Use OpenSearch LLM-Based Conversational Search Edition SDKs to perform text vectorization, text slicing, and slice vectorization - OpenSearch

Configure environment variables

Configure the ALIBABA_CLOUD_ACCESS_KEY_ID and ALIBABA_CLOUD_ACCESS_KEY_SECRET environment variables.

Important

The AccessKey pair of an Alibaba Cloud account can be used to access all API operations. We recommend that you use a Resource Access Management (RAM) user to call API operations or perform routine O&M. For information about how to use a RAM user, see Create a RAM user.
For information about how to create an AccessKey pair, see Create an AccessKey pair.
If you use the AccessKey pair of a RAM user, make sure that the required permissions are granted to the AliyunServiceRoleForOpenSearch role by using your Alibaba Cloud account. For more information, see AliyunServiceRoleForOpenSearch and Access authorization rules.
We recommend that you do not include your AccessKey pair in materials that are easily accessible to others, such as the project code. Otherwise, your AccessKey pair may be leaked and resources in your account become insecure.

Linux and macOS
Run the following commands. Replace <access_key_id> and <access_key_secret> with the AccessKey ID and AccessKey secret of the RAM user that you use.
```
export ALIBABA_CLOUD_ACCESS_KEY_ID=<access_key_id> 
export ALIBABA_CLOUD_ACCESS_KEY_SECRET=<access_key_secret>
```
Windows
1. Create an environment variable file, add the ALIBABA_CLOUD_ACCESS_KEY_ID and ALIBABA_CLOUD_ACCESS_KEY_SECRET environment variables to the file, and then set the environment variables to your AccessKey ID and AccessKey secret.
2. Restart Windows for the AccessKey pair to take effect.

Dependencies

To use OpenSearch SDK to upload files, you must specify the following dependencies:

Java

<dependency>
    <groupId>com.aliyun.opensearch</groupId>
    <artifactId>aliyun-sdk-opensearch</artifactId>
    <version>6.0.0</version>
</dependency>

Python

pip install alibabacloud_tea_util 
pip install alibabacloud_opensearch_util
pip install alibabacloud_credentials

PHP

V3.4.1 (2021-05-11)
Download URL: https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20230719/mxik/opensearch-sdk-php-release-v3.4.1.zip

Demo code for vectorizing text

For information about BaseRequest, see Demo code for using the Python client.

Java

package com.aliyun.opensearch;

import com.aliyun.opensearch.OpenSearchClient;
import com.aliyun.opensearch.sdk.generated.OpenSearch;
import com.aliyun.opensearch.sdk.generated.commons.OpenSearchClientException;
import com.aliyun.opensearch.sdk.generated.commons.OpenSearchException;
import com.aliyun.opensearch.sdk.generated.commons.OpenSearchResult;

import java.util.HashMap;
import java.util.Map;

public class LLMSearch {
    private static String appName = "The name of the OpenSearch application";
    private static String host = "The API endpoint of the OpenSearch application";
    private static String path = "/apps/AppName/actions/knowledge-embedding";

    public static void main(String[] args) {
      // Specify your AccessKey pair.
      // Obtain the AccessKey ID and AccessKey secret from environment variables. You must configure environment variables before you run this code.
      String accesskey = System.getenv("ALIBABA_CLOUD_ACCESS_KEY_ID");
      String secret = System.getenv("ALIBABA_CLOUD_ACCESS_KEY_SECRET");
        //ApiReadTimeOut
        OpenSearch openSearch = new OpenSearch(accesskey, secret, host);
        openSearch.setTimeout(62000);

        OpenSearchClient openSearchClient = new OpenSearchClient(openSearch);

        Map<String, String> params = new HashMap<String, String>() {{
            put("format", "full_json");
            put("_POST_BODY", "{\"content\":\"Test text\",\"query\":false}");
        }};
      	try {
            OpenSearchResult openSearchResult = openSearchClient
            .callAndDecodeResult(path, params, "POST");
            System.out.println("RequestID=" + openSearchResult.getTraceInfo().getRequestId());
            System.out.println(openSearchResult.getResult());
        } catch (
            OpenSearchException e) {
            System.out.println("RequestID=" + e.getRequestId());
            System.out.println("ErrorCode=" + e.getCode());
            System.out.println("ErrorMessage=" + e.getMessage());
        } catch (
            OpenSearchClientException e) {
            System.out.println("ErrorMessage=" + e.getMessage());
        }
    }
}

