ChatGPT Prompt Engineering

ChatGPT is the product of OpenAI so let’s first get an API key for OpenAI/ChatGPT

Setup

  1. Create an Openai account here
  2. Login
  3. Documentation is found here
  4. Create a new project: “xxxxx”
  5. Manage projects: you have a new ID for the project
  6. Left menu > scroll down to API Keys
  7. Name it optional, it will be tied to the project, if the project is removed the key is disabled

ChatGPT API Key

Key is retrieved from above

Install Packages

  • Make sure openai is installed in your python
pip install openai
pip install python-dotenv
# Done
...
Downloading pydantic_core-2.27.1-cp311-none-win_amd64.whl (2.0 MB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2.0/2.0 MB 6.1 MB/s eta 0:00:00
Downloading tqdm-4.67.1-py3-none-any.whl (78 kB)
Downloading annotated_types-0.7.0-py3-none-any.whl (13 kB)
Installing collected packages: tqdm, pydantic-core, jiter, distro, annotated-types, pydantic, openai
Successfully installed annotated-types-0.7.0 distro-1.9.0 jiter-0.8.0 openai-1.57.0 pydantic-2.10.3 pydantic-core-2.27.1 tqdm-4.67.1

Since I am using Rstudio I will need to load the reticulate package to use python

library(reticulate)

Now I can install the needed packages to access the openai python package

Helper Function

Throughout this section, we will use OpenAI’s gpt-3.5-turbo model and the chat completions endpoint.

This helper function will make it easier to use prompts and look at the generated outputs.
Note: In June 2023, OpenAI updated gpt-3.5-turbo. The results you see in the notebook may be slightly different than those in the video. Some of the prompts have also been slightly modified to product the desired results.

Helper Function

  • Will take in the prompt and return the result for that prompt
def get_completion(prompt, model="gpt-3.5-turbo"):
    messages = [{"role": "user", "content": prompt}]
    response = client.chat.completions.create(
        model=model,
        messages=messages,
        temperature=0
    )
    return response.choices[0].message.content

Prompting Principles

Strategy Context optimization LLM optimization
Write clear instructions X
Split complex tasks into simpler subtasks X X
Give GPTs time to “think” X
Test changes systematically X X
Provide reference text X
Use external tools X

Clear Specific Instructions

Use delimiters

  • To clearly indicate distinct parts of the input
  • Delimiters can be anything like: ```, “““, < >, <tag> </tag>, :
  • The prompt spells out what we want it to do
  • It returns a text
  • Using ““” at the start and end will clarify to the model what to follow and where instructions end and not mistaken the start and end with instructions
text = f"""
You should express what you want a model to do by \ 
providing instructions that are as clear and \ 
specific as you can possibly make them. \ 
This will guide the model towards the desired output, \ 
and reduce the chances of receiving irrelevant \ 
or incorrect responses. Don't confuse writing a \ 
clear prompt with writing a short prompt. \ 
In many cases, longer prompts provide more clarity \ 
and context for the model, which can lead to \ 
more detailed and relevant outputs.
"""
prompt = f"""
Summarize the text delimited by triple backticks \ 
into a single sentence.
"""
response = get_completion(prompt)
print(response)

Ask for Structured Output

  • Ask for HTML or Json output
prompt = f"""
Generate a list of three made-up book titles along \ 
with their authors and genres. 
Provide them in JSON format with the following keys: 
book_id, title, author, genre.
"""
response = get_completion(prompt)
print(response)

Check if Conditions are satisfied

  • Ask the model to check if assumptions made are satisfied before giving the response
  • Also give it instructions how to handle the conditions if not satisfied
text_1 = f"""
Making a cup of tea is easy! First, you need to get some \ 
water boiling. While that's happening, \ 
grab a cup and put a tea bag in it. Once the water is \ 
hot enough, just pour it over the tea bag. \ 
Let it sit for a bit so the tea can steep. After a \ 
few minutes, take out the tea bag. If you \ 
like, you can add some sugar or milk to taste. \ 
And that's it! You've got yourself a delicious \ 
cup of tea to enjoy.
"""
prompt = f"""
You will be provided with text delimited by triple quotes. 
If it contains a sequence of instructions, \ 
re-write those instructions in the following format:

Step 1 - ...
Step 2 - …
…
Step N - …

If the text does not contain a sequence of instructions, \ 
then simply write \"No steps provided.\"

\"\"\"{text_1}\"\"\"
"""
response = get_completion(prompt)
print("Completion for Text 1:")
print(response)

  • Let’s use the same prompt on a different input

  • It gives us No steps provided

    text_2 = f"""
The sun is shining brightly today, and the birds are \
singing. It's a beautiful day to go for a \ 
walk in the park. The flowers are blooming, and the \ 
trees are swaying gently in the breeze. People \ 
are out and about, enjoying the lovely weather. \ 
Some are having picnics, while others are playing \ 
games or simply relaxing on the grass. It's a \ 
perfect day to spend time outdoors and appreciate the \ 
beauty of nature.
"""
prompt = f"""
You will be provided with text delimited by triple quotes. 
If it contains a sequence of instructions, \ 
re-write those instructions in the following format:

Step 1 - ...
Step 2 - …
…
Step N - …

If the text does not contain a sequence of instructions, \ 
then simply write \"No steps provided.\"

\"\"\"{text_2}\"\"\"
"""
response = get_completion(prompt)
print("Completion for Text 2:")
print(response)

Few-Shot Prompting

  • Give examples of competing tasks
  • then ask model to perform the actual task
prompt = f"""
Your task is to answer in a consistent style.

