How to use OpenAI's ChatGPT for keyword research

Learn how to use OpenAI and GPT-3 inside the spreadsheet to generate keywords, translate them, find common misspellings and more.

How to use OpenAI in Rows

OpenAI template

There's a near-infinite amount of tasks you can solve using OpenAI. Follow this guide on how to set up the integration and use this template showcase to get started with 10 pre-built examples, follow along the list, or watch our video tutorial.

Connecting the OpenAI integration in Rows

You can find the OpenAI integration by browsing the integrations gallery and searching for "OpenAI".

OpenAI integration in gallery

To connect the integration and use the power of AI inside Rows all you need is an API Key. You can get your API key by going to the View API Keys option on your OpenAI account. If you don't have an account yet, sign-up here. All free accounts have API access.

API Key panel in OpenAI

Now simply copy the API key, go to the OpenAI integration page, press Connect, paste it and click Connect. Your Rows workspace is now connected to your OpenAI account and you're ready to go.

OpenAI integration page

Using the OpenAI functions

The OpenAI integration comes with five proprietary functions that automate prompts to address specific types of tasks:

  • ASK_OPENAI(), which aims at leveraging the power of GPT to solve general tasks.
  • CREATE_LIST_OPENAI(), which is designed specifically to create tables and list of dummy data, for testing purposes.
  • CLASSIFY_OPENAI(), which is designed specifically to classify texts into a given set of tags.
  • TRANSLATE_OPENAI(), which translates texts from/into a wide range of languages.
  • APPLY_TASK_OPENAI(), which is designed specifically to clean up or apply logic rules to data.

You can use them via the Autocomplete in the editor,

ASK_OPENAI on the editor

or via the Actions wizard:

Screenshot 2023-04-19 at 16.58.52

All OpenAI functions need to be configured through mandatory and optional parameters, depending on their purpose. Let's go through them one by one.

Prompt

The prompt is the instruction to give to the model in our most generic function ASK_OPENAI(). This is where you'll enter the "ask" you want the AI to answer. You can use the prompt to solve a task by explicitly writing it in prose. Example:

1=ASK_OPENAI("Generate 100-word paragraph about the latest iPhone release")

Ask anything to OpenAI

Tips for creating Prompts

The Open AI integration uses its Completions capability, which means that the artificial intelligence model will predict the next word(s) that follow the prompt. With that in mind, here are a few tips on how to construct the right prompt for your task:

  • Be specific: The more specific the prompt, the most likely it is to get the intended result. If you're looking for the Population of the country in millions, "The Population of France, in millions is: " is a better prompt than simply "The Population of France".
  • Give examples: You can train the model on the type of answer you're looking for. If you are using Open AI for text classification, use the prompt to give a couple of examples of inputs and expected outputs. For example: "Categorize job title by function name. Head of Marketing:Marketing, COO:C-Level, CMO: "
  • Phrase the end of the prompt as the start of the answer: The model will answer with a direct continuation to the prompt. Use that insight to end the prompt with the structure you expect from the answer. If you want to use the OpenAI integration to summarize text, be clear on how to start. Example: "What are 2 main takeaways from this review: ",A2(cell reference with the product review)," ? Summarize it into 2 bullet points. Main takeaways: ")

Temperature (optional)

The temperature is common to all functions and is used to fine tune the sampling temperature, varying between 0 and 1. Use 1 for creative applications, and 0 for well-defined straight answers.

If you're doing tasks that require a factual answer (e.g. country populations, capitalize text), then 0 (the default) is a better fit. If you're using the AI for tasks where there aren't definite answers - such as generating text, summarizing text, or translating - then experiment with a higher temperature, which allows the engine to better capture text nuances and idiomatic expressions.

Max_tokens (optional)

This max_tokens represents the maximum number of tokens to generate in the completion. It's present in all OpenAI functions. You can think of tokens as pieces of words. Here are a few helpful rules of thumb examples from the OpenAI Help center:

  • 1 token ~= 4 chars in English
  • 1 token ~= 3/4 words
  • 100 tokens ~= 75 words
  • 1-2 sentences ~= 30 tokens
  • 1 paragraph ~= 100 tokens
  • 1,500 words ~= 2048 tokens

You can use any number starting with 0. The default value is 200. Most models have a context length of 2048 tokens, except for the newest models which support a maximum of 4096. For tasks that require more text output - text generation/summarization/translation - pick a higher value (e.g. 250).