Python

# -*- coding: utf-8 -*-

import time, os
from typing import Dict, Any

from Tea.exceptions import TeaException
from Tea.request import TeaRequest
from alibabacloud_tea_util import models as util_models
from BaseRequest import Config, Client


class LLMSearch:
    def __init__(self, config: Config):
        self.Clients = Client(config=config)
        self.runtime = util_models.RuntimeOptions(
            connect_timeout=10000,
            read_timeout=10000,
            autoretry=False,
            ignore_ssl=False,
            max_idle_conns=50,
            max_attempts=3
        )
        self.header = {}


    def searchDoc(self, app_name: str,body:Dict, query_params: dict={}) -> Dict[str, Any]:
        try:
            response = self.Clients._request(method="POST", pathname=f'/v3/openapi/apps/{app_name}/actions/knowledge-embedding',
                                             query=query_params, headers=self.header, body=body, runtime=self.runtime)
            return response
        except TeaException as e:
            print(e)


if __name__ == "__main__":
    # Specify the endpoint of the OpenSearch API. The value does not contain the http:// prefix.
    endpoint = "<endpoint>"

    # Specify the request protocol. Valid values: HTTPS and HTTP.
    endpoint_protocol = "HTTP"

    # Specify your AccessKey pair.
    # Obtain the AccessKey ID and AccessKey secret from environment variables. 
    # You must configure environment variables before you run this code. For more information, see the "Configure environment variables" section of this topic.
    access_key_id = os.environ.get("ALIBABA_CLOUD_ACCESS_KEY_ID")
    access_key_secret = os.environ.get("ALIBABA_CLOUD_ACCESS_KEY_SECRET")

    # Specify the authentication method. Default value: access_key. A value of sts specifies authentication based on Resource Access Management (RAM) and Security Token Service (STS).
    # Valid values: sts and access_key.
    auth_type = "access_key"

    # If you use authentication based on RAM and STS, you must specify the security_token parameter. You can call the AssumeRole operation of Alibaba Cloud RAM to obtain an STS token.
    security_token =  "<security_token>"

    # Specify common request parameters.
    # The type and security_token parameters are required only if you use the SDK as a RAM user.
    Configs = Config(endpoint=endpoint, access_key_id=access_key_id, access_key_secret=access_key_secret,
                     security_token=security_token, type=auth_type, protocol=endpoint_protocol)

    # Create an OpenSearch LLM-Based Conversational Search Edition instance.
    # Replace <Application name> with the name of your OpenSearch LLM-Based Conversational Search Edition instance.
    ops = LLMSearch(Configs)
    app_name = "<Application name>"

    # --------------- Search for documents ---------------

    docQuery = {"content":"Test text","query":false}

    res1 = ops.searchDoc(app_name=app_name, body=docQuery)
    print(res1)

PHP

<?php
require_once($path . "/OpenSearch/Autoloader/Autoloader.php");

use OpenSearch\Client\OpenSearchClient;

// Specify your AccessKey pair.
// Obtain the AccessKey ID and AccessKey secret from environment variables. 
// You must configure environment variables before you run this code. For more information, see the "Configure environment variables" section of this topic.
// Specify the AccessKey ID.
$accessKeyId = getenv('ALIBABA_CLOUD_ACCESS_KEY_ID');
// Specify the AccessKey secret.
$secret = getenv('ALIBABA_CLOUD_ACCESS_KEY_SECRET');
$endPoint = '<The API endpoint of the OpenSearch application>';
$appName = '<The application name>';
$options = array('debug' => true);
$requestBody = "{"content":" Test text ","query":false}";

$client = new OpenSearchClient($accessKeyId, $secret, $endPoint, $options);

$uri = "/apps/{$appName}/actions/knowledge-embedding";

try{
    $ret = $client->post($uri, $requestBody);
    print_r(json_decode($ret->result, true));
}catch (\Throwable $e) {
    print_r($e);
}

Demo code for slicing text and vectorizing slices

Java

package com.aliyun.opensearch;

import com.aliyun.opensearch.OpenSearchClient;
import com.aliyun.opensearch.sdk.generated.OpenSearch;
import com.aliyun.opensearch.sdk.generated.commons.OpenSearchClientException;
import com.aliyun.opensearch.sdk.generated.commons.OpenSearchException;
import com.aliyun.opensearch.sdk.generated.commons.OpenSearchResult;

import java.util.HashMap;
import java.util.Map;

public class LLMSearch {
    private static String appName = "The name of the OpenSearch application";
    private static String host = "The API endpoint of the OpenSearch application";
    private static String path = "/apps/AppName/actions/knowledge-split";

    public static void main(String[] args) {
      // Specify your AccessKey pair.
      // Obtain the AccessKey ID and AccessKey secret from environment variables. You must configure environment variables before you run this code.
      String accesskey = System.getenv("ALIBABA_CLOUD_ACCESS_KEY_ID");
      String secret = System.getenv("ALIBABA_CLOUD_ACCESS_KEY_SECRET");
        //ApiReadTimeOut
        OpenSearch openSearch = new OpenSearch(accesskey, secret, host);
        openSearch.setTimeout(62000);