<child>: Teach me about patience.

<grandparent>: The river that carves the deepest \ 
valley flows from a modest spring; the \ 
grandest symphony originates from a single note; \ 
the most intricate tapestry begins with a solitary thread.

<child>: Teach me about resilience.
"""
response = get_completion(prompt)
print(response)

Other Tactics

Give Model Time to Think

Specify Steps Required

text = f"""
In a charming village, siblings Jack and Jill set out on \ 
a quest to fetch water from a hilltop \ 
well. As they climbed, singing joyfully, misfortune \ 
struck—Jack tripped on a stone and tumbled \ 
down the hill, with Jill following suit. \ 
Though slightly battered, the pair returned home to \ 
comforting embraces. Despite the mishap, \ 
their adventurous spirits remained undimmed, and they \ 
continued exploring with delight.
"""
# example 1
prompt_1 = f"""
Perform the following actions: 
1 - Summarize the following text delimited by triple \
backticks with 1 sentence.
2 - Translate the summary into French.
3 - List each name in the French summary.
4 - Output a json object that contains the following \
keys: french_summary, num_names.

Separate your answers with line breaks.

Text:
"""
response = get_completion(prompt_1)
print("Completion for prompt 1:")
print(response)

Ask for Specific Format

prompt_2 = f"""
Your task is to perform the following actions: 
1 - Summarize the following text delimited by 
  <> with 1 sentence.
2 - Translate the summary into French.
3 - List each name in the French summary.
4 - Output a json object that contains the 
  following keys: french_summary, num_names.

Use the following format:
Text: <text to summarize>
Summary: <summary>
Translation: <summary translation>
Names: <list of names in summary>
Output JSON: <json with summary and num_names>

Text: <{text}>
"""
response = get_completion(prompt_2)
print("\nCompletion for prompt 2:")
print(response)

Let it work out a solution before finishing

  • The solution is wrong
prompt = f"""
Determine if the student's solution is correct or not.

Question:
I'm building a solar power installation and I need \
 help working out the financials. 
- Land costs $100 / square foot
- I can buy solar panels for $250 / square foot
- I negotiated a contract for maintenance that will cost \ 
me a flat $100k per year, and an additional $10 / square \
foot
What is the total cost for the first year of operations 
as a function of the number of square feet.

Student's Solution:
Let x be the size of the installation in square feet.
Costs:
1. Land cost: 100x
2. Solar panel cost: 250x
3. Maintenance cost: 100,000 + 100x
Total cost: 100x + 250x + 100,000 + 100x = 450x + 100,000
"""
response = get_completion(prompt)
print(response)
  • So if we ask it to work out the answer it will come out to the right answer
prompt = f"""
Your task is to determine if the student's solution \
is correct or not.
To solve the problem do the following:
- First, work out your own solution to the problem including the final total. 
- Then compare your solution to the student's solution \ 
and evaluate if the student's solution is correct or not. 
Don't decide if the student's solution is correct until 
you have done the problem yourself.

Use the following format:
Question:
question here
Student's solution:
student's solution here
Actual solution:
steps to work out the solution and your solution here
Is the student's solution the same as actual solution \
just calculated:
yes or no
Student grade:
correct or incorrect

Question:
I'm building a solar power installation and I need help \
working out the financials. 
- Land costs $100 / square foot
- I can buy solar panels for $250 / square foot
- I negotiated a contract for maintenance that will cost \
me a flat $100k per year, and an additional $10 / square \
foot
What is the total cost for the first year of operations \
as a function of the number of square feet.
Student's solution:
Let x be the size of the installation in square feet.
Costs:
1. Land cost: 100x
2. Solar panel cost: 250x
3. Maintenance cost: 100,000 + 100x
Total cost: 100x + 250x + 100,000 + 100x = 450x + 100,000
Actual solution:
"""
response = get_completion(prompt)
print(response)

Subtasks

Just as it is good practice in software engineering to decompose a complex system into a set of modular components, the same is true of tasks submitted to a language model. Complex tasks tend to have higher error rates than simpler tasks. Furthermore, complex tasks can often be re-defined as a workflow of simpler tasks in which the outputs of earlier tasks are used to construct the inputs to later tasks.

