mirror of https://github.com/hwchase17/langchain
docs: update Google Cloud database integration docs (#18711)
**Description:** update Google Cloud database integration docs **Issue:** NA **Dependencies:** NApull/18774/head
Averi Kitsch
4 months ago
committed by
GitHub
parent
010a234f1e
commit
8accee57a9
@ -1,382 +1,362 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "E_RJy7C1bpCT"
|
||||
},
|
||||
"source": [
|
||||
"# Google Cloud SQL for PostgreSQL\n",
|
||||
"\n",
|
||||
"> [Cloud SQL for PostgreSQL](https://cloud.google.com/sql/docs/postgres) is a fully-managed database service that helps you set up, maintain, manage, and administer your PostgreSQL relational databases on Google Cloud Platform. Extend your database application to build AI-powered experiences leveraging Cloud SQL for PostgreSQL's Langchain integrations.\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use `Cloud SQL for PostgreSQL` to load Documents with the `PostgreSQLLoader` class."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "xjcxaw6--Xyy"
|
||||
},
|
||||
"source": [
|
||||
"## Before you begin\n",
|
||||
"\n",
|
||||
"To run this notebook, you will need to do the following:\n",
|
||||
"\n",
|
||||
" * [Create a Google Cloud Project](https://developers.google.com/workspace/guides/create-project)\n",
|
||||
" * [Enable the Cloud SQL Admin API.](https://console.cloud.google.com/marketplace/product/google/sqladmin.googleapis.com)\n",
|
||||
" * [Create a Cloud SQL for PostgreSQL instance.](https://cloud.google.com/sql/docs/postgres/create-instance)\n",
|
||||
" * [Create a Cloud SQL for PostgreSQL database.](https://cloud.google.com/sql/docs/postgres/create-manage-databases)\n",
|
||||
" * [Add a User to the database.](https://cloud.google.com/sql/docs/postgres/create-manage-users)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "IR54BmgvdHT_"
|
||||
},
|
||||
"source": [
|
||||
"### 🦜🔗 Library Installation\n",
|
||||
"Install the integration library, `langchain-google-cloud-sql-pg`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/",
|
||||
"height": 1000
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "E_RJy7C1bpCT"
|
||||
},
|
||||
"source": [
|
||||
"# Google Cloud SQL for PostgreSQL\n",
|
||||
"\n",
|
||||
"> [Cloud SQL for PostgreSQL](https://cloud.google.com/sql/docs/postgres) is a fully-managed database service that helps you set up, maintain, manage, and administer your PostgreSQL relational databases on Google Cloud Platform. Extend your database application to build AI-powered experiences leveraging Cloud SQL for PostgreSQL's Langchain integrations.\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use `Cloud SQL for PostgreSQL` to load Documents with the `PostgresLoader` class.\n",
|
||||
"\n",
|
||||
"Learn more about the package on [GitHub](https://github.com/googleapis/langchain-google-cloud-sql-pg-python/).\n",
|
||||
"\n",
|
||||
"[](https://colab.research.google.com/github/googleapis/langchain-google-cloud-sql-pg-python/blob/main/docs/document_loader.ipynb)"
|
||||
]
|
||||
},
|
||||
"id": "0ZITIDE160OD",
|
||||
"outputId": "90e0636e-ff34-4e1e-ad37-d2a6db4a317e"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%pip install --upgrade --quiet langchain-google-cloud-sql-pg"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"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."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "6o0iGVIdDD6K"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# # Automatically restart kernel after installs so that your environment can access the new packages\n",
|
||||
"# import IPython\n",
|
||||
"\n",
|
||||
"# app = IPython.Application.instance()\n",
|
||||
"# app.kernel.do_shutdown(True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "cTXTbj4UltKf"
|
||||
},
|
||||
"source": [
|
||||
"### 🔐 Authentication\n",
|
||||
"Authenticate to Google Cloud as the IAM user logged into this notebook in order to access your Google Cloud Project.\n",
|
||||
"\n",
|
||||
"* If you are using Colab to run this notebook, use 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": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from google.colab import auth\n",
|
||||
"\n",
|
||||
"auth.authenticate_user()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "Uj02bMRAc9_c"
|
||||
},
|
||||
"source": [
|
||||
"### ☁ Set Your Google Cloud Project\n",
|
||||
"Set your Google Cloud project so that you can leverage Google Cloud resources within this notebook.\n",
|
||||
"\n",
|
||||
"If you don't know your project ID, try the following:\n",
|
||||
"\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": {
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "xjcxaw6--Xyy"
|
||||
},
|
||||
"source": [
|
||||
"## Before you begin\n",
|
||||
"\n",
|
||||
"To run this notebook, you will need to do the following:\n",
|
||||
"\n",
|
||||
" * [Create a Google Cloud Project](https://developers.google.com/workspace/guides/create-project)\n",
|
||||
" * [Enable the Cloud SQL Admin API.](https://console.cloud.google.com/marketplace/product/google/sqladmin.googleapis.com)\n",
|
||||
" * [Create a Cloud SQL for PostgreSQL instance.](https://cloud.google.com/sql/docs/postgres/create-instance)\n",
|
||||
" * [Create a Cloud SQL for PostgreSQL database.](https://cloud.google.com/sql/docs/postgres/create-manage-databases)\n",
|
||||
" * [Add a User to the database.](https://cloud.google.com/sql/docs/postgres/create-manage-users)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "IR54BmgvdHT_"
|
||||
},
|
||||
"source": [
|
||||
"### 🦜🔗 Library Installation\n",
|
||||
"Install the integration library, `langchain_google_cloud_sql_pg`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/",
|
||||
"height": 1000
|
||||
},
|
||||
"id": "0ZITIDE160OD",
|
||||
"outputId": "90e0636e-ff34-4e1e-ad37-d2a6db4a317e"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%pip install --upgrade --quiet langchain_google_cloud_sql_pg"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"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."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "6o0iGVIdDD6K"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# # Automatically restart kernel after installs so that your environment can access the new packages\n",
|
||||
"# import IPython\n",
|
||||
"\n",
|
||||
"# app = IPython.Application.instance()\n",
|
||||
"# app.kernel.do_shutdown(True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "cTXTbj4UltKf"
|
||||
},
|
||||
"source": [
|
||||
"### 🔐 Authentication\n",
|
||||
"Authenticate to Google Cloud as the IAM user logged into this notebook in order to access your Google Cloud Project.\n",
|
||||
"\n",
|
||||
"* If you are using Colab to run this notebook, use 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": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from google.colab import auth\n",
|
||||
"\n",
|
||||
"auth.authenticate_user()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "Uj02bMRAc9_c"
|
||||
},
|
||||
"source": [
|
||||
"### ☁ Set Your Google Cloud Project\n",
|
||||
"Set your Google Cloud project so that you can leverage Google Cloud resources within this notebook.\n",
|
||||
"\n",
|
||||
"If you don't know your project ID, try the following:\n",
|
||||
"\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": {
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/"
|
||||
},
|
||||
"id": "wnp1R1PYc9_c",
|
||||
"outputId": "6502c721-a2fd-451f-b946-9f7b850d5966"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title Project { display-mode: \"form\" }\n",
|
||||
"PROJECT_ID = \"gcp_project_id\" # @param {type:\"string\"}\n",
|
||||
"\n",
|
||||
"# Set the project id\n",
|
||||
"! gcloud config set project {PROJECT_ID}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f8f2830ee9ca1e01",
|
||||
"metadata": {
|
||||
"id": "f8f2830ee9ca1e01"
|
||||
},
|
||||
"source": [
|
||||
"## Basic Usage"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "OMvzMWRrR6n7",
|
||||
"metadata": {
|
||||
"id": "OMvzMWRrR6n7"
|
||||
},
|
||||
"source": [
|
||||
"### Set Cloud SQL database values\n",
|
||||
"Find your database variables, in the [Cloud SQL Instances page](https://console.cloud.google.com/sql/instances)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "irl7eMFnSPZr",
|
||||
"metadata": {
|
||||
"id": "irl7eMFnSPZr"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title Set Your Values Here { display-mode: \"form\" }\n",
|
||||
"REGION = \"us-central1\" # @param {type: \"string\"}\n",
|
||||
"INSTANCE = \"my-primary\" # @param {type: \"string\"}\n",
|
||||
"DATABASE = \"my-database\" # @param {type: \"string\"}\n",
