Expanding is the task of taking a short piece of text,
such as a set of instructions or a list of topics,
and having the large language model generate a
longer piece of text, such as an email or
an essay about some topic. There are some great uses of this,
such as if you use a large language model as a brainstorming partner.
But I just also want to acknowledge that
there are some problematic use cases of this,
such as if someone were to use it, they generate a large amount of spam.
So when you use these capabilities of a large language model,
please use it only in a responsible way and in
a way that helps people.
In this video we’ll go through an example of how you can
use a language model to generate a personalized
email based on some information. The
email is kind of self-proclaimed to be from an AI
bot which as Andrew mentioned is very important.
We’re also going to use another one of the models input
parameters called temperature and this kind of allows
you to vary the kind of degree of exploration and variety in
the kind of models responses. So let’s get into it.
So before we get started we’re going to kind of
do the usual setup. So set up the OpenAI Python package and then also define
our helper function getCompletion
and now we’re going to write a custom email response to
a customer review and so given a customer review and the sentiment
we’re going to generate a custom response. Now we’re
going to use the language model to generate a custom
email to a customer based on a customer
review and the sentiment of the review. So we’ve already
extracted the sentiment
using the kind of prompts that we saw
in the inferring video
and then this is the customer review for a blender
and now we’re going to customize the reply
based on the sentiment.
And so here the instruction is you are a customer service AI
assistant your task is to send an email reply to about your
customer given the customer email delimited
by three backticks generate a reply to thank the customer for their
review. If the sentiment is positive or neutral thank
them for their review. If the sentiment is
negative apologize and suggest that they can reach
out to customer service. Make sure to use
specific details from the review write in a
concise and professional tone and sign the email
as AI customer agent. And when you’re using a language model to
generate text that you’re going to show to a user it’s very important
to have this kind of transparency and let
the user know that the text they’re seeing was generated
And then we’ll just input the customer review
and the review sentiment. And also note that this part isn’t necessarily
important because we could actually use this prompt to
also extract the review sentiment and then in a follow-up step write
the email. But just for the sake of the example, well, we’ve already
extracted the sentiment from the review. And so, here we have a
response to the customer. It kind of addresses
details that the customer mentioned in their review.
And kind of as we instructed, suggests that they reach
out to customer service because this is just
an AI customer service agent.
Next, we’re going to use a parameter of the language
model called temperature that will allow us to
change the kind of variety of the model’s responses. So you can kind of
think of temperature as the degree of exploration
or kind of randomness of the model. And so, for
this particular phrase, my favourite food is the
kind of most likely next word that the
model predicts is pizza and the kind of next to most likely
it suggests are sushi and tacos. And so, at
a temperature of zero, the model will always choose the
most likely next word, which in this case is pizza, and
at a higher temperature,
it will kind of also choose one of the less likely words
and at an even higher temperature, it might even choose tacos,
which only kind of has a five percent
chance of being chosen.
And you can imagine that kind of,
as the model continues this final response, so my favourite food is
pizza and it kind of continues to generate more words,
this response will kind of diverge from the response,
the first response, which is my favourite food is tacos.
And so, as the kind of model continues,
these two responses will become more and more different.
In general, when building applications
where you want a kind of predictable response,
I would recommend using temperature zero.
Throughout all of these videos, we’ve been using temperature zero and
I think that if you’re trying to build a system that is
reliable and predictable, you should go with this. If you’re trying to
kind of use the model in a more creative way where you
might kind of want
a kind of wider variety of different outputs,
you might want to use a higher temperature. So,
now let’s take this same prompt that we just used and let’s try
generating an email, but let’s use a higher temperature. So, in our getCompletion
function that we’ve been using throughout the videos, we have kind of
specified a model and then also a temperature,
but we’ve kind of set them to default. So, now let’s try varying the
So, we’ll use the prompt and then
let’s try temperature 0.7.
And so, with temperature 0, every time you execute the same prompt,
you should expect the same completion. Whereas with temperature 0.7, you’ll get
a different output every time. So, here we have
our email, and as you can see, it’s different to the email that we
kind of received previously. And let’s just execute it again, to show
that we’ll get a different email again.
And here we have another different email. And so, I recommend that
you kind of play around with temperature yourself.
Maybe you could pause the video now and
try this prompt with a variety of different temperatures,
just to see how the outputs vary.
So, to summarise, at higher temperatures,
the outputs from the model are kind of more random.
You can almost think of it as that at higher temperatures,
the assistant is more distractible, but maybe more creative.
In the next video, we’re going to talk more about the
Chat Completions Endpoint format, and
how you can create a custom chatbot using this format.