Tactics:

  • Use intent classification to identify the most relevant instructions for a user query
  • For dialogue applications that require very long conversations, summarize or filter previous dialogue
  • Summarize long documents piecewise and construct a full summary recursively

Hallucinations

  • If it wasn’t trained on something it will fabricate results by guessing

  • Language models can confidently invent fake answers, especially when asked about esoteric topics or for citations and URLs. In the same way that a sheet of notes can help a student do better on a test, providing reference text to these models can help in answering with fewer fabrications.

    Tactics:

    • Instruct the model to answer using a reference text

    • Instruct the model to answer with citations from a reference text

Compensate for the weaknesses of the model by feeding it the outputs of other tools. For example, a text retrieval system (sometimes called RAG or retrieval augmented generation) can tell the model about relevant documents. A code execution engine like OpenAI’s Code Interpreter can help the model do math and run code. If a task can be done more reliably or efficiently by a tool rather than by a language model, offload it to get the best of both.

Tactics:

  • Use embeddings-based search to implement efficient knowledge retrieval
  • Use code execution to perform more accurate calculations or call external APIs
  • Give the model access to specific functions

Iterative Prompt Development

You’ll most likely not going to achieve your results on the first try, so iteration is a part of prompting.

Generate Marketing Description

In this example we’ll try to create a marketing description for some products. Let’s start with the first prompt and edit till we get close.

We need to create a fact sheet for a chair for an online description

Factsheet

fact_sheet_chair = """
OVERVIEW
- Part of a beautiful family of mid-century inspired office furniture, 
including filing cabinets, desks, bookcases, meeting tables, and more.
- Several options of shell color and base finishes.
- Available with plastic back and front upholstery (SWC-100) 
or full upholstery (SWC-110) in 10 fabric and 6 leather options.
- Base finish options are: stainless steel, matte black, 
gloss white, or chrome.
- Chair is available with or without armrests.
- Suitable for home or business settings.
- Qualified for contract use.

CONSTRUCTION
- 5-wheel plastic coated aluminum base.
- Pneumatic chair adjust for easy raise/lower action.

DIMENSIONS
- WIDTH 53 CM | 20.87”
- DEPTH 51 CM | 20.08”
- HEIGHT 80 CM | 31.50”
- SEAT HEIGHT 44 CM | 17.32”
- SEAT DEPTH 41 CM | 16.14”

OPTIONS
- Soft or hard-floor caster options.
- Two choices of seat foam densities: 
 medium (1.8 lb/ft3) or high (2.8 lb/ft3)
- Armless or 8 position PU armrests 

MATERIALS
SHELL BASE GLIDER
- Cast Aluminum with modified nylon PA6/PA66 coating.
- Shell thickness: 10 mm.
SEAT
- HD36 foam

COUNTRY OF ORIGIN
- Italy
"""

Prompt 1

prompt = f"""
Your task is to help a marketing team create a 
description for a retail website of a product based 
on a technical fact sheet.

Write a product description based on the information 
provided in the technical specifications delimited by 
triple backticks.

Technical specifications: ```{fact_sheet_chair}```
"""
response = get_completion(prompt)
print(response)

Response 1

  • It’s too long so let’s limit the output

Prompt 2

prompt = f"""
Your task is to help a marketing team create a 
description for a retail website of a product based 
on a technical fact sheet.

Write a product description based on the information 
provided in the technical specifications delimited by 
triple backticks.

Use at most 50 words.

Technical specifications: ```{fact_sheet_chair}```
"""
response = get_completion(prompt)
print(response)

Introducing our versatile and stylish mid-century office chair, available in a range of colors and finishes. With adjustable height and comfortable upholstery options, this chair is perfect for both home and business use. Made in Italy with quality materials, it's a perfect blend of form and function.

Let’s see how long it is:

len(response.split())
# OUTPUT 
47

Change the focus

Prompt 3

  • We want a more technical description
prompt = f"""
Your task is to help a marketing team create a 
description for a retail website of a product based 
on a technical fact sheet.

Write a product description based on the information 
provided in the technical specifications delimited by 
triple backticks.

The description is intended for furniture retailers, 
so should be technical in nature and focus on the 
materials the product is constructed from.

Use at most 50 words.

Technical specifications: ```{fact_sheet_chair}```
"""
response = get_completion(prompt)
print(response)


Introducing our versatile and stylish office chair, part of a mid-century inspired furniture collection. Choose from a variety of shell colors and base finishes to suit your space. Constructed with durable materials like cast aluminum and HD36 foam, this chair is perfect for both home and business settings. Made in Italy.

Prompt 4

  • How about if we want to target retailers as if we were a wholesaler
  • We want to include the product id
prompt = f"""
Your task is to help a marketing team create a 
description for a retail website of a product based 
on a technical fact sheet.

Write a product description based on the information 
provided in the technical specifications delimited by 
triple backticks.

The description is intended for furniture retailers, 
so should be technical in nature and focus on the 
materials the product is constructed from.

At the end of the description, include every 7-character 
Product ID in the technical specification.

Use at most 50 words.

Technical specifications: ```{fact_sheet_chair}```
"""
response = get_completion(prompt)
print(response)

Introducing our versatile and stylish office chair, part of a mid-century inspired furniture collection. Choose from a variety of shell colors and base finishes to suit your space. Constructed with a durable aluminum base and high-density foam seat for comfort. Perfect for home or business use. 