|
||||
"TABLE_NAME = \"vector_store\" # @param {type: \"string\"}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "QuQigs4UoFQ2",
|
||||
"metadata": {
|
||||
"id": "QuQigs4UoFQ2"
|
||||
},
|
||||
"source": [
|
||||
"### Cloud SQL Engine\n",
|
||||
"\n",
|
||||
"One of the requirements and arguments to establish PostgreSQL as a document loader is a `PostgresEngine` object. The `PostgresEngine` configures a connection pool to your Cloud SQL for PostgreSQL database, enabling successful connections from your application and following industry best practices.\n",
|
||||
"\n",
|
||||
"To create a `PostgresEngine` using `PostgresEngine.from_instance()` you need to provide only 4 things:\n",
|
||||
"\n",
|
||||
"1. `project_id` : Project ID of the Google Cloud Project where the Cloud SQL instance is located.\n",
|
||||
"1. `region` : Region where the Cloud SQL instance is located.\n",
|
||||
"1. `instance` : The name of the Cloud SQL instance.\n",
|
||||
"1. `database` : The name of the database to connect to on the Cloud SQL instance.\n",
|
||||
"\n",
|
||||
"By default, [IAM database authentication](https://cloud.google.com/sql/docs/postgres/iam-authentication) will be used as the method of database authentication. This library uses the IAM principal belonging to the [Application Default Credentials (ADC)](https://cloud.google.com/docs/authentication/application-default-credentials) sourced from the environment.\n",
|
||||
"\n",
|
||||
"Optionally, [built-in database authentication](https://cloud.google.com/sql/docs/postgres/users) using a username and password to access the Cloud SQL database can also be used. Just provide the optional `user` and `password` arguments to `PostgresEngine.from_instance()`:\n",
|
||||
"\n",
|
||||
"* `user` : Database user to use for built-in database authentication and login\n",
|
||||
"* `password` : Database password to use for built-in database authentication and login.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**Note**: This tutorial demonstrates the async interface. All async methods have corresponding sync methods."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_google_cloud_sql_pg import PostgresEngine\n",
|
||||
"\n",
|
||||
"engine = await PostgresEngine.afrom_instance(\n",
|
||||
" project_id=PROJECT_ID,\n",
|
||||
" region=REGION,\n",
|
||||
" instance=INSTANCE,\n",
|
||||
" database=DATABASE,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "e1tl0aNx7SWy"
|
||||
},
|
||||
"source": [
|
||||
"### Create PostgresLoader"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "z-AZyzAQ7bsf"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_google_cloud_sql_pg import PostgresLoader\n",
|
||||
"\n",
|
||||
"# Creating a basic PostgreSQL object\n",
|
||||
"loader = await PostgresLoader.create(engine, table_name=TABLE_NAME)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "PeOMpftjc9_e"
|
||||
},
|
||||
"source": [
|
||||
"### Load Documents via default table\n",
|
||||
"The loader returns a list of Documents from the table using the first column as page_content and all other columns as metadata. The default table will have the first column as\n",
|
||||
"page_content and the second column as metadata (JSON). Each row becomes a document. Please note that if you want your documents to have ids you will need to add them in."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "cwvi_O5Wc9_e"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_google_cloud_sql_pg import PostgresLoader\n",
|
||||
"\n",
|
||||
"# Creating a basic PostgresLoader object\n",
|
||||
"loader = await PostgresLoader.create(engine, table_name=TABLE_NAME)\n",
|
||||
"\n",
|
||||
"docs = await loader.aload()\n",
|
||||
"print(docs)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "kSkL9l1Hc9_e"
|
||||
},
|
||||
"source": [
|
||||
"### Load documents via custom table/metadata or custom page content columns"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader = await PostgresLoader.create(\n",
|
||||
" engine,\n",
|
||||
" table_name=TABLE_NAME,\n",
|
||||
" content_columns=[\"product_name\"], # Optional\n",
|
||||
" metadata_columns=[\"id\"], # Optional\n",
|
||||
")\n",
|
||||
"docs = await loader.aload()\n",
|
||||
"print(docs)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "5R6h0_Cvc9_f"
|
||||
},
|
||||
"source": [
|
||||
"### Set page content format\n",
|
||||
"The loader returns a list of Documents, with one document per row, with page content in specified string format, i.e. text (space separated concatenation), JSON, YAML, CSV, etc. JSON and YAML formats include headers, while text and CSV do not include field headers.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "NGNdS7cqc9_f"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader = await PostgresLoader.create(\n",
|
||||
" engine,\n",
|
||||
" table_name=\"products\",\n",
|
||||
" content_columns=[\"product_name\", \"description\"],\n",
|
||||
" format=\"YAML\",\n",
|
||||
")\n",
|
||||
"docs = await loader.aload()\n",
|
||||
"print(docs)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/"
|
||||
"provenance": [],
|
||||
"toc_visible": true
|
||||
},
|
||||
"id": "wnp1R1PYc9_c",
|
||||
"outputId": "6502c721-a2fd-451f-b946-9f7b850d5966"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title Project { display-mode: \"form\" }\n",
|
||||
"PROJECT_ID = \"gcp_project_id\" # @param {type:\"string\"}\n",
|
||||
"\n",
|
||||
"# Set the project id\n",
|
||||
"! gcloud config set project {PROJECT_ID}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "rEWWNoNnKOgq",
|
||||
"metadata": {
|
||||
"id": "rEWWNoNnKOgq"
|
||||
},
|
||||
"source": [
|
||||
"### 💡 API Enablement\n",
|
||||
"The `langchain_google_cloud_sql_pg` package requires that you [enable the Cloud SQL Admin API](https://console.cloud.google.com/flows/enableapi?apiid=sqladmin.googleapis.com) in your Google Cloud Project."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "5utKIdq7KYi5",
|
||||
"metadata": {
|
||||
"id": "5utKIdq7KYi5"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# enable Cloud SQL Admin API\n",
|
||||
"!gcloud services enable sqladmin.googleapis.com"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f8f2830ee9ca1e01",
|
||||
"metadata": {
|
||||
"id": "f8f2830ee9ca1e01"
|
||||
},
|
||||
"source": [
|
||||
"## Basic Usage"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "OMvzMWRrR6n7",
|
||||
"metadata": {
|
||||
"id": "OMvzMWRrR6n7"
|
||||
},
|
||||
"source": [
|
||||
"### Set Cloud SQL database values\n",
|
||||
"Find your database variables, in the [Cloud SQL Instances page](https://console.cloud.google.com/sql/instances)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "irl7eMFnSPZr",
|
||||
"metadata": {
|
||||
"id": "irl7eMFnSPZr"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title Set Your Values Here { display-mode: \"form\" }\n",
|
||||
"REGION = \"us-central1\" # @param {type: \"string\"}\n",
|
||||
"INSTANCE = \"my-primary\" # @param {type: \"string\"}\n",
|
||||
"DATABASE = \"my-database\" # @param {type: \"string\"}\n",
|
||||
"TABLE_NAME = \"vector_store\" # @param {type: \"string\"}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "QuQigs4UoFQ2",
|
||||
"metadata": {
|
||||
"id": "QuQigs4UoFQ2"
|
||||
},
|
||||
"source": [
|
||||
"### Cloud SQL Engine\n",
|
||||
"\n",
|
||||
"One of the requirements and arguments to establish PostgreSQL as a document loader is a `PostgresEngine` object. The `PostgresEngine` configures a connection pool to your Cloud SQL for PostgreSQL database, enabling successful connections from your application and following industry best practices.\n",
|
||||
"\n",
|
||||
"To create a `PostgresEngine` using `PostgresEngine.from_instance()` you need to provide only 4 things:\n",
|
||||
"\n",
|
||||
"1. `project_id` : Project ID of the Google Cloud Project where the Cloud SQL instance is located.\n",
|
||||
"1. `region` : Region where the Cloud SQL instance is located.\n",
|
||||
"1. `instance` : The name of the Cloud SQL instance.\n",
|
||||
"1. `database` : The name of the database to connect to on the Cloud SQL instance.\n",
|
||||
"\n",
|
||||
"By default, [IAM database authentication](https://cloud.google.com/sql/docs/postgres/iam-authentication) will be used as the method of database authentication. This library uses the IAM principal belonging to the [Application Default Credentials (ADC)](https://cloud.google.com/docs/authentication/application-default-credentials) sourced from the environment.\n",
|
||||
"\n",
|
||||