        OpenSearchClient openSearchClient = new OpenSearchClient(openSearch);

        Map<String, String> params = new HashMap<String, String>() {{
            put("format", "full_json");
            put("_POST_BODY", "{"title":"Test title","content":"Test text","use_embedding":true}");
        }};
      	try {
            OpenSearchResult openSearchResult = openSearchClient
            .callAndDecodeResult(path, params, "POST");
            System.out.println("RequestID=" + openSearchResult.getTraceInfo().getRequestId());
            System.out.println(openSearchResult.getResult());
        } catch (
            OpenSearchException e) {
            System.out.println("RequestID=" + e.getRequestId());
            System.out.println("ErrorCode=" + e.getCode());
            System.out.println("ErrorMessage=" + e.getMessage());
        } catch (
            OpenSearchClientException e) {
            System.out.println("ErrorMessage=" + e.getMessage());
        }
    }
}

Python

# -*- coding: utf-8 -*-

import time, os
from typing import Dict, Any

from Tea.exceptions import TeaException
from Tea.request import TeaRequest
from alibabacloud_tea_util import models as util_models
from BaseRequest import Config, Client


class LLMSearch:
    def __init__(self, config: Config):
        self.Clients = Client(config=config)
        self.runtime = util_models.RuntimeOptions(
            connect_timeout=10000,
            read_timeout=10000,
            autoretry=False,
            ignore_ssl=False,
            max_idle_conns=50,
            max_attempts=3
        )
        self.header = {}


    def searchDoc(self, app_name: str,body:Dict, query_params: dict={}) -> Dict[str, Any]:
        try:
            response = self.Clients._request(method="POST", pathname=f'/v3/openapi/apps/{app_name}/actions/knowledge-split',
                                             query=query_params, headers=self.header, body=body, runtime=self.runtime)
            return response
        except TeaException as e:
            print(e)


if __name__ == "__main__":
    # Specify the endpoint of the OpenSearch API. The value does not contain the http:// prefix.
    endpoint = "<endpoint>"

    # Specify the request protocol. Valid values: HTTPS and HTTP.
    endpoint_protocol = "HTTP"

    # Specify your AccessKey pair.
    # Obtain the AccessKey ID and AccessKey secret from environment variables. 
    # You must configure environment variables before you run this code. For more information, see the "Configure environment variables" section of this topic.
    access_key_id = os.environ.get("ALIBABA_CLOUD_ACCESS_KEY_ID")
    access_key_secret = os.environ.get("ALIBABA_CLOUD_ACCESS_KEY_SECRET")

    # Specify the authentication method. Default value: access_key. A value of sts specifies authentication based on RAM and STS.
    # Valid values: sts and access_key.
    auth_type = "access_key"

    # If you use authentication based on RAM and STS, you must specify the security_token parameter. You can call the AssumeRole operation of Alibaba Cloud RAM to obtain an STS token.
    security_token =  "<security_token>"

    # Specify common request parameters.
    # The type and security_token parameters are required only if you use the SDK as a RAM user.
    Configs = Config(endpoint=endpoint, access_key_id=access_key_id, access_key_secret=access_key_secret,
                     security_token=security_token, type=auth_type, protocol=endpoint_protocol)

    # Create an OpenSearch LLM-Based Conversational Search Edition instance.
    # Replace <Application name> with the name of your OpenSearch LLM-Based Conversational Search Edition instance.
    ops = LLMSearch(Configs)
    app_name = "<Application name>"

    # --------------- Search for documents ---------------

    docQuery = {"title":"Test title","content":"Test text","use_embedding":true}

    res1 = ops.searchDoc(app_name=app_name, body=docQuery)
    print(res1)

PHP

<?php
require_once($path . "/OpenSearch/Autoloader/Autoloader.php");

use OpenSearch\Client\OpenSearchClient;

// Specify your AccessKey pair.
// Obtain the AccessKey ID and AccessKey secret from environment variables. 
// You must configure environment variables before you run this code. For more information, see the "Configure environment variables" section of this topic.
// Specify the AccessKey ID.
$accessKeyId = getenv('ALIBABA_CLOUD_ACCESS_KEY_ID');
// Specify the AccessKey secret.
$secret = getenv('ALIBABA_CLOUD_ACCESS_KEY_SECRET');
$endPoint = '<The API endpoint of the OpenSearch application>';
$appName = '<The application name>';
$options = array('debug' => true);
$requestBody = "{"title":"Test title","content":"Test text","use_embedding":true}";

$client = new OpenSearchClient($accessKeyId, $secret, $endPoint, $options);

$uri = "/apps/{$appName}/actions/knowledge-split";

try{
    $ret = $client->post($uri, $requestBody);
    print_r(json_decode($ret->result, true));
}catch (\Throwable $e) {
    print_r($e);
}