Product IDs: SWC-100, SWC-110

Prompt 5

  • What if we need more of the description of the table
  • We want it to output in HTML form
prompt = f"""
Your task is to help a marketing team create a 
description for a retail website of a product based 
on a technical fact sheet.

Write a product description based on the information 
provided in the technical specifications delimited by 
triple backticks.

The description is intended for furniture retailers, 
so should be technical in nature and focus on the 
materials the product is constructed from.

At the end of the description, include every 7-character 
Product ID in the technical specification.

After the description, include a table that gives the 
product's dimensions. The table should have two columns.
In the first column include the name of the dimension. 
In the second column include the measurements in inches only.

Give the table the title 'Product Dimensions'.

Format everything as HTML that can be used in a website. 
Place the description in a <div> element.

Technical specifications: ```{fact_sheet_chair}```
"""

response = get_completion(prompt)
print(response)

Introducing our latest addition to the mid-century inspired office furniture collection - the versatile and stylish office chair. This chair is designed to elevate any workspace, whether it be at home or in a business setting. With a variety of shell colors and base finishes to choose from, you can customize this chair to fit your aesthetic perfectly.

The construction of this chair is top-notch, featuring a 5-wheel plastic coated aluminum base for stability and mobility. The pneumatic chair adjust allows for easy raise and lower action, ensuring maximum comfort throughout the day.

Constructed with high-quality materials, the shell base glider is made of cast aluminum with a modified nylon PA6/PA66 coating, providing durability and style. The seat is filled with HD36 foam, offering a comfortable seating experience.

Product ID: SWC-100

Product Dimensions:

WIDTH 20.87”
DEPTH 20.08”
HEIGHT 31.50”
SEAT HEIGHT 17.32”
SEAT DEPTH 16.14”

Summarizing

We can summarize articles so we don’t take the time to read an entire article.

  • Let’s summarize reviews of all the customers

Input

prod_review = """
Got this panda plush toy for my daughter's birthday, \
who loves it and takes it everywhere. It's soft and \ 
super cute, and its face has a friendly look. It's \ 
a bit small for what I paid though. I think there \ 
might be other options that are bigger for the \ 
same price. It arrived a day earlier than expected, \ 
so I got to play with it myself before I gave it \ 
to her.
"""

Summarize 1

  • Sum with a word/sentence/char limit
prompt = f"""
Your task is to generate a short summary of a product \
review from an ecommerce site. 

Summarize the review below, delimited by triple 
backticks, in at most 30 words. 

Review: ```{prod_review}```
"""

response = get_completion(prompt)
print(response)

# Soft, cute panda plush toy loved by daughter, but smaller than expected for the price. Arrived early, friendly face.

Summarize 2

  • Sum with a focus on shipping and delivery
prompt = f"""
Your task is to generate a short summary of a product \
review from an ecommerce site to give feedback to the \
Shipping deparmtment. 

Summarize the review below, delimited by triple 
backticks, in at most 30 words, and focusing on any aspects \
that mention shipping and delivery of the product. 

Review: ```{prod_review}```
"""

response = get_completion(prompt)
print(response)

# The customer was pleased with the early delivery of the panda plush toy, but felt it was slightly small for the price paid.

Summarize 3

  • Sum with a focus on price and value
prompt = f"""
Your task is to generate a short summary of a product \
review from an ecommerce site to give feedback to the \
pricing deparmtment, responsible for determining the \
price of the product.  

Summarize the review below, delimited by triple 
backticks, in at most 30 words, and focusing on any aspects \
that are relevant to the price and perceived value. 

Review: ```{prod_review}```
"""

response = get_completion(prompt)
print(response)

# The panda plush toy is loved for its softness and cuteness, but some customers feel it's a bit small for the price.

Extract / Summarize

  • Let’s try extracting instead of summarizing
prompt = f"""
Your task is to extract relevant information from \ 
a product review from an ecommerce site to give \
feedback to the Shipping department. 

From the review below, delimited by triple quotes \
extract the information relevant to shipping and \ 
delivery. Limit to 30 words. 

Review: ```{prod_review}```
"""

response = get_completion(prompt)
print(response)

# Feedback: The product arrived a day earlier than expected, which was a pleasant surprise. Consider offering larger options for the same price to improve customer satisfaction.