"Optionally, [built-in database authentication](https://cloud.google.com/sql/docs/postgres/users) using a username and password to access the Cloud SQL database can also be used. Just provide the optional `user` and `password` arguments to `PostgresEngine.from_instance()`:\n",
|
||||
"\n",
|
||||
"* `user` : Database user to use for built-in database authentication and login\n",
|
||||
"* `password` : Database password to use for built-in database authentication and login.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**Note**: This tutorial demonstrates the async interface. All async methods have corresponding sync methods."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_google_cloud_sql_pg import PostgresEngine\n",
|
||||
"\n",
|
||||
"engine = await PostgresEngine.afrom_instance(\n",
|
||||
" project_id=PROJECT_ID,\n",
|
||||
" region=REGION,\n",
|
||||
" instance=INSTANCE,\n",
|
||||
" database=DATABASE,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "e1tl0aNx7SWy"
|
||||
},
|
||||
"source": [
|
||||
"### Create PostgresLoader"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "z-AZyzAQ7bsf"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_google_cloud_sql_pg import PostgresLoader\n",
|
||||
"\n",
|
||||
"# Creating a basic PostgreSQL object\n",
|
||||
"loader = await PostgresLoader.create(engine, table_name=TABLE_NAME)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "PeOMpftjc9_e"
|
||||
},
|
||||
"source": [
|
||||
"### Load Documents via default table\n",
|
||||
"The loader returns a list of Documents from the table using the first column as page_content and all other columns as metadata. The default table will have the first column as\n",
|
||||
"page_content and the second column as metadata (JSON). Each row becomes a document. Please note that if you want your documents to have ids you will need to add them in."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "cwvi_O5Wc9_e"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_google_cloud_sql_pg import PostgresLoader\n",
|
||||
"\n",
|
||||
"# Creating a basic PostgresLoader object\n",
|
||||
"loader = await PostgresLoader.create(engine, table_name=TABLE_NAME)\n",
|
||||
"\n",
|
||||
"docs = await loader.aload()\n",
|
||||
"print(docs)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "kSkL9l1Hc9_e"
|
||||
},
|
||||
"source": [
|
||||
"### Load documents via custom table/metadata or custom page content columns"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader = await PostgresLoader.create(\n",
|
||||
" engine,\n",
|
||||
" table_name=TABLE_NAME,\n",
|
||||
" content_columns=[\"product_name\"], # Optional\n",
|
||||
" metadata_columns=[\"id\"], # Optional\n",
|
||||
")\n",
|
||||
"docs = await loader.aload()\n",
|
||||
"print(docs)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "5R6h0_Cvc9_f"
|
||||
},
|
||||
"source": [
|
||||
"### Set page content format\n",
|
||||
"The loader returns a list of Documents, with one document per row, with page content in specified string format, i.e. text (space separated concatenation), JSON, YAML, CSV, etc. JSON and YAML formats include headers, while text and CSV do not include field headers.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "NGNdS7cqc9_f"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader = await PostgresLoader.create(\n",
|
||||
" engine,\n",
|
||||
" table_name=\"products\",\n",
|
||||
" content_columns=[\"product_name\", \"description\"],\n",
|
||||
" format=\"YAML\",\n",
|
||||
")\n",
|
||||
"docs = await loader.aload()\n",
|
||||
"print(docs)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"provenance": [],
|
||||
"toc_visible": true
|
||||
},
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
"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": "3.9.6"
|
||||
}
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.6"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
@ -1,411 +1,336 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Google Firestore in Datastore mode\n",
|
||||
"\n",
|
||||
"> [Firestore in Datastore mode](https://cloud.google.com/datastore) is a serverless document-oriented database that scales to meet any demand. Extend your database application to build AI-powered experiences leveraging Datastore's Langchain integrations.\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use [Firestore in Datastore mode](https://cloud.google.com/datastore) to [save, load and delete langchain documents](https://python.langchain.com/docs/modules/data_connection/document_loaders/) with `DatastoreLoader` and `DatastoreSaver`.\n",
|
||||
"\n",
|
||||
"[](https://colab.research.google.com/github/googleapis/langchain-google-datastore-python/blob/main/docs/document_loader.ipynb)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Before You Begin\n",
|
||||
"\n",
|
||||
"To run this notebook, you will need to do the following:\n",
|
||||
"\n",
|
||||
"* [Create a Google Cloud Project](https://developers.google.com/workspace/guides/create-project)\n",
|
||||
"* [Create a Datastore database](https://cloud.google.com/datastore/docs/manage-databases)\n",
|
||||
"\n",
|
||||
"After confirmed access to database in the runtime environment of this notebook, filling the following values and run the cell before running example scripts."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @markdown Please specify a source for demo purpose.\n",
|
||||
"SOURCE = \"test\" # @param {type:\"Query\"|\"CollectionGroup\"|\"DocumentReference\"|\"string\"}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 🦜🔗 Library Installation\n",
|
||||
"\n",
|
||||
"The integration lives in its own `langchain-google-datastore` package, so we need to install it."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%pip install -upgrade --quiet langchain-google-datastore"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"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."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# # Automatically restart kernel after installs so that your environment can access the new packages\n",
|
||||
"# import IPython\n",
|
||||
"\n",
|
||||
"# app = IPython.Application.instance()\n",
|
||||
"# app.kernel.do_shutdown(True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### ☁ Set Your Google Cloud Project\n",
|
||||
"Set your Google Cloud project so that you can leverage Google Cloud resources within this notebook.\n",
|
||||
"\n",
|
||||
"If you don't know your project ID, try the following:\n",
|
||||
"\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": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @markdown Please fill in the value below with your Google Cloud project ID and then run the cell.\n",
|
||||
"\n",
|
||||
"PROJECT_ID = \"my-project-id\" # @param {type:\"string\"}\n",
|
||||
"\n",
|
||||
"# Set the project id\n",
|
||||
"!gcloud config set project {PROJECT_ID}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 🔐 Authentication\n",
|
||||
"\n",
|
||||
"Authenticate to Google Cloud as the IAM user logged into this notebook in order to access your Google Cloud Project.\n",
|
||||
"\n",
|
||||
"- If you are using Colab to run this notebook, use 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": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from google.colab import auth\n",
|
||||
"\n",
|
||||
"auth.authenticate_user()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### API Enablement\n",
|
||||
"The `langchain-google-datastore` package requires that you [enable the Datastore API](https://console.cloud.google.com/flows/enableapi?apiid=datastore.googleapis.com) in your Google Cloud Project."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# enable Datastore API\n",
|
||||
"!gcloud services enable datastore.googleapis.com"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Basic Usage"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Save documents\n",
|
||||
"\n",
|
||||
"`DatastoreSaver` can store Documents into Datastore. By default it will try to extract the Document reference from the metadata\n",
|
||||
"\n",
|
||||
"Save langchain documents with `DatastoreSaver.upsert_documents(<documents>)`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_core.documents import Document\n",
|
||||
"from langchain_google_datastore import DatastoreSaver\n",
|
||||
"\n",
|
||||
"data = [Document(page_content=\"Hello, World!\")]\n",
|
||||
"saver = DatastoreSaver()\n",
|
||||
"saver.upsert_documents(data)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Save documents without reference\n",
|
||||
"\n",
|
||||
"If a collection is specified the documents will be stored with an auto generated id."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"saver = DatastoreSaver(\"Collection\")\n",
|
||||
"\n",
|
||||
