Purely generative tasks are not suited for Dialogflow or for that matter any other intent-based chatbot framework. Brainstorming new ideas For example, if you want to brainstorm new ideas based on some text input. This is a purely generative task, where you ask a bot to construct entirely new sentences based on some prompt. This…
As I mentioned in the previous lesson, GPT is very well suited for extractive question answering. So you should use ChatGPT for such tasks, and it will very likely perform much better than other options in those scenarios. But there are also some situations where you should not use GPT. Reasoning OUTSIDE the code layer…
As I have already explained earlier, at the moment GPT works best for extractive question answering where you feed a whole bunch of questions and answers (or just regular paragraphs) and ask GPT a question based on the information provided. But once you go past extractive Q&A, GPT is still not a very mature tool,…
Google recently introduced Generative Agents in Dialogflow CX. It is quite likely the best way to add a GPT-like bot to your website. When should you use it? I recommend using Generative Dialogflow CX in all your CX bots as long as you remember that not just generative Dialogflow CX, but all large language models…
If you are deciding between Dialogflow ES and Dialogflow CX, here are some rules of thumb you can use. I recommend using Dialogflow CX in the following cases. You need to build complex multi-turn conversations If you use the slot filling and follow up intent features in Dialogflow ES, you will almost certainly benefit from…
If you are deciding between Dialogflow ES and Dialogflow CX, here are some rules of thumb you can use. I recommend using Dialogflow ES in the following cases. You are building a large FAQ chatbot A large FAQ chatbot is not likely to answer follow up questions. Usually these provide links to other resources etc….
In the previous lesson, I explained how “Extractive Question Answering” which is more suited to ChatGPT, differs from “Intent based Question Answering” which is more suited to Dialogflow. In this lesson, I explain how this makes Dialogflow a better choice for certain tasks. In my view a) Dialogflow is much more suitable for non-programmers b)…
In the previous lesson, I mentioned the difference between “Extractive Question Answering” (this is where ChatGPT really shines) and “Intent-based Question Answering” (this is much more suited to Dialogflow). In this lesson, I will explain the difference. Dialogflow ES is based on the following building blocks: intent mapping – it can map the user’s utterance…