Summarize Multiple Reviews

review_1 = prod_review 

# review for a standing lamp
review_2 = """
Needed a nice lamp for my bedroom, and this one \
had additional storage and not too high of a price \
point. Got it fast - arrived in 2 days. The string \
to the lamp broke during the transit and the company \
happily sent over a new one. Came within a few days \
as well. It was easy to put together. Then I had a \
missing part, so I contacted their support and they \
very quickly got me the missing piece! Seems to me \
to be a great company that cares about their customers \
and products. 
"""

# review for an electric toothbrush
review_3 = """
My dental hygienist recommended an electric toothbrush, \
which is why I got this. The battery life seems to be \
pretty impressive so far. After initial charging and \
leaving the charger plugged in for the first week to \
condition the battery, I've unplugged the charger and \
been using it for twice daily brushing for the last \
3 weeks all on the same charge. But the toothbrush head \
is too small. I’ve seen baby toothbrushes bigger than \
this one. I wish the head was bigger with different \
length bristles to get between teeth better because \
this one doesn’t.  Overall if you can get this one \
around the $50 mark, it's a good deal. The manufactuer's \
replacements heads are pretty expensive, but you can \
get generic ones that're more reasonably priced. This \
toothbrush makes me feel like I've been to the dentist \
every day. My teeth feel sparkly clean! 
"""

# review for a blender
review_4 = """
So, they still had the 17 piece system on seasonal \
sale for around $49 in the month of November, about \
half off, but for some reason (call it price gouging) \
around the second week of December the prices all went \
up to about anywhere from between $70-$89 for the same \
system. And the 11 piece system went up around $10 or \
so in price also from the earlier sale price of $29. \
So it looks okay, but if you look at the base, the part \
where the blade locks into place doesn’t look as good \
as in previous editions from a few years ago, but I \
plan to be very gentle with it (example, I crush \
very hard items like beans, ice, rice, etc. in the \ 
blender first then pulverize them in the serving size \
I want in the blender then switch to the whipping \
blade for a finer flour, and use the cross cutting blade \
first when making smoothies, then use the flat blade \
if I need them finer/less pulpy). Special tip when making \
smoothies, finely cut and freeze the fruits and \
vegetables (if using spinach-lightly stew soften the \ 
spinach then freeze until ready for use-and if making \
sorbet, use a small to medium sized food processor) \ 
that you plan to use that way you can avoid adding so \
much ice if at all-when making your smoothie. \
After about a year, the motor was making a funny noise. \
I called customer service but the warranty expired \
already, so I had to buy another one. FYI: The overall \
quality has gone done in these types of products, so \
they are kind of counting on brand recognition and \
consumer loyalty to maintain sales. Got it in about \
two days.
"""

reviews = [review_1, review_2, review_3, review_4]
for i in range(len(reviews)):
    prompt = f"""
    Your task is to generate a short summary of a product \ 
    review from an ecommerce site. 

    Summarize the review below, delimited by triple \
    backticks in at most 20 words. 

    Review: ```{reviews[i]}```
    """

    response = get_completion(prompt)
    print(i, response, "\n")
    
0 Summary: 
Adorable panda plush loved by daughter, but small for price. Arrived early, soft and cute. 

1 Great lamp with storage, fast delivery, excellent customer service for missing parts. Company cares about customers. 

2 Impressive battery life, small brush head, good deal for $50, generic replacement heads available, leaves teeth feeling clean. 

3 17-piece system on sale for $49, prices increased later. Base quality not as good, motor issues after a year.

Inferring

We can extract sentiments from text. For example we need to get an idea of what the sentiments are in customer reviews

Sentiment Extraction

Product Review

lamp_review = """
Needed a nice lamp for my bedroom, and this one had \
additional storage and not too high of a price point. \
Got it fast.  The string to our lamp broke during the \
transit and the company happily sent over a new one. \
Came within a few days as well. It was easy to put \
together.  I had a missing part, so I contacted their \
support and they very quickly got me the missing piece! \
Lumina seems to me to be a great company that cares \
about their customers and products!!
"""

Sentiment Prompt

prompt = f"""
What is the sentiment of the following product review, 
which is delimited with triple backticks?

Review text: '''{lamp_review}'''
"""
response = get_completion(prompt)
print(response)

# The sentiment of the review is positive. The reviewer is satisfied with the lamp they purchased, mentioning the additional storage, reasonable price, fast delivery, good customer service, and ease of assembly. They also praise the company for caring about their customers and products.

Shorten Response

prompt = f"""
What is the sentiment of the following product review, 
which is delimited with triple backticks?

Give your answer as a single word, either "positive" \
or "negative".

Review text: '''{lamp_review}'''
"""
response = get_completion(prompt)
print(response)

# Positive

Identify Types of Emotions

prompt = f"""
Identify a list of emotions that the writer of the \
following review is expressing. Include no more than \
five items in the list. Format your answer as a list of \
lower-case words separated by commas.

Review text: '''{lamp_review}'''
"""
response = get_completion(prompt)
print(response)

# happy, satisfied, grateful, impressed, content

Identify Anger

prompt = f"""
Is the writer of the following review expressing anger?\
The review is delimited with triple backticks. \
Give your answer as either yes or no.

Review text: '''{lamp_review}'''
"""
response = get_completion(prompt)
print(response)

# No

Extract Specifics from Reviews

  • Items like company names and product names from reviews
prompt = f"""
Identify the following items from the review text: 
- Item purchased by reviewer
- Company that made the item

The review is delimited with triple backticks. \
Format your response as a JSON object with \
"Item" and "Brand" as the keys. 
If the information isn't present, use "unknown" \
as the value.
Make your response as short as possible.
  