"saver.upsert_documents(data)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Save documents with other references"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"doc_ids = [\"AnotherCollection/doc_id\", \"foo/bar\"]\n",
|
||||
"saver = DatastoreSaver()\n",
|
||||
"\n",
|
||||
"saver.upsert_documents(documents=data, document_ids=doc_ids)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Load from Collection or SubCollection"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Load langchain documents with `DatastoreLoader.load()` or `Datastore.lazy_load()`. `lazy_load` returns a generator that only queries database during the iteration. To initialize `DatastoreLoader` class you need to provide:\n",
|
||||
"\n",
|
||||
"1. `source` - An instance of a Query, CollectionGroup, DocumentReference or the single `\\`-delimited path to a Datastore collection`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_google_datastore import DatastoreLoader\n",
|
||||
"\n",
|
||||
"loader_collection = DatastoreLoader(\"Collection\")\n",
|
||||
"loader_subcollection = DatastoreLoader(\"Collection/doc/SubCollection\")\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"data_collection = loader_collection.load()\n",
|
||||
"data_subcollection = loader_subcollection.load()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Load a single Document"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from google.cloud import datastore\n",
|
||||
"\n",
|
||||
"client = datastore.Client()\n",
|
||||
"doc_ref = client.collection(\"foo\").document(\"bar\")\n",
|
||||
"\n",
|
||||
"loader_document = DatastoreLoader(doc_ref)\n",
|
||||
"\n",
|
||||
"data = loader_document.load()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Load from CollectionGroup or Query"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from google.cloud.datastore import CollectionGroup, FieldFilter, Query\n",
|
||||
"\n",
|
||||
"col_ref = client.collection(\"col_group\")\n",
|
||||
"collection_group = CollectionGroup(col_ref)\n",
|
||||
"\n",
|
||||
"loader_group = DatastoreLoader(collection_group)\n",
|
||||
"\n",
|
||||
"col_ref = client.collection(\"collection\")\n",
|
||||
"query = col_ref.where(filter=FieldFilter(\"region\", \"==\", \"west_coast\"))\n",
|
||||
"\n",
|
||||
"loader_query = DatastoreLoader(query)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Delete documents\n",
|
||||
"\n",
|
||||
"Delete a list of langchain documents from Datastore collection with `DatastoreSaver.delete_documents(<documents>)`.\n",
|
||||
"\n",
|
||||
"If document ids is provided, the Documents will be ignored."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"saver = DatastoreSaver()\n",
|
||||
"\n",
|
||||
"saver.delete_documents(data)\n",
|
||||
"\n",
|
||||
"# The Documents will be ignored and only the document ids will be used.\n",
|
||||
"saver.delete_documents(data, doc_ids)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Advanced Usage"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Load documents with customize document page content & metadata\n",
|
||||
"\n",
|
||||
"The arguments of `page_content_fields` and `metadata_fields` will specify the Datastore Document fields to be written into LangChain Document `page_content` and `metadata`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader = DatastoreLoader(\n",
|
||||
" source=\"foo/bar/subcol\",\n",
|
||||
" page_content_fields=[\"data_field\"],\n",
|
||||
" metadata_fields=[\"metadata_field\"],\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"data = loader.load()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Customize Page Content Format\n",
|
||||
"\n",
|
||||
"When the `page_content` contains only one field the information will be the field value only. Otherwise the `page_content` will be in JSON format."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Customize Connection & Authentication"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from google.auth import compute_engine\n",
|
||||
"from google.cloud.datastore import Client\n",
|
||||
"\n",
|
||||
"client = Client(database=\"non-default-db\", creds=compute_engine.Credentials())\n",
|
||||
"loader = DatastoreLoader(\n",
|
||||
" source=\"foo\",\n",
|
||||
" client=client,\n",
|
||||
")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"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": "3.10.6"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Google Firestore in Datastore Mode\n",
|
||||
"\n",
|
||||
"> [Firestore in Datastore Mode](https://cloud.google.com/datastore) is a NoSQL document database built for automatic scaling, high performance and ease of application development. Extend your database application to build AI-powered experiences leveraging Datastore's Langchain integrations.\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use [Firestore in Datastore Mode](https://cloud.google.com/datastore) to [save, load and delete langchain documents](https://python.langchain.com/docs/modules/data_connection/document_loaders/) with `DatastoreLoader` and `DatastoreSaver`.\n",
|
||||
"\n",
|
||||
"Learn more about the package on [GitHub](https://github.com/googleapis/langchain-google-datastore-python/).\n",
|
||||
"\n",
|
||||
"[](https://colab.research.google.com/github/googleapis/langchain-google-datastore-python/blob/main/docs/document_loader.ipynb)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Before You Begin\n",
|
||||
"\n",
|
||||
"To run this notebook, you will need to do the following:\n",
|
||||
"\n",
|
||||
"* [Create a Google Cloud Project](https://developers.google.com/workspace/guides/create-project)\n",
|
||||
"* [Enable the Datastore API](https://console.cloud.google.com/flows/enableapi?apiid=datastore.googleapis.com)\n",
|
||||
"* [Create a Firestore in Datastore Mode database](https://cloud.google.com/datastore/docs/manage-databases)\n",
|
||||
"\n",
|
||||
"After confirmed access to database in the runtime environment of this notebook, filling the following values and run the cell before running example scripts."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 🦜🔗 Library Installation\n",
|
||||
"\n",
|
||||
"The integration lives in its own `langchain-google-datastore` package, so we need to install it."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%pip install -upgrade --quiet langchain-google-datastore"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"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."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# # Automatically restart kernel after installs so that your environment can access the new packages\n",
|
||||
"# import IPython\n",
|
||||
"\n",
|
||||
"# app = IPython.Application.instance()\n",
|
||||
"# app.kernel.do_shutdown(True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### ☁ Set Your Google Cloud Project\n",
|
||||
"Set your Google Cloud project so that you can leverage Google Cloud resources within this notebook.\n",
|
||||
"\n",
|
||||
"If you don't know your project ID, try the following:\n",
|
||||
"\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": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @markdown Please fill in the value below with your Google Cloud project ID and then run the cell.\n",
|
||||
"\n",
|
||||
"PROJECT_ID = \"my-project-id\" # @param {type:\"string\"}\n",
|
||||
"\n",
|
||||
"# Set the project id\n",
|
||||
"!gcloud config set project {PROJECT_ID}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 🔐 Authentication\n",
|
||||
"\n",
|
||||
"Authenticate to Google Cloud as the IAM user logged into this notebook in order to access your Google Cloud Project.\n",
|
||||
"\n",
|
||||
"- If you are using Colab to run this notebook, use 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": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from google.colab import auth\n",
|
||||
"\n",
|
||||
"auth.authenticate_user()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Basic Usage"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Save documents\n",
|
||||
"\n",
|
||||
"Save langchain documents with `DatastoreSaver.upsert_documents(<documents>)`. By default it will try to extract the entity key from the `key` in the Document metadata."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_core.documents import Document\n",
|
||||
"from langchain_google_datastore import DatastoreSaver\n",
|
||||
"\n",
|
||||
"saver = DatastoreSaver()\n",
|
||||
"\n",
|
||||
"data = [Document(page_content=\"Hello, World!\")]\n",
|
||||
"saver.upsert_documents(data)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Save documents without key\n",
|
