Knowledge Base is automatically enabled and empowers your chatbot to search within documents and web pages for answers. To set up your first Knowledge Base, visit cloud.google.com/dialogflow/docs/knowledge-connectors.
Knowledge Base is automatically enabled and empowers your chatbot to search within documents and web pages for answers. To set up your first Knowledge Base, visit cloud.google.com/dialogflow/docs/knowledge-connectors.
Dialogflow assigns intent detection confidence scores ranging from 0.0 to 1.0 to potential matches. Specify a value between 0.1 and 1.0 to filter responses. Any score lower than the specified value is disregarded. If you are utilizing Dialogflow alongside your OpenAI chatbot that is trained using your resources, it is recommended to configure the value as 0.81. Go to chat.RPAiX > Artificial Intelligence > Google > Dialogflow Intent detection confidence.
The fulfillment data sent to your webhook URL is like below:
{
"responseId": "4a68fc8r...",
"queryResult": {
"queryText": "fullfilment",
"parameters": [],
"allRequiredParamsPresent": true,
"fulfillmentText": "Example",
"fulfillmentMessages": [{
"text": {
"text": ["Response"]
}
}],
"outputContexts": [{
"name": "projects/rpaix...",
"parameters": {
"no-input": 0,
"no-match": 0
}
}],
"intent": {
"name": "projects/rpaix...",
"displayName": "Fullfilment"
},
"intentDetectionConfidence": 1,
"languageCode": "en"
},
"originalDetectIntentRequest": {
"payload": {
"support_board": {
"conversation_id": "3002",
"user_id": "3777"
}
}
},
"session": "projects/example/agent/sessions/3777-3002"
}The payload and session fields contain the Chat.RPAiX user ID and conversation ID.
To trigger human takeover, use the following Custom Payload response:
{ "human-takeover": true }
Use the “chips” rich message with the ID sb-human-takeover to provide options like “Human support” to users, allowing them to initiate manual takeover.
To manually initiate human takeover, create a new Intent and add a Custom Payload response with the syntax: { "human-takeover": true }.
Future user messages within ten days of human takeover, without an answer from the chatbot, will trigger agent notifications.
Conversations that the chatbot has successfully answered are marked as read and moved to the bottom of the Inbox list.
If enabled, requests are sent only when a user message is longer than three characters and contains at least two words. This prevents mistaken requests and ensures meaningful interactions.
When a human agent in Chat.RPAiX replies to a user, the human takeover is automatically activated, ensuring a seamless transition between automated and human-assisted interactions.
If you’re using Slack, no messages will be sent by the chatbot if it knows the answer to the user’s question. All conversation messages are forwarded to Slack once human takeover is active.
The chatbot is fully reactivated when the conversation is either archived or deleted.
Yes, you can force a Dialogflow message to be sent by adding the custom Payload value "force-message": true to the Intent.
No, default fallback messages are not sent within ten days of human takeover if the chatbot is unable to answer the user’s question in the same conversation.
Once the human agent goes offline, the chatbot is reactivated and resumes handling conversations.
The (chatbot) Chat.RPAiX remains disabled as long as the human agent is online and actively engaged in the conversation.
When human takeover is activated, the Chat.RPAiX is automatically disabled while the human agent is online and available to handle the conversation.
You can update or modify the autonomous interaction actions whenever needed by editing the corresponding Intents in DialogFlow.
The website should be designed in a way that allows the chatbot to interact with its elements. If the website uses standard HTML and controls, autonomous interactions should work seamlessly.
Yes, you can include a mix of other responses like text, images, and autonomous interactions within a single Intent to create a comprehensive user experience.
You can test the autonomous interactions within DialogFlow’s testing environment to ensure the actions are performed as intended.
The limitations depend on the website’s structure and the capabilities of the chatbot. Complex interactions might require more detailed setup and validation.
Make sure to follow the provided syntax accurately, and verify that the website’s structure and elements match the defined actions.
Yes, you can include multiple autonomous interaction actions in a single response by using the specified syntax for each action.
Yes, you can define custom actions based on the website’s functionality. For example, you could define actions like clicking buttons, filling out forms, navigating to specific pages, and more.
The chatbot understands the action based on the provided "ACTION-NAME" and performs the action specified by the "ACTION-VALUE."