Review text: '''{lamp_review}'''
"""
response = get_completion(prompt)
print(response)

# {
  "Item": "lamp",
  "Brand": "Lumina"
}

Perform Multiple Tasks

prompt = f"""
Identify the following items from the review text: 
- Sentiment (positive or negative)
- Is the reviewer expressing anger? (true or false)
- Item purchased by reviewer
- Company that made the item

The review is delimited with triple backticks. \
Format your response as a JSON object with \
"Sentiment", "Anger", "Item" and "Brand" as the keys.
If the information isn't present, use "unknown" \
as the value.
Make your response as short as possible.
Format the Anger value as a boolean.

Review text: '''{lamp_review}'''
"""
response = get_completion(prompt)
print(response)

# {
    "Sentiment": "positive",
    "Anger": false,
    "Item": "lamp",
    "Brand": "Lumina"
}

Inferring Topics

We can extract the topic from an article, or document. Here is the text:

Input

story = """
In a recent survey conducted by the government, 
public sector employees were asked to rate their level 
of satisfaction with the department they work at. 
The results revealed that NASA was the most popular 
department with a satisfaction rating of 95%.

One NASA employee, John Smith, commented on the findings, 
stating, "I'm not surprised that NASA came out on top. 
It's a great place to work with amazing people and 
incredible opportunities. I'm proud to be a part of 
such an innovative organization."

The results were also welcomed by NASA's management team, 
with Director Tom Johnson stating, "We are thrilled to 
hear that our employees are satisfied with their work at NASA. 
We have a talented and dedicated team who work tirelessly 
to achieve our goals, and it's fantastic to see that their 
hard work is paying off."

The survey also revealed that the 
Social Security Administration had the lowest satisfaction 
rating, with only 45% of employees indicating they were 
satisfied with their job. The government has pledged to 
address the concerns raised by employees in the survey and 
work towards improving job satisfaction across all departments.
"""

Infer Topics

prompt = f"""
Determine five topics that are being discussed in the \
following text, which is delimited by triple backticks.

Make each item one or two words long. 

Format your response as a list of items separated by commas.

Text sample: '''{story}'''
"""
response = get_completion(prompt)
print(response)

1. Survey
2. Job satisfaction
3. NASA
4. Social Security Administration
5. Government pledge
response.split(sep=',')
# Output
['1. Survey\n2. Job satisfaction\n3. NASA\n4. Social Security Administration\n5. Government pledge']

Topic Lists

It is more efficient to use the output in a list format. It is more accurate and provides a more efficient outcome.

topic_list = [
    "nasa", "local government", "engineering", 
    "employee satisfaction", "federal government"
]

Create an Alert

Setup an alert for Topic

Prompt

prompt = f"""
Determine whether each item in the following list of \
topics is a topic in the text below, which
is delimited with triple backticks.

Give your answer as follows:
item from the list: 0 or 1

List of topics: {", ".join(topic_list)}

Text sample: '''{story}'''
"""
response = get_completion(prompt)
print(response)

nasa: 1
local government: 0
engineering: 0
employee satisfaction: 1
federal government: 1
topic_dict = {i.split(': ')[0]: int(i.split(': ')[1]) for i in response.split(sep='\n')}
if topic_dict['nasa'] == 1:
    print("ALERT: New NASA story!")
    
# ALERT: New NASA story!

Transforming

Translation

ChatGPT is trained with sources in many languages. This gives the model the ability to do translation.

prompt = f"""
Translate the following English text to Spanish: \ 
"""
response = get_completion(prompt)
print(response)

# Hola, me gustaría ordenar una licuadora.
prompt = f"""
Tell me which language this is: 
"""
response = get_completion(prompt)
print(response)

# This is French
prompt = f"""
Translate the following  text to French and Spanish
and English pirate: \
"""
response = get_completion(prompt)
print(response)

French: Je veux commander un ballon de basket
Spanish: Quiero ordenar un balón de baloncesto
English: I want to order a basketball
prompt = f"""
Translate the following text to Spanish in both the \
formal and informal forms: 
'Would you like to order a pillow?'
"""
response = get_completion(prompt)
print(response)


Formal: ¿Le gustaría ordenar una almohada?
Informal: ¿Te gustaría ordenar una almohada?

Universal Translator

Imagine you are in charge of IT at a large multinational e-commerce company. Users are messaging you with IT issues in all their native languages. Your staff is from all over the world and speaks only their native languages. You need a universal translator!

Prompt

user_messages = [
  "La performance du système est plus lente que d'habitude.",  # System performance is slower than normal         
  "Mi monitor tiene píxeles que no se iluminan.",              # My monitor has pixels that are not lighting
  "Il mio mouse non funziona",                                 # My mouse is not working
  "Mój klawisz Ctrl jest zepsuty",                             # My keyboard has a broken control key
  "我的屏幕在闪烁"                                               # My screen is flashing
] 
for issue in user_messages:
    prompt = f"Tell me what language this is: ```{issue}```"
    lang = get_completion(prompt)
    print(f"Original message ({lang}): {issue}")

    prompt = f"""
    Translate the following  text to English \
    and Korean: ```{issue}```
    """
    response = get_completion(prompt)
    print(response, "\n")
    
    
Original message (This is French.): La performance du système est plus lente que d'habitude.
English: "The system performance is slower than usual."