||||
"\n",
|
||||
"If a `kind` is specified the documents will be stored with an auto generated id."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"saver = DatastoreSaver(\"MyKind\")\n",
|
||||
"\n",
|
||||
"saver.upsert_documents(data)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Load documents via Kind\n",
|
||||
"\n",
|
||||
"Load langchain documents with `DatastoreLoader.load()` or `DatastoreLoader.lazy_load()`. `lazy_load` returns a generator that only queries database during the iteration. To initialize `DatastoreLoader` class you need to provide:\n",
|
||||
"1. `source` - The source to load the documents. It can be an instance of Query or the name of the Datastore kind to read from."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_google_datastore import DatastoreLoader\n",
|
||||
"\n",
|
||||
"loader = DatastoreLoader(\"MyKind\")\n",
|
||||
"data = loader.load()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Load documents via query\n",
|
||||
"\n",
|
||||
"Other than loading documents from kind, we can also choose to load documents from query. For example:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from google.cloud import datastore\n",
|
||||
"\n",
|
||||
"client = datastore.Client(database=\"non-default-db\", namespace=\"custom_namespace\")\n",
|
||||
"query_load = client.query(kind=\"MyKind\")\n",
|
||||
"query_load.add_filter(\"region\", \"=\", \"west_coast\")\n",
|
||||
"\n",
|
||||
"loader_document = DatastoreLoader(query_load)\n",
|
||||
"\n",
|
||||
"data = loader_document.load()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Delete documents\n",
|
||||
"\n",
|
||||
"Delete a list of langchain documents from Datastore with `DatastoreSaver.delete_documents(<documents>)`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"saver = DatastoreSaver()\n",
|
||||
"\n",
|
||||
"saver.delete_documents(data)\n",
|
||||
"\n",
|
||||
"keys_to_delete = [\n",
|
||||
" [\"Kind1\", \"identifier\"],\n",
|
||||
" [\"Kind2\", 123],\n",
|
||||
" [\"Kind3\", \"identifier\", \"NestedKind\", 456],\n",
|
||||
"]\n",
|
||||
"# The Documents will be ignored and only the document ids will be used.\n",
|
||||
"saver.delete_documents(data, keys_to_delete)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Advanced Usage"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Load documents with customized document page content & metadata\n",
|
||||
"\n",
|
||||
"The arguments of `page_content_properties` and `metadata_properties` will specify the Entity properties to be written into LangChain Document `page_content` and `metadata`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader = DatastoreLoader(\n",
|
||||
" source=\"MyKind\",\n",
|
||||
" page_content_fields=[\"data_field\"],\n",
|
||||
" metadata_fields=[\"metadata_field\"],\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"data = loader.load()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Customize Page Content Format\n",
|
||||
"\n",
|
||||
"When the `page_content` contains only one field the information will be the field value only. Otherwise the `page_content` will be in JSON format."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Customize Connection & Authentication"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from google.auth import compute_engine\n",
|
||||
"from google.cloud.firestore import Client\n",
|
||||
"\n",
|
||||
"client = Client(database=\"non-default-db\", creds=compute_engine.Credentials())\n",
|
||||
"loader = DatastoreLoader(\n",
|
||||
" source=\"foo\",\n",
|
||||
" client=client,\n",
|
||||
")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"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": "3.10.6"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@ -1,259 +1,245 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Google Firestore in Datastore\n",
|
||||
"\n",
|
||||
"> [Firestore in Datastore](https://cloud.google.com/datastore) is a serverless document-oriented database that scales to meet any demand. Extend your database application to build AI-powered experiences leveraging Datastore's Langchain integrations.\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use [Firestore in Datastore](https://cloud.google.com/datastore) to to store chat message history with the `DatastoreChatMessageHistory` class.\n",
|
||||
"\n",
|
||||
"[](https://colab.research.google.com/github/googleapis/langchain-google-datastore-python/blob/main/docs/chat_message_history.ipynb)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Before You Begin\n",
|
||||
"\n",
|
||||
"To run this notebook, you will need to do the following:\n",
|
||||
"\n",
|
||||
"* [Create a Google Cloud Project](https://developers.google.com/workspace/guides/create-project)\n",
|
||||
"* [Create a Datastore database](https://cloud.google.com/datastore/docs/manage-databases)\n",
|
||||
"\n",
|
||||
"After confirmed access to database in the runtime environment of this notebook, filling the following values and run the cell before running example scripts."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 🦜🔗 Library Installation\n",
|
||||
"\n",
|
||||
"The integration lives in its own `langchain-google-datastore` package, so we need to install it."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%pip install -upgrade --quiet langchain-google-datastore"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"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."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# # Automatically restart kernel after installs so that your environment can access the new packages\n",
|
||||
"# import IPython\n",
|
||||
"\n",
|
||||
"# app = IPython.Application.instance()\n",
|
||||
"# app.kernel.do_shutdown(True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### ☁ Set Your Google Cloud Project\n",
|
||||
"Set your Google Cloud project so that you can leverage Google Cloud resources within this notebook.\n",
|
||||
"\n",
|
||||
"If you don't know your project ID, try the following:\n",
|
||||
"\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": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @markdown Please fill in the value below with your Google Cloud project ID and then run the cell.\n",
|
||||
"\n",
|
||||
"PROJECT_ID = \"my-project-id\" # @param {type:\"string\"}\n",
|
||||
"\n",
|
||||
"# Set the project id\n",
|
||||
"!gcloud config set project {PROJECT_ID}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 🔐 Authentication\n",
|
||||
"\n",
|
||||
"Authenticate to Google Cloud as the IAM user logged into this notebook in order to access your Google Cloud Project.\n",
|
||||
"\n",
|
||||
"- If you are using Colab to run this notebook, use 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": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from google.colab import auth\n",
|
||||
"\n",
|
||||
"auth.authenticate_user()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### API Enablement\n",
|
||||
"The `langchain-google-datastore` package requires that you [enable the Datastore API](https://console.cloud.google.com/flows/enableapi?apiid=datastore.googleapis.com) in your Google Cloud Project."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# enable Datastore API\n",
|
||||
"!gcloud services enable datastore.googleapis.com"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Basic Usage"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### DatastoreChatMessageHistory\n",
|
||||
"\n",
|
||||
"To initialize the `DatastoreChatMessageHistory` class you need to provide only 3 things:\n",
|
||||
"\n",
|
||||
"1. `session_id` - A unique identifier string that specifies an id for the session.\n",
|
||||
"1. `collection` : The single `/`-delimited path to a Datastore collection."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_google_datastore import DatastoreChatMessageHistory\n",
|
||||
"\n",
|
||||
"chat_history = DatastoreChatMessageHistory(\n",
|
||||
" session_id=\"user-session-id\", collection=\"HistoryMessages\"\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"chat_history.add_user_message(\"Hi!\")\n",
|
||||
"chat_history.add_ai_message(\"How can I help you?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chat_history.messages"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Cleaning up\n",
|
||||
"When the history of a specific session is obsolete and can be deleted from the database and memory, it can be done the following way.\n",
|
||||
"\n",
|
||||
"**Note:** Once deleted, the data is no longer stored in Datastore and is gone forever."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chat_history.clear()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Custom Client\n",