Sure, let’s say you want the chatbot to click a “Buy Now” button on a website. In the Intent’s Custom Payload response, you would add:
{ "clickButton": "Buy Now" }
For defining an autonomous interaction action, use the following syntax:
{ "ACTION-NAME": ACTION-VALUE }
In the Intent editing interface in DialogFlow, add a new Custom Payload response.
To enable autonomous interactions, go to DialogFlow and edit an Intent.
The following actions allow the chatbot to interact with the website autonomously on behalf of the user. To use an action, go to DialogFlow, edit an Intent, and add a new Custom Payload response with the following syntax:
{ “ACTION-NAME”: ACTION-VALUE }.
| Action code | Description |
|---|---|
| { “human-takeover”: true } | Disable the chatbot for 5 minutes, notify agents, and leave the conversation marked as unread. |
| { “disable-bot”: true } | Disable the chatbot for 5 minutes. |
| { “redirect”: “URL” } | Redirect the user to the given URL. Add the value “new-window”: true to open the URL in a new window. |
| { “open-article”: ID } | Open the article with the given ID. |
| { “transcript”: true } | Generate the conversation transcript as a text file and download it. Set it to email to send the transcript to the user’s email, add the value message: “Your message” to include a message in the email. |
| { “department”: ID } | Change or set the conversation department and notify the agents. |
| { “agent”: ID } | Change or set the agent assigned to the conversation and notify the agent. |
| { “send-email”: { “recipient”: “active_user”, “message”: “”, “attachments”: [] } } | Send an email to the active user or agents. Attachments syntax: [[“name”, “link”], [“name”, “link”], …]}. Recipient value can be active_user or agents. |
| { “update-user”: true } | Tells the admin area to update the user of the active conversation. Use this action in combination with other actions to update the user details of the admin area in real-time. |
| { “archive-chat”: true } | Archive the chat and send the close message if active. |
| { “update-user-details”: { “email”: “”, “last_name”: “”, “first_name”: “”, “extra”: { “phone”: [“+123456789”, “Phone”] }}} | Update the details of the active user. You can update all details, including first_name, last_name, email, user_type, password You can update the user extra details, like the phone number, by inserting the values into the extra key, the values must use the following syntax: “slug”: [value, “label”]. |
To activate the Dialogflow chatbot, enter your chatbot Project ID or Agent Name in Chat.RPAiX. Follow the provided steps to obtain this information. Note that app approval by Google is not required.
After synchronization, copy the Refresh token and paste it into Chat.RPAiX > Settings > Artificial Intelligence > Google > Refresh token.
Click Chat.RPAiX > Settings > Artificial Intelligence > Google > Synchronize. Log in with the same Google account used previously. On the next screen, select all scopes and click “Continue.”
Under Settings > APIs & Services > OAuth Consent Screen, click “PUBLISH APP.” It’s not necessary to complete the review process; leaving it in pending review is fine.
Copy the Client ID and Client Secret from the generated credentials and paste them into Chat.RPAiX > Settings > Artificial Intelligence > Dialogflow. Save the settings.
Go to Left menu > APIs and services > Credentials and click “Create credentials.” Choose “OAuth client ID” and select “Web application” as the application type. Enter a name and the authorized redirect URI (obtain from Chat.RPAiX settings). Click “Create.”
In the “test users” area, click “Add users” and add your Google email (use the same email as the currently logged-in account). Click “Save and continue.”
Under the “scopes” area, click “Add or remove scopes.” Enter the following URLs into the “Manually add scopes” section:
Click “Add to table,” then “Update” and “Save and continue.”
Select your project and go to Left menu > APIs and services > OAuth consent screen.
Choose “External” and click “Create.” Enter the app name, user support email, and developer contact information. Save and continue.
In the top search bar, enter “Dialogflow API.” Click on the Dialogflow API link, then click “Enable.”
Click on the “Select a project” button on the top-left corner of the Google Cloud Console. Name your project as desired.
Visit console.cloud.google.com and sign in with your Google account.
Navigate to RPAiX Chat > Settings > Artificial Intelligence > Google > Dialogflow Chatbot and save the changes.
To begin using Google AI services and Dialogflow with Chat.RPAiX follow these steps: