Google AlloyDB for PostgreSQL - `AlloyDBChatStore`

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 chat history with AlloyDBChatStore class.

Learn more about the package on GitHub.

Before you begin

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

• Create a Google Cloud Project
• Enable the AlloyDB API
• Create a AlloyDB cluster and instance.
• Create a AlloyDB database.
• Add a User to the database.

🦙 Library Installation

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)

🔐 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

auth.authenticate_user()

☁ 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:

• 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 Usage

Set AlloyDB database values

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 = "chat_store"  # @param {type: "string"}
VECTOR_STORE_TABLE_NAME = "vector_store"  # @param {type: "string"}
USER = "postgres"  # @param {type: "string"}
PASSWORD = "my-password"  # @param {type: "string"}

AlloyDBEngine Connection Pool

One of the requirements and arguments to establish AlloyDB as a chat 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:

1. project_id : Project ID of the Google Cloud Project where the AlloyDB instance is located.
2. region : Region where the AlloyDB instance is located.
3. cluster: The name of the AlloyDB cluster.
4. instance : The name of the AlloyDB instance.
5. 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 login
• password : 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 Omni

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 table

The AlloyDBChatStore class requires a database table. The AlloyDBEngine engine has a helper method ainit_chat_store_table() that can be used to create a table with the proper schema for you.

await engine.ainit_chat_store_table(table_name=TABLE_NAME)

Optional Tip: 💡

You can also specify a schema name by passing schema_name wherever you pass table_name.

SCHEMA_NAME = "my_schema"

await engine.ainit_chat_store_table(
    table_name=TABLE_NAME,
    schema_name=SCHEMA_NAME,
)

Initialize a default AlloyDBChatStore

from llama_index_alloydb_pg import AlloyDBChatStore

chat_store = await AlloyDBChatStore.create(
    engine=engine,
    table_name=TABLE_NAME,
    # schema_name=SCHEMA_NAME
)

Create a ChatMemoryBuffer

from llama_index.core.memory import ChatMemoryBuffer

memory = ChatMemoryBuffer.from_defaults(
    token_limit=3000,
    chat_store=chat_store,
    chat_store_key="user1",
)

Create an LLM class instance

You can use any of the LLMs compatible with LlamaIndex. You may need to enable Vertex AI API to use Vertex.

from llama_index.llms.vertex import Vertex

llm = Vertex(model="gemini-1.5-flash-002", project=PROJECT_ID)

Use the AlloyDBChatStore without a storage context

Create and use the Chat Engine

from llama_index.core.chat_engine import SimpleChatEngine

chat_engine = SimpleChatEngine(memory=memory, llm=llm, prefix_messages=[])

response = chat_engine.chat("Hello.")

print(response)

Use the AlloyDBChatStore with a storage context

Create an AlloyDBVectorStore instance

Find a detailed guide on how to use the AlloyDBVectorStore here.

You can also use the AlloyDBDocumentStore and AlloyDBIndexStore to persist documents and index metadata. For a detailed python notebook on this, see LlamaIndex Doc Store Guide

from llama_index_alloydb_pg import AlloyDBVectorStore

await engine.ainit_vector_store_table(
    table_name=VECTOR_STORE_TABLE_NAME,
    vector_size=768,  # Vector size for VertexAI model(textembedding-gecko@latest)
)

vector_store = await AlloyDBVectorStore.create(
    engine=engine,
    table_name=VECTOR_STORE_TABLE_NAME,
)

Create an embedding class instance

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

# enable Vertex AI API
!gcloud services enable aiplatform.googleapis.com

from llama_index.core import Settings
from llama_index.embeddings.vertex import VertexTextEmbedding
from llama_index.llms.vertex import Vertex
import google.auth

credentials, project_id = google.auth.default()
Settings.embed_model = VertexTextEmbedding(
    model_name="textembedding-gecko@003",
    project=PROJECT_ID,
    credentials=credentials,
)

Settings.llm = Vertex(model="gemini-1.5-flash-002", project=PROJECT_ID)

Download and load sample data

!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'

from llama_index.core import SimpleDirectoryReader

documents = SimpleDirectoryReader("./data/paul_graham").load_data()
print("Document ID:", documents[0].doc_id)

Create a VectorStoreIndex with a storage context

from llama_index.core import StorageContext, VectorStoreIndex

storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(
    documents, storage_context=storage_context, show_progress=True
)

Create and use the Chat Engine

chat_engine = index.as_chat_engine(llm=llm, chat_mode="context", memory=memory)
response = chat_engine.chat("What did the author do?")