Data Transmission Service:Build and use a DTS RAGFlow knowledge base

Create a RAGFlow knowledge base

1. Go to the RAGFlow knowledge base list page for the destination region.

   1. Log on to the Data Transmission Service (DTS) console.

   2. In the left navigation pane, click Data preparation.

   3. In the upper-left corner of the page, select the region where your data preparation instance is located.

   4. Click the RAGFlow Knowledge Base tab.

2. Click Create Knowledge Base to open the configuration page.

3. Configure the RAGFlow knowledge base.

   1. In the Deployment Scope section, specify the Instance Name for the RAGFlow knowledge base.

   2. In the Network and Zone section, select a VPC, a Primary Zone and VSwitch, and a Secondary Zone and VSwitch for the RAGFlow knowledge base.

   3. In the RAGFlow Knowledge Base Configuration section, specify the Number of Knowledge Base Services.

      Note

      For this example, keep Configuration Plan set to Default.

   4. In the Vector Database Configuration section, configure the vector database.

      Engine: ADB PostgreSQL

      Set Engine to ADB PostgreSQL. In the Database section, select the destination AnalyticDB for PostgreSQL instance and enter its Database Name, Database Account, and Password.

      Engine: Lindorm

      Set the Engine to Lindorm. In the Database section, select the destination Lindorm instance and enter the Database Account and Password.

   5. In the OSS Configuration section, select the destination bucket and enter a storage path.

   Parameters

   Parameter		Description
   Billing Method		Only Pay-as-you-go is supported.
   Region		The region where the RAGFlow knowledge base resides.
   Deployment Scope	Deployment Scope	The default value is RAGFlow Knowledge Base.
   	Instance Name	The name of the RAGFlow knowledge base. Specify a name that is easy to identify.
   Permission Check	SLR Authorization	The AliyunServiceRoleForADBPG service-linked role for AnalyticDB for PostgreSQL is required.
   Network And Zone	Network Type	The default value is VPC.
   	VPC	The VPC where the RAGFlow knowledge base resides.
   	Primary Zone And VSwitch	The primary zone and vSwitch where the RAGFlow knowledge base resides.
   	Deployment Solution	Only Multi-zone Deployment is supported.
   	Secondary Zone And VSwitch	The secondary zone and vSwitch where the RAGFlow knowledge base resides. Note The secondary zone must be different from the primary zone.
   RAGFlow Knowledge Base Configuration	Configuration Plan	DTS supports the Default and Custom plans. Note If you select Default, you only need to configure Number Of Knowledge Base Services for the RAGFlow Knowledge Base Configuration section. The Knowledge Base Service Specification parameter supports only 4 VCPU, 16 GB Memory.
   	Knowledge Base Basic Service Specification	The specification of the RAGFlow knowledge base basic services. Currently, only 4 VCPU, 16 GB Memory is supported.
   	Number Of Knowledge Base Basic Services	The number of RAGFlow knowledge base basic services. The default value is 4. Note This number affects the cost of the RAGFlow knowledge base.
   	Knowledge Base Data Preparation Service Specification	The specification of the RAGFlow knowledge base data preparation services. Currently, only 4 VCPU, 16 GB Memory is supported.
   	Number Of Knowledge Base Data Preparation Services	The number of RAGFlow knowledge base data preparation services. The default value is 2. Note This number affects the cost of the RAGFlow knowledge base.
   Vector Database Configuration	Vector Database	Currently, only Import Existing Instance is supported.
   	Engine	The type of the destination vector database.
   	Database	The destination vector database instance.
   	Database Name	The name of the database in the AnalyticDB for PostgreSQL instance that is used to receive data. Note This parameter is available only when Engine is set to ADB PostgreSQL.
   	Database Schema Name	The name of the schema in the database of the AnalyticDB for PostgreSQL instance that is used to receive data. Note This parameter is available only when Engine is set to ADB PostgreSQL. The default value is public and cannot be changed.
   	Database Account	The database account and password of the vector database instance.
   	Password
   OSS Configuration	OSS Bucket	The destination bucket.
   	Path	The path in the bucket where data is stored.

4. After completing the configuration, click Buy Now on the right side of the page.

5. Return to the RAGFlow knowledge base list page and wait until the knowledge base is in the Normal state (i.e., its Running Status is Running).

   Note

   You can click the icon in the upper-right corner to refresh the task list and view the latest status of the RAGFlow knowledge base.

Configure an IP whitelist

1. In the Actions column for the target RAGFlow knowledge base, click Configure Whitelist.

2. In the Configure Whitelist panel, you can add IP addresses or CIDR blocks to the whitelist based on the access method.

   Access Method	Example Scenario	IP Whitelist to Add	Description
   Internal network	The client and the RAGFlow knowledge base are in the same VPC.	The private IP address or CIDR block of the client.	Separate multiple IP addresses or CIDR blocks with a comma (,). To find the public IP address of the client, run the curl ipinfo.io/ip (recommended) or curl ifconfig.me command.
   Internet	The client is on your local server.	The public IP address or CIDR block of the client.

3. Click Set.

Log on to RAGFlow

1. In the Actions column for the target RAGFlow knowledge base, click Manage.

   Note

   You can also click Log On To Knowledge Base in the Actions column and choose whether to log on through the internal network or the Internet.

2. In the Endpoint section, click Log On With Public Endpoint or Log On With Internal Endpoint.

   Note

   To access the RAGFlow knowledge base over the internet, you must enable a public endpoint for the instance.

3. On the logon page, enter your email address and password, and then click Log On.

4. On the RAGFlow page, you can manage knowledge bases and perform other operations.

   Note

   For more information about the operations, see the official RAGFlow documentation.

   

(Optional) Configure the network

By default, RAGFlow cannot access external networks. To add model providers in RAGFlow, you must configure a NAT Gateway for the VPC that the vector database uses. This allows RAGFlow to access external models.

• Connect through PrivateLink (Alibaba Cloud Model Studio)

  Accessing the Alibaba Cloud Model Studio platform through a private network improves the security and efficiency of data transmission. You can use PrivateLink to establish a network connection between a VPC and Alibaba Cloud Model Studio. For more information, see Access Alibaba Cloud Model Studio models or application APIs over a private network.

• Connect through the internet

  Configure a NAT Gateway for the VPC that the vector database uses to allow RAGFlow to access external models. For more information about NAT Gateway, see Public NAT Gateway.

Enable a public endpoint

1. In the Actions column for the target RAGFlow knowledge base, click Manage.

2. In the Endpoint section, click Enable Public Endpoint.

3. In the Enable Public Endpoint dialog box, click OK.

4. Wait for the Running Status in the Basic Information section to change to Running.

Register a RAGFlow account

1. Go to the RAGFlow logon page for the target RAGFlow knowledge base.

2. On the RAGFlow logon page, click Register.

   

3. Enter an email address, name, and password for the account.

   

4. Click Continue.

   A message appears at the top of the page, indicating that the account is registered.