docs/guides/chatchannel/channel_access_and_configuration.md
Users can chat with a Chat directly in Discord. This is suitable for community support, product Q&A, user feedback collection, and similar scenarios.
Configuration prerequisites:
BotToken on the Bot page.bot scope.Configuration parameters:
Usage:
When adding a Discord channel in RAGFlow, fill in the BotToken obtained from the Discord Developer Portal and connect the channel to a Chat after saving it. The bot must join the target server and have permissions to read and send messages. If MessageContentIntent is not enabled, the bot may appear online but fail to read the body text of user messages.
Connection verification:
After completing configuration, send a test message to the bot in Discord to verify whether replies are received normally.
The DingTalk channel is suitable for organizational collaboration scenarios. Members can complete knowledge Q&A, process consultation, and business support in DingTalk conversations.
Configuration prerequisites:
qyapi_robot_sendmsg, Card.Streaming.Write, and Card.Instance.Write.ClientID and ClientSecret.Configuration parameters:
Usage:
When adding a DingTalk channel in RAGFlow, fill in the ClientID and ClientSecret from the DingTalk Open Platform and connect the channel to a Chat after saving it. DingTalk replies depend on the conversation Webhook returned in message events. Therefore, the user must first send a message to the bot in DingTalk before RAGFlow can return a reply in the corresponding conversation.
Connection verification:
After completing configuration, send a test message to the bot in DingTalk to verify whether replies are received normally.
The Feishu / Lark channel helps organization members use knowledge assistants in daily chat windows. It is suitable for enterprise knowledge Q&A, customer service collaboration, and internal business assistants.
Configuration prerequisites:
AppID and AppSecret.Configuration parameters:
Usage:
When adding a Feishu / Lark channel in RAGFlow, fill in the AppID and AppSecret from the open platform and select the Domain based on the platform where the application is located. After saving the configuration, connect the channel to a Chat and add the bot to the Feishu / Lark conversation where it will be used.
Connection verification:
After completing configuration, send a test message to the bot in Feishu or Lark to verify whether replies are received normally.
The QQ Bot channel is suitable for providing automatic Q&A services to QQ users. It can cover one-on-one chats, group chats, channels, private messages, and other conversation scenarios.
Configuration prerequisites:
AppID.ClientSecret.Configuration parameters:
Usage:
When adding a QQ Bot channel in RAGFlow, fill in the AppID and ClientSecret obtained from the QQ platform and connect the channel to a Chat after saving it. In ordinary public network environments, keep BaseURL empty and use the system default address. Fill in this parameter only when the platform requires another API domain name, a proxy gateway, or a private forwarding address.
Connection verification:
After completing configuration, send a test message to the bot in QQ to verify whether replies are received normally.
The Telegram channel supports real-time conversations with users through a bot. It is suitable for overseas user services, community operations, and lightweight message bot scenarios.
Configuration prerequisites:
BotToken.Configuration parameters:
Usage:
If you need to use the bot in a group, add it to the target group and confirm that it can receive the messages that need to be processed. Group privacy mode may affect whether the bot can read ordinary messages.
Connection verification:
After completing configuration, send a test message to the bot in Telegram to verify whether replies are received normally.
The WeCom channel is suitable for providing knowledge Q&A, employee services, and business bot capabilities inside an enterprise. You can select Webhook or WebSocket access based on the deployment environment.
Configuration prerequisites:
Webhook, prepare the enterprise ID, application ID, application secret, and callback configuration.WebSocket, create a smart bot through the WeCom API.BotID and Secret required by the WebSocket method.Configuration parameters:
WeCom supports two connection methods: Webhook and WebSocket. Different parameters are required for different methods.
Parameters required by the Webhook method:
Webhook. After selecting it, you need to fill in CorpID, AgentID, Secret, Token, and AESKey.Parameters required by the WebSocket method:
WebSocket. After selecting it, you only need to fill in BotID and Secret.WebSocket authentication to fail.Usage:
The credentials for Webhook and WebSocket cannot be mixed. When selecting WebSocket, first create a smart bot in WeCom, then fill the obtained BotID and Secret into RAGFlow. When selecting Webhook, fill in CorpID, AgentID, Secret, Token, and AESKey according to the WeCom application callback configuration.
After saving the channel, connect the WeCom channel to a Chat. After the connection succeeds, users can send messages to the bot in WeCom, and the bot calls the bound Chat to return replies.
Connection verification:
After completing configuration, send a test message to the bot in WeCom to verify whether replies are received normally.
The WhatsApp channel connects an account through QR pairing. It is suitable for service scenarios that use WhatsApp to stay in contact with external users. This method does not require open platform keys to be filled in on the page.
Configuration prerequisites:
WhatsAppGateway is running normally.Configuration parameters:
WhatsApp completes account connection through QR pairing. You do not need to fill in open platform keys on the page. After filling in the name and saving the channel, wait a few seconds until the page generates the QR code used for pairing.
Usage:
When adding a WhatsApp channel, fill in the name first and save it. After saving, the page may first display prompt information. Wait a few seconds and use the mobile phone to scan the QR code after it is generated.
Complete the scanning operation in the mobile WhatsApp app: go to settings, click Linked devices, select Link a device, and then scan the QR code on the RAGFlow page. After successful scanning, subsequent messages sent by users to this WhatsApp account enter RAGFlow.
WhatsApp depends on the WhatsAppGateway in the RAGFlow backend. By default, RAGFlow connects to the local gateway service and stores the login state in the gateway data directory. Ordinary users do not need to fill in these gateway parameters on the page. If the administrator has separately configured the gateway address, access token, or session directory for the deployment environment, use the runtime environment provided by the administrator.
Connection verification:
After completing QR scanning and connecting the channel to a Chat, use another WhatsApp account to send a test message to this account and verify whether replies are received normally.
:::caution NOTE
After deleting a WhatsApp channel or clearing the gateway login state, you may need to scan the QR code again for pairing. If the QR code is not displayed for a long time, confirm that WhatsAppGateway has started and check network connectivity between the backend service and the gateway.
:::