🆕 GPT-3 [Beta]
GPT-3 uses state-of-the-art NLP technology to generate responses in your chatbot, by providing answers that fit the context of the conversation. Make your chatbot next-generation!
GPT-3 is a beta integration and is not recommended for production use cases. Read more about this in the section about GPT-3 limitations.
This documentation page covers:
GPT is a series of advanced Natural Language Processing systems developed by OpenAI that allow you to execute several text-based tasks.
The GPT-3 integration allows you to generate responses in your chatbot. As a bot builder or conversation designer, all you need to do is to tell GPT-3 the right query that defines the kind of answer that you would like, and GPT-3 will make it up for you!
To be able to use GPT-3 on Chatlayer, you will need to set up the GPT integration, then use this integration inside bot dialogs.
Using the GPT-3 integration means that your data is sent to OpenAI services which are based in the United States. Make sure you understand the OpenAI terms of service and implications. Use GPT-3 in production bots with caution, Chatlayer is not held responsible for generated content.
Here is a video we made about how and why you could bring value to your bot if you use GPT.
How to use GPT integration inside your Chatlayer chatbot.mp4
5MB
Binary
Before being able to use GPT-3 inside dialogs, you need to connect a GPT-3 account to the GPT-3 integration on Chatlayer. For this, you might require an OpenAI API key.
Chatlayer provides customers with its own OpenAI API key to use GPT-3 with a limit of 100 messages per bot. This means that from the 101st message, GPT-3 will stop generating and send errors. If you wish to be able to use an unlimited amount of GPT-generated messages, you will need to create your own API key on the OpenAI's website.
To connect your chatbot with GPT-3:
- On your Chatlayer home page, go to
Integrations
The Integration tab is on the left-hand side of your Chatlayer home page.
- Search for "GPT-3" in the search bar
Search for GPT-3 and you will find the GPT-3 integration ready to be configured
- Click on the integration to open it
View of the GPT-3 integration when open.
- Click on
+ Add Accountto start connecting your GPT-3 account with the GPT-3 integration - This will open a pop-up in which you will need to enter a Chatlayer Access token:
Pop-up to provide the necessary credentials for connecting GPT-3 to Chatlayer
- Paste your access token in the
Access tokenfield
- Under
Display name, write an identifier that can be later used to select this specific access token when using the GPT-3 integration inside a bot. In this example, we have used the identifier Chatlayer Example GPT-3. - Optionally, you can provide an
OpenAI API key.
To try the GPT-3 integration, Chatlayer offers 100 messages per bot. If this suits you, you can leave the OpenAI key field empty. Yet if you would like to go unlimited in the your number of GPT-generated messages, you will need to get your own API key on the OpenAI's website.
- Click on
Submitwhen you're done - The GPT-3 account should now be visible under the
Connected Accountstab. Note that the word "Auth" was automatically added in front of the "Display Name".
You can see your GPT-3 account under the Connected Accounts tab.
You've set up your GPT account and would like to jump straight to bot building? We've got you covered with our GPT-3 template bot. Give it a go!
Your GPT-3 integration is set up! Now it's time to use it inside the conversation.
You will need to do two things so that your customers can interact with GPT-3:
- 1.
- 2.Display a GPT-3 response within another dialog
To generate a GPT-3 response:
- Search for the GPT-3 integration in the search bar and select it
Search for the GPT-3 integration in the Action dialog toolbar and select it.
- Under
GPT-3 account, select your GPT account that you connected to Chatlayer earlier. In our case, it is called "Auth Chatlayer Example GPT-3".
Enter your GPT-3 account to connect it to the Action dialog.
- Select the action to execute, called "GPT-3 response". This means the action will send the conversation to GPT-3 and retrieve a response.
Select the action for the GPT-3 integration.
- Now, give to GPT-3 the required information to be able to generate an answer. These are called the
Action fields:- Fill the
Bot description, which is a small depiction of what your bot is about. For instance, a restaurant bot. - Fill the
Bot prompt, which is a description of the response that you would like GPT-3 to generate. Example: generate a personalized message to apologize for an inconvenience.
Be mindful: the longer you make your bot description or bot prompt, the longer it will take to get a response from GPT-3.
Fill the Action fields so that GPT-3 gets all the necessary information to generate a response.
- Click on
Createto save your GPT-3 integrated Action dialog
You have made an Action dialog that uses GPT-3 to generate a response based on your chatbot description! Now, let's see how we can display that generated response within the conversation.
The generated answer from GPT-3 is available on the session data after executing the above Action dialog. This response is saved under the
{apps.gpt-3.gpt.text} variable.To display the GPT-3 response in the conversation:
- Add a text field and fill it with the
{apps.gpt-3.gpt.text}variable
Add the variable that holds the generated response from GPT-3 to a text field to display it in your conversation.
You know now how to set up an Action dialogs that generates a GPT-3 response, and how to display this response within a dialog.
In the next sections, we will take a use-case to exemplify how you can use GPT-3 for your bot.
One way to use the GPT-3 integration is as a fallback message for when your bot didn't understand the user question.
Once you've created a bot, go into your
General flow, and open the Not Understood dialog. From there, we will modify the Not Understood dialog so that it uses the GPT-3 integration: - Delete the text message inside the
Not Understooddialog by clicking on the bin icon - In the
Go Tofield, create a new Action dialog that you will call "Generate GPT-3 response", then save your changes - Open the
Generate GPT-3 responsedialog that you have just created and configure this Action dialog so that it integrates GPT-3 - In the Go To field, create a Bot message dialog and call it "Display GPT-3 response" , then save your changes
- Open the
Display GPT-3 responsedialog and add the{apps.gpt-3.gpt.text}variable inside the text field
How your fallback flow should look like if you use GPT-3 as a Not Understood message
If you talk to your bot now and ask something the bot doesn't know, the "Not Understood" dialogue state should be triggered. Next, GPT-3 will be called and the response will be displayed to you.
Example of a GPT-3 fallback flow where GPT-3 was asked to generate an apology for an inconvenience in a restaurant bot.
GPT-3 is able to read the whole conversation between your customer and the bot, which means that it can generate text based on the context of the conversation.
As for an example of contextualized GPT-3 responses:
- Create an intent that will trigger a GPT-3 response. In this example, we created an
intent_not_deliveredintent. - Create an action dialog that generates a GPT answer and connect it to a dialog that displays it, as explained in the tutorial above. In our example, we have queried the following text to GPT-3:
Example of action fields for a personalized apology response made by GPT-3
- Do the same for any other dialog that you would like to have personalized. In our example, we have created a chitchat.tell_a_joke intent that triggers a GPT-generated response of a joke that takes into account the context above:
-
Example of action fields for a personalized joke made by GPT-3 and based on the context of the conversation - Your can now have more contextualized interactions with your customers!
Conversation sample of a flow that uses GPT-3 to generate a personalized apology then a joke
GPT-3 is a generative AI model built by OpenAI, which is located in the US. Because it is generative, we do not control what GPT-3 creates. Depending on the input it receives, the answer can either be very good, contain wrong info or even be offensive. Therefore, we do not recommend GPT-3 be used in production (i.e. a customer facing bot).
We do not recommend the GPT-3 integration to be used in production (i.e. a customer facing bot). Still, if you want to use it in production anyway you should use your own OpenAI API key. Please also check the OpenAI terms of service to understand the implications of using OpenAI services.
We are eager to receive your feedback if you found a valuable and safe production use case. Please contact us here. 🙏
Last modified 23d ago