experiences leveraging AlloyDB's LlamaIndex integrations.
This notebook goes over how to use AlloyDB for PostgreSQL
to store documents and indexes with the AlloyDBDocumentStore
and AlloyDBIndexStore
classes.
Learn more about the package on GitHub.
Before you beginĀ¶
To run this notebook, you will need to do the following:
š¦ Library InstallationĀ¶
Install the integration library, llama-index-alloydb-pg
, and the library for the embedding service, llama-index-embeddings-vertex
.
%pip install --upgrade --quiet llama-index-alloydb-pg llama-index-llms-vertex llama-index
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)
from google.colab import auth
auth.authenticate_user()
ā Set Your Google Cloud ProjectĀ¶
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:
- Run
gcloud config list
. - Run
gcloud projects list
. - See the support page: Locate the project ID.
# @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}
Basic UsageĀ¶
Set AlloyDB database valuesĀ¶
Find your database values, in the AlloyDB Instances page.
# @title Set Your Values Here { display-mode: "form" }
REGION = "us-central1" # @param {type: "string"}
CLUSTER = "my-cluster" # @param {type: "string"}
INSTANCE = "my-primary" # @param {type: "string"}
DATABASE = "my-database" # @param {type: "string"}
TABLE_NAME = "document_store" # @param {type: "string"}
USER = "postgres" # @param {type: "string"}
PASSWORD = "my-password" # @param {type: "string"}
AlloyDBEngine Connection PoolĀ¶
One of the requirements and arguments to establish AlloyDB as a document store is a AlloyDBEngine
object. The AlloyDBEngine
configures a connection pool to your AlloyDB database, enabling successful connections from your application and following industry best practices.
To create a AlloyDBEngine
using AlloyDBEngine.from_instance()
you need to provide only 5 things:
project_id
: Project ID of the Google Cloud Project where the AlloyDB instance is located.region
: Region where the AlloyDB instance is located.cluster
: The name of the AlloyDB cluster.instance
: The name of the AlloyDB instance.database
: The name of the database to connect to on the AlloyDB instance.
By default, IAM database authentication will be used as the method of database authentication. This library uses the IAM principal belonging to the Application Default Credentials (ADC) sourced from the environment.
Optionally, built-in database authentication using a username and password to access the AlloyDB database can also be used. Just provide the optional user
and password
arguments to AlloyDBEngine.from_instance()
:
user
: Database user to use for built-in database authentication and loginpassword
: Database password to use for built-in database authentication and login.
Note: This tutorial demonstrates the async interface. All async methods have corresponding sync methods.
from llama_index_alloydb_pg import AlloyDBEngine
engine = await AlloyDBEngine.afrom_instance(
project_id=PROJECT_ID,
region=REGION,
cluster=CLUSTER,
instance=INSTANCE,
database=DATABASE,
user=USER,
password=PASSWORD,
)
AlloyDBEngine for AlloyDB OmniĀ¶
To create an AlloyDBEngine
for AlloyDB Omni, you will need a connection url. AlloyDBEngine.from_connection_string
first creates an async engine and then turns it into an AlloyDBEngine
. Here is an example connection with the asyncpg
driver:
# Replace with your own AlloyDB Omni info
OMNI_USER = "my-omni-user"
OMNI_PASSWORD = ""
OMNI_HOST = "127.0.0.1"
OMNI_PORT = "5432"
OMNI_DATABASE = "my-omni-db"
connstring = f"postgresql+asyncpg://{OMNI_USER}:{OMNI_PASSWORD}@{OMNI_HOST}:{OMNI_PORT}/{OMNI_DATABASE}"
engine = AlloyDBEngine.from_connection_string(connstring)
Initialize a tableĀ¶
The AlloyDBDocumentStore
class requires a database table. The AlloyDBEngine
engine has a helper method init_doc_store_table()
that can be used to create a table with the proper schema for you.
await engine.ainit_doc_store_table(
table_name=TABLE_NAME,
)
Optional Tip: š”Ā¶
You can also specify a schema name by passing schema_name
wherever you pass table_name
.
SCHEMA_NAME = "my_schema"
await engine.ainit_doc_store_table(
table_name=TABLE_NAME,
schema_name=SCHEMA_NAME,
)
Initialize a default AlloyDBDocumentStoreĀ¶
from llama_index_alloydb_pg import AlloyDBDocumentStore
doc_store = await AlloyDBDocumentStore.create(
engine=engine,
table_name=TABLE_NAME,
# schema_name=SCHEMA_NAME
)
Download dataĀ¶
!mkdir -p 'data/paul_graham/'
!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'
Load documentsĀ¶
from llama_index.core import SimpleDirectoryReader
documents = SimpleDirectoryReader("./data/paul_graham").load_data()
print("Document ID:", documents[0].doc_id)
Parse into nodesĀ¶
from llama_index.core.node_parser import SentenceSplitter
nodes = SentenceSplitter().get_nodes_from_documents(documents)
Set up an IndexStoreĀ¶
from llama_index_alloydb_pg import AlloyDBIndexStore
INDEX_TABLE_NAME = "index_store"
await engine.ainit_index_store_table(
table_name=INDEX_TABLE_NAME,
)
index_store = await AlloyDBIndexStore.create(
engine=engine,
table_name=INDEX_TABLE_NAME,
# schema_name=SCHEMA_NAME
)
Add to DocstoreĀ¶
from llama_index.core import StorageContext
storage_context = StorageContext.from_defaults(
docstore=doc_store, index_store=index_store
)
storage_context.docstore.add_documents(nodes)
Use with IndexesĀ¶
The Document Store can be used with multiple indexes. Each index uses the same underlying nodes.
from llama_index.core import Settings, SimpleKeywordTableIndex, SummaryIndex
from llama_index.llms.vertex import Vertex
Settings.llm = Vertex(model="gemini-1.5-flash", project=PROJECT_ID)
summary_index = SummaryIndex(nodes, storage_context=storage_context)
keyword_table_index = SimpleKeywordTableIndex(
nodes, storage_context=storage_context
)
Query the indexĀ¶
query_engine = summary_index.as_query_engine()
response = query_engine.query("What did the author do?")
print(response)
Load existing indexesĀ¶
The Document Store can be used with multiple indexes. Each index uses the same underlying nodes.
# note down index IDs
list_id = summary_index.index_id
keyword_id = keyword_table_index.index_id
from llama_index.core import load_index_from_storage
# re-create storage context
storage_context = StorageContext.from_defaults(
docstore=doc_store, index_store=index_store
)
# load indices
summary_index = load_index_from_storage(
storage_context=storage_context, index_id=list_id
)
keyword_table_index = load_index_from_storage(
storage_context=storage_context, index_id=keyword_id
)