|
||||
"\n",
|
||||
"The client is created by default using the available environment variables. A [custom client](https://cloud.google.com/python/docs/reference/datastore/latest/client) can be passed to the constructor."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from google.auth import compute_engine\n",
|
||||
"from google.cloud import datastore\n",
|
||||
"\n",
|
||||
"client = datastore.Client(\n",
|
||||
" project=\"project-custom\",\n",
|
||||
" database=\"non-default-database\",\n",
|
||||
" credentials=compute_engine.Credentials(),\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"history = DatastoreChatMessageHistory(\n",
|
||||
" session_id=\"session-id\", collection=\"History\", client=client\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"history.add_user_message(\"New message\")\n",
|
||||
"\n",
|
||||
"history.messages\n",
|
||||
"\n",
|
||||
"history.clear()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"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": "3.10.6"
|
||||
}
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Google Firestore in Datastore Mode\n",
|
||||
"\n",
|
||||
"> [Firestore in Datastore Mode](https://cloud.google.com/datastore) is a NoSQL document database build for automatic scaling, high performance and ease of application development. Extend your database application to build AI-powered experiences leveraging Datastore's Langchain integrations.\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use [Firestore in Datastore Mode](https://cloud.google.com/datastore) to save chat messages into `Firestore` in Datastore Mode.\n",
|
||||
"\n",
|
||||
"Learn more about the package on [GitHub](https://github.com/googleapis/langchain-google-datastore-python/).\n",
|
||||
"\n",
|
||||
"[](https://colab.research.google.com/github/googleapis/langchain-google-datastore-python/blob/main/docs/chat_message_history.ipynb)"
|
||||
]
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Before You Begin\n",
|
||||
"\n",
|
||||
"To run this notebook, you will need to do the following:\n",
|
||||
"\n",
|
||||
"* [Create a Google Cloud Project](https://developers.google.com/workspace/guides/create-project)\n",
|
||||
"* [Enable the Datastore API](https://console.cloud.google.com/flows/enableapi?apiid=datastore.googleapis.com)\n",
|
||||
"* [Create a Firestore in Datastore Mode database](https://cloud.google.com/datastore/docs/manage-databases)\n",
|
||||
"\n",
|
||||
"After confirmed access to database in the runtime environment of this notebook, filling the following values and run the cell before running example scripts."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 🦜🔗 Library Installation\n",
|
||||
"\n",
|
||||
"The integration lives in its own `langchain-google-datastore` package, so we need to install it."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%pip install -upgrade --quiet langchain-google-datastore"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"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."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# # Automatically restart kernel after installs so that your environment can access the new packages\n",
|
||||
"# import IPython\n",
|
||||
"\n",
|
||||
"# app = IPython.Application.instance()\n",
|
||||
"# app.kernel.do_shutdown(True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### ☁ Set Your Google Cloud Project\n",
|
||||
"Set your Google Cloud project so that you can leverage Google Cloud resources within this notebook.\n",
|
||||
"\n",
|
||||
"If you don't know your project ID, try the following:\n",
|
||||
"\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": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @markdown Please fill in the value below with your Google Cloud project ID and then run the cell.\n",
|
||||
"\n",
|
||||
"PROJECT_ID = \"my-project-id\" # @param {type:\"string\"}\n",
|
||||
"\n",
|
||||
"# Set the project id\n",
|
||||
"!gcloud config set project {PROJECT_ID}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 🔐 Authentication\n",
|
||||
"\n",
|
||||
"Authenticate to Google Cloud as the IAM user logged into this notebook in order to access your Google Cloud Project.\n",
|
||||
"\n",
|
||||
"- If you are using Colab to run this notebook, use 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": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from google.colab import auth\n",
|
||||
"\n",
|
||||
"auth.authenticate_user()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Basic Usage"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### DatastoreChatMessageHistory\n",
|
||||
"\n",
|
||||
"To initialize the `DatastoreChatMessageHistory` class you need to provide only 2 things:\n",
|
||||
"\n",
|
||||
"1. `session_id` - A unique identifier string that specifies an id for the session.\n",
|
||||
"1. `kind` : The name of the Datastore kind to write into. This is an optional value and by default it will use `ChatHistory` as the kind."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_google_datastore import DatastoreChatMessageHistory\n",
|
||||
"\n",
|
||||
"chat_history = DatastoreChatMessageHistory(\n",
|
||||
" session_id=\"user-session-id\", kind=\"HistoryMessages\"\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"chat_history.add_user_message(\"Hi!\")\n",
|
||||
"chat_history.add_ai_message(\"How can I help you?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chat_history.messages"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Cleanup\n",
|
||||
"\n",
|
||||
"When the history of a specific session is obsolete and can be deleted from the database and memory, it can be done the following way.\n",
|
||||
"\n",
|
||||
"**Note:** Once deleted, the data is no longer stored in Datastore and is gone forever."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chat_history.clear()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Custom Client\n",
|
||||
"\n",
|
||||
"The client is created by default using the available environment variables. A [custom client](https://cloud.google.com/python/docs/reference/datastore/latest/client) can be passed to the constructor."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from google.auth import compute_engine\n",
|
||||
"from google.cloud import datastore\n",
|
||||
"\n",
|
||||
"client = datastore.Client(\n",
|
||||
" project=\"project-custom\",\n",
|
||||
" database=\"non-default-database\",\n",
|
||||
" credentials=compute_engine.Credentials(),\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"history = DatastoreChatMessageHistory(\n",
|
||||
" session_id=\"session-id\", kind=\"History\", client=client\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"history.add_user_message(\"New message\")\n",
|
||||
"\n",
|
||||
"history.messages\n",
|
||||
"\n",
|
||||
"history.clear()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"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": "3.10.6"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
|
||||
@ -1,393 +1,400 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Google El Carro Oracle Operator\n",
|
||||
"\n",
|
||||
"> Google [El Carro Oracle Operator](https://github.com/GoogleCloudPlatform/elcarro-oracle-operator) offers a way to run Oracle databases in Kubernetes as a portable, open source, community driven, no vendor lock-in container orchestration system. El Carro provides a powerful declarative API for comprehensive and consistent configuration and deployment as well as for real-time operations and monitoring. Extend your Oracle database's capabilities to build AI-powered experiences by leveraging the El Carro Langchain integration.\n",
|
||||
"\n",
|
||||
"This guide goes over how to use the El Carro Langchain integration to store chat message history with the `ElCarroChatMessageHistory` class. This integration works for any Oracle database, regardless of where it is running.\n",
|
||||
"\n",
|
||||
"[](https://colab.research.google.com/github/googleapis/langchain-google-el-carro-python/blob/main/docs/chat_message_history.ipynb)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Before You Begin\n",
|
||||
"\n",
|
||||
"To run this notebook, you will need to do the following:\n",
|
||||
" * Complete the [Getting Started](https://github.com/googleapis/langchain-google-el-carro-python/tree/main/README.md#getting-started) section if you would like to run your Oracle database with El Carro."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 🦜🔗 Library Installation\n",
|
||||