Korean: "시스템 성능이 평소보다 느립니다." 

Original message (This is Spanish.): Mi monitor tiene píxeles que no se iluminan.
English: "My monitor has pixels that do not light up."

Korean: "내 모니터에는 빛나지 않는 픽셀이 있습니다." 

Original message (Italian): Il mio mouse non funziona
English: My mouse is not working
Korean: 내 마우스가 작동하지 않습니다 

Original message (Polish): Mój klawisz Ctrl jest zepsuty
English: My Ctrl key is broken
Korean: 제 Ctrl 키가 고장 났어요 

Original message (This is Chinese.): 我的屏幕在闪烁
English: My screen is flickering
Korean: 내 화면이 깜박거립니다

Tone Transformation

Writing can vary based on the intended audience. ChatGPT can produce different tones.

prompt = f"""
Translate the following from slang to a business letter: 
'Dude, This is Joe, check out this spec on this standing lamp.'
"""
response = get_completion(prompt)
print(response)

Dear Sir/Madam,

I am writing to bring to your attention the specifications of a standing lamp that I believe may be of interest to you. 

Sincerely,
Joe

Format Conversion

ChatGPT can translate between formats. The prompt should describe the input and output formats

data_json = { "resturant employees" :[ 
    {"name":"Shyam", "email":"shyamjaiswal@gmail.com"},
    {"name":"Bob", "email":"bob32@gmail.com"},
    {"name":"Jai", "email":"jai87@gmail.com"}
]}

prompt = f"""
Translate the following python dictionary from JSON to an HTML \
table with column headers and title: {data_json}
"""
response = get_completion(prompt)
print(response)

<html>
<head>
    <title>Restaurant Employees</title>
</head>
<body>
    <table>
        <tr>
            <th>Name</th>
            <th>Email</th>
        </tr>
        <tr>
            <td>Shyam</td>
            <td>shyamjaiswal@gmail.com</td>
        </tr>
        <tr>
            <td>Bob</td>
            <td>bob32@gmail.com</td>
        </tr>
        <tr>
            <td>Jai</td>
            <td>jai87@gmail.com</td>
        </tr>
    </table>
</body>
</html>

If using jupyter notebook we can run the code above by running the code.

from IPython.display import display, Markdown, Latex, HTML, JSON
display(HTML(response))

Spellcheck & Grammar Check

To signal to the LLM that you want it to proofread your text, you instruct the model to ‘proofread’ or ‘proofread and correct’.

text = [ 
  "The girl with the black and white puppies have a ball.",  # The girl has a ball.
  "Yolanda has her notebook.", # ok
  "Its going to be a long day. Does the car need it’s oil changed?",  # Homonyms
  "Their goes my freedom. There going to bring they’re suitcases.",  # Homonyms
  "Your going to need you’re notebook.",  # Homonyms
  "That medicine effects my ability to sleep. Have you heard of the butterfly affect?", # Homonyms
  "This phrase is to cherck chatGPT for speling abilitty"  # spelling
]
for t in text:
    prompt = f"""Proofread and correct the following text
    and rewrite the corrected version. If you don't find
    and errors, just say "No errors found". Don't use 
    any punctuation around the text:
    ```{t}```"""
    response = get_completion(prompt)
    print(response)
    

The girl with the black and white puppies has a ball.
No errors found
No errors found.
Their goes my freedom. There going to bring they’re suitcases.

No errors found.

Rewritten:
Their goes my freedom. There going to bring their suitcases.
You're going to need your notebook.
No errors found.
No errors found
text = f"""
Got this for my daughter for her birthday cuz she keeps taking \
mine from my room.  Yes, adults also like pandas too.  She takes \
it everywhere with her, and it's super soft and cute.  One of the \
ears is a bit lower than the other, and I don't think that was \
designed to be asymmetrical. It's a bit small for what I paid for it \
though. I think there might be other options that are bigger for \
the same price.  It arrived a day earlier than expected, so I got \
to play with it myself before I gave it to my daughter.
"""
prompt = f"proofread and correct this review: ```{text}```"
response = get_completion(prompt)
print(response)

I got this for my daughter for her birthday because she keeps taking mine from my room. Yes, adults also like pandas too. She takes it everywhere with her, and it's super soft and cute. One of the ears is a bit lower than the other, and I don't think that was designed to be asymmetrical. It's a bit small for what I paid for it though. I think there might be other options that are bigger for the same price. It arrived a day earlier than expected, so I got to play with it myself before I gave it to my daughter.
from redlines import Redlines

diff = Redlines(text,response)
display(Markdown(diff.output_markdown))

