Agent Builder contains prebuilt UI and blueprint blocks that you can combine to build a full-featured chatbot.
This tutorial demonstrates how to build a chatbot that is connected to the Palmyra X5 model and integrates with a Knowledge Graph for domain-specific knowledge. It covers the following steps:
If you are unfamiliar with Agent Builder interface, check out the Agent Builder Quickstart.
The UI for the agent contains a single Chatbot block. This block handles the full UI for the chatbot, including the chat interface and the chat messages.
Add a Chatbot block to the UI
Drag and drop a Chatbot component onto the Interface.
In the block’s configuration panel, set the following fields:
@{chat}
. This is the state variable that stores the chat conversation.AI
. This is the text that appears next to the assistant’s messages in the chat.YOU
. This is the text that appears next to the user’s messages in the chat.no
. You can change this to yes
if you want to parse Markdown formatting in messages.no
. This disables the file uploads in the chatbot.Type your message here.
. This is the text that appears in the input field when it’s empty.The blueprint for the agent contains the following blocks:
Add a UI trigger for the chat message event
To run the blueprint when a user enters a chat message, add a UI trigger block to the canvas. In the block’s configuration panel, update the following fields:
Chatbot
component from the dropdown of UI blockswf-chatbot-message
Add a Chat reply block
Add a Chat reply block to the canvas, which runs after the UI trigger block. This block manages the chat conversation, including the chat messages and the chat history.
Connect the UI trigger block to the Chat reply block by dragging a line from the green dot on the UI trigger block to the Chat reply block.
In the Chat reply block’s configuration panel, set the following fields:
chat
@{payload}
. This is the message that the user sends to the chatbot that triggers the blueprint to run.At this point, the chatbot isn’t connected to a Knowledge Graph, but it’s configured to respond to messages from the user. You can preview the agent to see how it works and then connect a Knowledge Graph to the chatbot to enable the chatbot to answer domain-specific questions.
To preview the agent, navigate to the Preview tab. Type a message in the chatbot and see the response from the model.
You can connect one or more Knowledge Graphs to the chatbot to answer questions about data related to your business or a specific dataset.
To connect a Knowledge Graph to the chatbot, update the Chat reply block.
Update the Chat reply block
Now when the user asks questions related to data in the connected Knowledge Graphs, the chatbot can reference the data in the Knowledge Graphs to answer the question.
If you encounter any issues, refer to the Troubleshooting guide for debugging information.