"The integration lives in its own `langchain-google-el-carro` package, so we need to install it."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%pip install --upgrade --quiet langchain-google-el-carro langchain-google-vertexai langchain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"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."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# # Automatically restart kernel after installs so that your environment can access the new packages\n",
|
||||
"# import IPython\n",
|
||||
"\n",
|
||||
"# app = IPython.Application.instance()\n",
|
||||
"# app.kernel.do_shutdown(True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 🔐 Authentication\n",
|
||||
"Authenticate to Google Cloud as the IAM user logged into this notebook in order to access your Google Cloud Project.\n",
|
||||
"\n",
|
||||
"* If you are using Colab to run this notebook, use 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": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from google.colab import auth\n",
|
||||
"\n",
|
||||
"auth.authenticate_user()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### ☁ Set Your Google Cloud Project\n",
|
||||
"Set your Google Cloud project so that you can leverage Google Cloud resources within this notebook.\n",
|
||||
"\n",
|
||||
"If you don't know your project ID, try the following:\n",
|
||||
"\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": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @markdown Please fill in the value below with your Google Cloud project ID and then run the cell.\n",
|
||||
"\n",
|
||||
"PROJECT_ID = \"my-project-id\" # @param {type:\"string\"}\n",
|
||||
"\n",
|
||||
"# Set the project id\n",
|
||||
"!gcloud config set project {PROJECT_ID}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Basic Usage"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Set Up Oracle Database Connection\n",
|
||||
"Fill out the following variable with your Oracle database connections details."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title Set Your Values Here { display-mode: \"form\" }\n",
|
||||
"HOST = \"127.0.0.1\" # @param {type: \"string\"}\n",
|
||||
"PORT = 3307 # @param {type: \"integer\"}\n",
|
||||
"DATABASE = \"my-database\" # @param {type: \"string\"}\n",
|
||||
"TABLE_NAME = \"message_store\" # @param {type: \"string\"}\n",
|
||||
"USER = \"my-user\" # @param {type: \"string\"}\n",
|
||||
"PASSWORD = input(\"Please provide a password to be used for the database user: \")"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"\n",
|
||||
"If you are using `El Carro`, you can find the hostname and port values in the\n",
|
||||
"status of the `El Carro` Kubernetes instance.\n",
|
||||
"Use the user password you created for your PDB.\n",
|
||||
"Example"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"kubectl get -w instances.oracle.db.anthosapis.com -n db\n",
|
||||
"NAME DB ENGINE VERSION EDITION ENDPOINT URL DB NAMES BACKUP ID READYSTATUS READYREASON DBREADYSTATUS DBREADYREASON\n",
|
||||
"mydb Oracle 18c Express mydb-svc.db 34.71.69.25:6021 False CreateInProgress"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### ElCarroEngine Connection Pool\n",
|
||||
"\n",
|
||||
"`ElCarroEngine` configures a connection pool to your Oracle database, enabling successful connections from your application and following industry best practices."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_google_el_carro import ElCarroEngine\n",
|
||||
"\n",
|
||||
"elcarro_engine = ElCarroEngine.from_instance(\n",
|
||||
" db_host=HOST,\n",
|
||||
" db_port=PORT,\n",
|
||||
" db_name=DATABASE,\n",
|
||||
" db_user=USER,\n",
|
||||
" db_password=PASSWORD,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Initialize a table\n",
|
||||
"The `ElCarroChatMessageHistory` class requires a database table with a specific\n",
|
||||
"schema in order to store the chat message history.\n",
|
||||
"\n",
|
||||
"The `ElCarroEngine` class has a\n",
|
||||
"method `init_chat_history_table()` that can be used to create a table with the\n",
|
||||
"proper schema for you."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"elcarro_engine.init_chat_history_table(table_name=TABLE_NAME)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### ElCarroChatMessageHistory\n",
|
||||
"\n",
|
||||
"To initialize the `ElCarroChatMessageHistory` class you need to provide only 3\n",
|
||||
"things:\n",
|
||||
"\n",
|
||||
"1. `elcarro_engine` - An instance of an `ElCarroEngine` engine.\n",
|
||||
"1. `session_id` - A unique identifier string that specifies an id for the\n",
|
||||
" session.\n",
|
||||
"1. `table_name` : The name of the table within the Oracle database to store the\n",
|
||||
" chat message history."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_google_el_carro import ElCarroChatMessageHistory\n",
|
||||
"\n",
|
||||
"history = ElCarroChatMessageHistory(\n",
|
||||
" elcarro_engine=elcarro_engine, session_id=\"test_session\", table_name=TABLE_NAME\n",
|
||||
")\n",
|
||||
"history.add_user_message(\"hi!\")\n",
|
||||
"history.add_ai_message(\"whats up?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"history.messages"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Cleaning up\n",
|
||||
"When the history of a specific session is obsolete and can be deleted, it can be done the following way.\n",
|
||||
"\n",
|
||||
"**Note:** Once deleted, the data is no longer stored in your database and is gone forever."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"history.clear()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 🔗 Chaining\n",
|
||||
"\n",
|
||||
"We can easily combine this message history class with [LCEL Runnables](/docs/expression_language/how_to/message_history)\n",
|
||||
"\n",
|
||||
"To do this we will use one of [Google's Vertex AI chat models](https://python.langchain.com/docs/integrations/chat/google_vertex_ai_palm) which requires that you [enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com) in your Google Cloud Project.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# enable Vertex AI API\n",
|
||||
"!gcloud services enable aiplatform.googleapis.com"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
|
||||
"from langchain_core.runnables.history import RunnableWithMessageHistory\n",
|
||||
"from langchain_google_vertexai import ChatVertexAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"prompt = ChatPromptTemplate.from_messages(\n",
|
||||
" [\n",
|
||||
" (\"system\", \"You are a helpful assistant.\"),\n",
|
||||
" MessagesPlaceholder(variable_name=\"history\"),\n",
|
||||
" (\"human\", \"{question}\"),\n",
|
||||
" ]\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"chain = prompt | ChatVertexAI(project=PROJECT_ID)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chain_with_history = RunnableWithMessageHistory(\n",
|
||||
" chain,\n",
|
||||
" lambda session_id: ElCarroChatMessageHistory(\n",
|
||||
" elcarro_engine,\n",
|
||||
" session_id=session_id,\n",
|
||||
" table_name=TABLE_NAME,\n",
|
||||
" ),\n",
|
||||
" input_messages_key=\"question\",\n",
|
||||
" history_messages_key=\"history\",\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# This is where we configure the session id\n",
|
||||
"config = {\"configurable\": {\"session_id\": \"test_session\"}}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chain_with_history.invoke({\"question\": \"Hi! I'm bob\"}, config=config)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chain_with_history.invoke({\"question\": \"Whats my name\"}, config=config)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"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": "3.11.5"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Google El Carro for Oracle Workloads\n",
|
||||
"\n",
|
||||
"> Google [El Carro Oracle Operator](https://github.com/GoogleCloudPlatform/elcarro-oracle-operator) offers a way to run Oracle databases in Kubernetes as a portable, open source, community driven, no vendor lock-in container orchestration system. El Carro provides a powerful declarative API for comprehensive and consistent configuration and deployment as well as for real-time operations and monitoring. Extend your Oracle database's capabilities to build AI-powered experiences by leveraging the El Carro Langchain integration.\n",
|
||||
"\n",
|
||||
"This guide goes over how to use the El Carro Langchain integration to store chat message history with the `ElCarroChatMessageHistory` class. This integration works for any Oracle database, regardless of where it is running.\n",
|
||||
"\n",
|
||||
"Learn more about the package on [GitHub](https://github.com/googleapis/langchain-google-el-carro-python/).\n",
|
||||
"\n",
|
||||
"[](https://colab.research.google.com/github/googleapis/langchain-google-el-carro-python/blob/main/docs/chat_message_history.ipynb)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Before You Begin\n",
|
||||
"\n",
|
||||
"To run this notebook, you will need to do the following:\n",
|
||||
"\n",
|
||||
" * Complete the [Getting Started](https://github.com/googleapis/langchain-google-el-carro-python/tree/main/README.md#getting-started) section"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 🦜🔗 Library Installation\n",
|
||||
"The integration lives in its own `langchain-google-el-carro` package, so we need to install it."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%pip install --upgrade --quiet langchain-google-el-carro langchain-google-vertexai langchain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"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."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# # Automatically restart kernel after installs so that your environment can access the new packages\n",
|
||||
"# import IPython\n",
|
||||
"\n",
|
||||
"# app = IPython.Application.instance()\n",
|
||||
"# app.kernel.do_shutdown(True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### 🔐 Authentication\n",
|
||||
"Authenticate to Google Cloud as the IAM user logged into this notebook in order to access your Google Cloud Project.\n",
|
||||
"\n",
|
||||
"* If you are using Colab to run this notebook, use 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": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# from google.colab import auth\n",
|
||||
"\n",
|
||||
"# auth.authenticate_user()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### ☁ Set Your Google Cloud Project\n",
|
||||
"Set your Google Cloud project so that you can leverage Google Cloud resources within this notebook.\n",
|
||||
"\n",
|
||||
"If you don't know your project ID, try the following:\n",
|
||||
"\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": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @markdown Please fill in the value below with your Google Cloud project ID and then run the cell.\n",
|
||||
"\n",
|
||||
"PROJECT_ID = \"my-project-id\" # @param {type:\"string\"}\n",
|
||||
"\n",
|
||||
"# Set the project id\n",
|
||||
"!gcloud config set project {PROJECT_ID}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "azV0k45WWSVI"
|
||||
},
|
||||
"source": [
|
||||
"## Basic Usage\n",
|
||||
"\n",
|
||||
"### Set Up Oracle Database Connection\n",
|
||||
"Fill out the following variable with your Oracle database connections details."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title Set Your Values Here { display-mode: \"form\" }\n",
|
||||
"HOST = \"127.0.0.1\" # @param {type: \"string\"}\n",
|
||||
"PORT = 3307 # @param {type: \"integer\"}\n",
|
||||
"DATABASE = \"my-database\" # @param {type: \"string\"}\n",
|
||||
"TABLE_NAME = \"message_store\" # @param {type: \"string\"}\n",
|
||||
"USER = \"my-user\" # @param {type: \"string\"}\n",
|
||||
"PASSWORD = input(\"Please provide a password to be used for the database user: \")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"source": [
|
||||
"\n",
|
||||
"If you are using El Carro, you can find the hostname and port values in the\n",
|
||||
"status of the El Carro Kubernetes instance.\n",
|
||||
"Use the user password you created for your PDB.\n",
|
||||
"Example Output"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"source": [
|
||||
"```\n",
|
||||
"kubectl get -w instances.oracle.db.anthosapis.com -n db\n",
|
||||
"NAME DB ENGINE VERSION EDITION ENDPOINT URL DB NAMES BACKUP ID READYSTATUS READYREASON DBREADYSTATUS DBREADYREASON\n",
|
||||
"\n",
|
||||
"mydb Oracle 18c Express mydb-svc.db 34.71.69.25:6021 ['pdbname'] TRUE CreateComplete True CreateComplete\n",
|
||||
"```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"source": [
|
||||
"### ElCarroEngine Connection Pool\n",
|
||||
"\n",
|
||||
"`ElCarroEngine` configures a connection pool to your Oracle database, enabling successful connections from your application and following industry best practices."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "xG1mYFkEWbkp"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_google_el_carro import ElCarroEngine\n",
|
||||
"\n",
|
||||
"elcarro_engine = ElCarroEngine.from_instance(\n",
|
||||
" db_host=HOST,\n",
|
||||
" db_port=PORT,\n",
|
||||
" db_name=DATABASE,\n",
|
||||
" db_user=USER,\n",
|
||||
" db_password=PASSWORD,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Initialize a table\n",
|
||||
"The `ElCarroChatMessageHistory` class requires a database table with a specific\n",
|
||||
"schema in order to store the chat message history.\n",
|
||||
"\n",
|
||||
"The `ElCarroEngine` class has a\n",
|
||||
"method `init_chat_history_table()` that can be used to create a table with the\n",
|
||||
"proper schema for you."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"elcarro_engine.init_chat_history_table(table_name=TABLE_NAME)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### ElCarroChatMessageHistory\n",
|
||||
"\n",
|
||||
"To initialize the `ElCarroChatMessageHistory` class you need to provide only 3\n",
|
||||
"things:\n",
|
||||
"\n",
|
||||
"1. `elcarro_engine` - An instance of an `ElCarroEngine` engine.\n",
|
||||
"1. `session_id` - A unique identifier string that specifies an id for the\n",
|
||||
" session.\n",
|
||||
"1. `table_name` : The name of the table within the Oracle database to store the\n",
|
||||
" chat message history."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_google_el_carro import ElCarroChatMessageHistory\n",
|
||||
"\n",
|
||||
"history = ElCarroChatMessageHistory(\n",
|
||||
" elcarro_engine=elcarro_engine, session_id=\"test_session\", table_name=TABLE_NAME\n",
|
||||
")\n",
|
||||
"history.add_user_message(\"hi!\")\n",
|
||||
"history.add_ai_message(\"whats up?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"history.messages"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### Cleaning up\n",
|
||||
"When the history of a specific session is obsolete and can be deleted, it can be done the following way.\n",
|
||||
"\n",
|
||||
"**Note:** Once deleted, the data is no longer stored in the database and is gone forever."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"history.clear()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 🔗 Chaining\n",
|
||||
"\n",
|
||||
"We can easily combine this message history class with [LCEL Runnables](/docs/expression_language/how_to/message_history)\n",
|
||||
"\n",
|
||||
"To do this we will use one of [Google's Vertex AI chat models](https://python.langchain.com/docs/integrations/chat/google_vertex_ai_palm) which requires that you [enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com) in your Google Cloud Project.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# enable Vertex AI API\n",
|
||||
"!gcloud services enable aiplatform.googleapis.com"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
|
||||
"from langchain_core.runnables.history import RunnableWithMessageHistory\n",
|
||||
"from langchain_google_vertexai import ChatVertexAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"prompt = ChatPromptTemplate.from_messages(\n",
|
||||
" [\n",
|
||||
" (\"system\", \"You are a helpful assistant.\"),\n",
|
||||
" MessagesPlaceholder(variable_name=\"history\"),\n",
|
||||
" (\"human\", \"{question}\"),\n",
|
||||
" ]\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"chain = prompt | ChatVertexAI(project=PROJECT_ID)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chain_with_history = RunnableWithMessageHistory(\n",
|
||||
" chain,\n",
|
||||
" lambda session_id: ElCarroChatMessageHistory(\n",
|
||||
" elcarro_engine,\n",
|
||||
" session_id=session_id,\n",
|
||||
" table_name=TABLE_NAME,\n",
|
||||
" ),\n",
|
||||
" input_messages_key=\"question\",\n",
|
||||
" history_messages_key=\"history\",\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# This is where we configure the session id\n",
|
||||
"config = {\"configurable\": {\"session_id\": \"test_session\"}}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chain_with_history.invoke({\"question\": \"Hi! I'm bob\"}, config=config)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chain_with_history.invoke({\"question\": \"Whats my name\"}, config=config)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"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": "3.11.5"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
Loading…
Reference in New Issue