OpenSearch:Lark chatbots

Overview

To better meet the needs of users for intelligent conversational search in multiple scenarios, OpenSearch provides the ecosystem integration feature. You can integrate OpenSearch LLM-Based Conversational Search Edition with the chatbots of open platforms such as DingTalk and Lark in a simple, fast, and convenient manner. This feature can be used to introduce various types of intelligent assistants into chat groups, such as intelligent customer service and internal knowledge chatbot.

Procedure

Configure ecosystem integration for a custom Lark application

1. Log on to the OpenSearch LLM-Based Conversational Search Edition console. Go to the details page of your instance and click Ecosystem Connection in the left-side navigation pane. On the Endpoint tab, click Create. In the Create Access Point panel, select Lark Chatbot from the Ecosystem Platform drop-down list.

2. Configure other parameters such as Access Point Name, App ID, and App Secret.

3. After the endpoint is created, you can find the endpoint and click Edit in the Actions column to modify the endpoint.

Configure a Lark chatbot

1. Log on to the Feishu Open Platform. Click Developer Console in the upper right corner.

2. In the Developer Console, click Create Custom App. In the dialog box that appears, configure the Name and Description parameters and click Create. On the application details page that appears, choose Features > Add Features in the left-side navigation pane. On the By Feature tab, find the Bot card and click Add.

3. Choose Development Configuration > Permissions & Scopes in the left-side navigation pane and add permissions. The following figure shows the permissions that are required.

4. Choose Basic Info > Credentials & Basic Info in the left-side navigation pane. Copy the App ID and App secret and paste the values to the App ID and App Secret fields in the Create Access Point panel.

The App ID and App Secret fields on the Feishu Open Platform

The App ID and App Secret fields of an endpoint in the OpenSearch LLM-Based Conversational Search Edition console

5. Choose Development Configuration > Events & Callbacks in the left-side navigation pane and configure the verification token, encrypt key, and request URL of the endpoint that you create in OpenSearch LLM-Based Conversational Search Edition.

Copy the verification token, encrypt key, and request URL of the endpoint that you create in OpenSearch LLM-Based Conversational Search Edition.

On the Events & Callbacks page, paste the verification token, encrypt key, and request URL to the corresponding fields and click Save.

Click Add Events to add the Receive Message event.

6. Choose App Versions > Version Management & Release in the left-side navigation pane. Click Create a version in the upper right corner.

On the Version Details page, enter the version number and update notes, and click Save. In the message that appears, read the App Review Rules and click Submit for release.

7. After the version is approved, the version is in the Released state. The "The current changes have been published" message appears in the upper part of the screen.

Add the chatbot to a Lark group

1. Open the dialog box of the group to which you want to add the chatbot in Lark. Click the More icon in the upper right corner and then click Settings. In the Settings panel, click Bots. In the Bots panel, click Add Bot. In the Add bot dialog box, search for the chatbot and click Add.

2. After the chatbot is added to the group, you can @mention the chatbot and enter questions.

Chat with the chatbot in a private dialog box

1. Enter the name of the chatbot in the top search box of Lark and click the chatbot name to open a private dialog box.

2. Enter questions.