Chat

Agents with the chat capability can answer questions with tailored responses based on topics, personas, or data.

​

Building an agent with chat

To build an agent with chat capabilities, choose the Chat option after clicking Build an agent in AI Studio.

​

Writing a welcome message

Next, create a welcome message. A welcome message is the first message your users will see. Greet them, tell them how to use the chat, and include any special instructions or anything else they should know.

​

Creating an avatar

Choose an avatar for your chat. This can be your company logo or any other image you prefer.

​

Choosing a mode

To choose the right mode for your chat you need to decide how your users will interact with it. If you want them to ask general questions, choose the General chat mode. If you want them to ask specific questions about your company’s data, choose the Knowledge Graph mode.

Here is a detailed breakdown:

​

General chat mode

• Use this mode to ideate or create content

​

Knowledge Graph mode

• Use this mode to get answers from your company’s data
• Before you can use Knowledge Graph mode, you need to set up a Knowledge Graph with all the relevant files for your use case. You can do this from the side navigation bar. You won’t be able to build a chat with a Knowledge Graph if no Knowledge Graph exists. Read how to set it up here.

​

Document mode

• Use this mode to answer questions about specific documents
• You can specify the number, types, and sources of documents you want to allow users to upload. You can also choose to allow users to add URLs or copy and paste text.

You’ll need to select at least one mode. If you’re not sure which one to choose, select the General chat mode.

​

Providing instructions

All of the modes allow you to provide instructions. Instructions are the system messages that reach the LLM and can be used to provide context or structure to how your chat responds to requests.

For example, you can use instructions to:

1. Request answers in a specific language by providing examples.
2. Patch stale data in your Knowledge Graph that’s hard to retrieve by providing additional information.
3. Provide context about the users and how to address them.
4. Set limits on the topics that can be answered.

Your instructions will tell the LLM what answers to generate and how to format them.