Got I purchased this adorable panda plush as a birthday gift for my daughter for her birthday cuz daughter, as she keeps taking kept borrowing mine from my room. Yes, room. It’s not just for kids - even adults also like pandas too. She can appreciate the charm of this cuddly companion. My daughter absolutely adores it and takes it everywhere with her, and it’s super thanks to its irresistibly soft and cute. One of cute design. However, I did notice a slight asymmetry in the ears is ears, which I believe was not intentional. Additionally, considering the price, I found the size to be a bit lower smaller than the other, and expected. I don’t think that was designed to be asymmetrical. It’s a bit small for what I paid for it though. I think suspect there might be other are larger options that are bigger available for the same price. It cost. Despite this, I was pleasantly surprised when it arrived a day earlier than expected, so I got anticipated, allowing me to play with enjoy its company before passing it myself before I gave it on to my daughter. daughter. This panda plush is a delightful gift choice, perfect for anyone who appreciates quality and cuteness in a stuffed animal.

prompt = f"""
proofread and correct this review. Make it more compelling. 
Ensure it follows APA style guide and targets an advanced reader. 
Output in markdown format.
Text: ```{text}```
"""
response = get_completion(prompt)
display(Markdown(response))

I purchased this adorable panda plush as a birthday gift for my daughter, as she kept borrowing mine from my room. It's not just for kids - even adults can appreciate the charm of this cuddly companion. My daughter absolutely adores it and takes it everywhere with her, thanks to its irresistibly soft and cute design. However, I did notice a slight asymmetry in the ears, which I believe was not intentional. Additionally, considering the price, I found the size to be a bit smaller than expected. I suspect there are larger options available for the same cost. Despite this, I was pleasantly surprised when it arrived a day earlier than anticipated, allowing me to enjoy its company before passing it on to my daughter. This panda plush is a delightful gift choice, perfect for anyone who appreciates quality and cuteness in a stuffed animal.

Expanding

We will generate customer service emails that are tailored to each customer’s review.

Customize Automated Reply

# given the sentiment from the lesson on "inferring",
# and the original customer message, customize the email
sentiment = "negative"

# review for a blender
review = f"""
So, they still had the 17 piece system on seasonal \
sale for around $49 in the month of November, about \
half off, but for some reason (call it price gouging) \
around the second week of December the prices all went \
up to about anywhere from between $70-$89 for the same \
system. And the 11 piece system went up around $10 or \
so in price also from the earlier sale price of $29. \
So it looks okay, but if you look at the base, the part \
where the blade locks into place doesn’t look as good \
as in previous editions from a few years ago, but I \
plan to be very gentle with it (example, I crush \
very hard items like beans, ice, rice, etc. in the \ 
blender first then pulverize them in the serving size \
I want in the blender then switch to the whipping \
blade for a finer flour, and use the cross cutting blade \
first when making smoothies, then use the flat blade \
if I need them finer/less pulpy). Special tip when making \
smoothies, finely cut and freeze the fruits and \
vegetables (if using spinach-lightly stew soften the \ 
spinach then freeze until ready for use-and if making \
sorbet, use a small to medium sized food processor) \ 
that you plan to use that way you can avoid adding so \
much ice if at all-when making your smoothie. \
After about a year, the motor was making a funny noise. \
I called customer service but the warranty expired \
already, so I had to buy another one. FYI: The overall \
quality has gone done in these types of products, so \
they are kind of counting on brand recognition and \
consumer loyalty to maintain sales. Got it in about \
two days.
"""
prompt = f"""
You are a customer service AI assistant.
Your task is to send an email reply to a valued customer.
Given the customer email delimited by ```, \
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.
Sign the email as `AI customer agent`.
Customer review: ```{review}```
Review sentiment: {sentiment}
"""
response = get_completion(prompt)
print(response)

Dear valued customer,

Thank you for taking the time to share your detailed feedback with us. We are truly sorry to hear about the issues you experienced with the pricing changes and the quality of the product. We apologize for any inconvenience this may have caused you.

If you have any further concerns or would like to discuss this matter further, please feel free to reach out to our customer service team for assistance. We are here to help address any issues you may have encountered.

Thank you again for your feedback and for being a loyal customer. We appreciate your support.

AI customer agent
  • Remind Model to use Details from the email
prompt = f"""
You are a customer service AI assistant.
Your task is to send an email reply to a valued customer.
Given the customer email delimited by ```, \
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.
Sign the email as `AI customer agent`.
Customer review: ```{review}```
Review sentiment: {sentiment}
"""
response = get_completion(prompt, temperature=0.7)
print(response)

Dear valued customer,

Thank you for sharing your detailed feedback with us regarding your recent purchase. We are sorry to hear about the issues you have experienced with the pricing changes, product quality, and the motor noise after a year of use. We apologize for any inconvenience this may have caused you.

If you have any further concerns or would like to discuss this matter further, please feel free to reach out to our customer service team. We are here to assist you in any way we can.

Thank you for your loyalty and for taking the time to provide us with your feedback.

AI customer agent