Model (optional)

The AI model to use to generate the answer. It can be chosen in both functions, and by default, it uses "gpt-3.5-turbo". Below you find a list of all of the available GPT-3.5 models:

LATEST MODELDESCRIPTIONMAX TOKENSTRAINING DATA
gpt-3.5-turboMost capable GPT-3.5 model and optimized for chat at 1/10th the cost of text-davinci-003. Will be updated with our latest model iteration.4,096 tokensUp to Sep 2021
gpt-3.5-turbo-0301Snapshot of gpt-3.5-turbo from March 1st 2023. Unlike gpt-3.5-turbo, this model will not receive updates, and will only be supported for a three month period ending on June 1st 2023.4,096 tokensUp to Sep 2021
text-davinci-003Can do any language task with better quality, longer output, and consistent instruction-following than the curie, babbage, or ada models. Also supports inserting completions within text.4,097 tokensUp to Jun 2021
text-davinci-002Similar capabilities to text-davinci-003 but trained with supervised fine-tuning instead of reinforcement learning4,097 tokensUp to Jun 2021

Number of items (optional)

The number of items is available only in the CREATE_LIST_OPENAI() function, and represents the expected number of items in the list.

1=CREATE_LIST_OPENAI("Full names and email address",5,,500)

Tags and multi-tag (optional)

The tags and multi-tag properties are available only in the CLASSIFY_OPENAI() function. The first is mandatory and represents the categories you want your text to be classified into.

For example, if you need to classify a list of product reviews in column A, into positive, neutral, negative and very negative, you just need to input those tags separated by a coma, as follows:

1=CLASSIFY_OPENAI(A2, "positive, neutral, negative, very negative")

The second is optional and can be "true" (default) or "false". If true, the function can use more than one tag to classify your text. If false, it will only use one tag. Use false when you need a mutually exclusive strict categorization.

Language

The language is available only in the TRANSLATE_OPENAI() function, and indicates the destination language for your translation tasks. Use the function as follows:

1=TRANSLATE_OPENAI(B1,"hebrew")

Task and text

The task and text are available only in the APPLY_TASK_OPENAI() function, and are used to specify the logic rule to some text.

For example, if you need to capitalize a string of text, use the function as follows:

1=APPLY_TASK_OPENAI("Capitalize all letters", "i HavE a doG")

Examples of OpenAI functions for keyword research

There are several ways to use OpenAI to automate keyword research tasks inside a spreadsheet:

  • Generate keywords: Generate keyword ideas based on a topic.
  • Generate variations of keywords: Generate new keywords based on a list of keywords.
  • Generate common misspellings of keywords: Generate keywords that represent the common typing errors users do when looking for your target keywords.
  • Translate keywords: Translate a list of keywords to several languages to capture traffic in multiple geographies.

Let's go through each of them.

Generate keywords

Goal: Generate keyword ideas based on a topic. Create separate lists for Informational, Transactional, Navigational and Commercial keywords.

Example:

1=ASK_OPENAI(CONCATENATE("Generate a list of 10 Informational keywords based on the topic of: ",A2))

Add new columns to the spreadsheet for different keyword types.

Details: Assumes that A2 contains the topic.

Generate keywords

💡 To have the list of keywords in a new table, use the CREATE_LIST_OPENAI() function from the Actions menu. Input the prompt 'Generate a list of Informational keywords based on the topic of Vegan dog food'.

Then specify the number of items you expect, here 10. Set a temperature of 1, to allow for creative responses, and max_tokens of 500.

Screenshot 2023-03-09 at 11.57.23

Once the function has been configured, click on Next step and your table will appear below.

Screenshot 2023-03-09 at 11.58.10

Generate variations of keywords

Goal: Generate new keywords based on a list of keywords.

Example:

There are two steps to generate a variation of keywords:

  1. Creating a list with the keywords that will be used as a source.
  2. Using OpenAI to generate a new list of keywords.

Use RANGE2JSON to create a list with the first group of keywords. We'll use this formula inside the ASK_OPENAI prompt to generate the new list.

1=RANGE2JSON(A1,A2:A)

List of keywords

With the list of source keywords, we'll use OpenAI to generate the variations. We'll use the =RANGE2JSON(A1,A2:A) inside the prompt of the CREATE_LIST_OPENAI formula:

1=ASK_OPENAI(CONCATENATE("List new keywords based on this list: ",RANGE2JSON(A1,A2:A)),10,,)

Keyword variations

💡 Add a new table in the spreadsheet and move the OpenAI formula to keep the table with the keywords easier to read and use.

Multi-tables

Generate common misspellings of keywords

Goal:

Generate a list of common mispellings of given keywords.

Example:

1=ASK_OPENAI(CONCATENATE("Generate a json list with 1 column with the most common misspellings of ",B1),,500)

💡 Tips on improving the results

  1. Set a value for the max_token parameter to ensure it returns the full list.
  2. Be specific on the number of columns you expect. By default, OpenAI will return a column with misspellings and another with the correction.

Misspellings

Detail:

Assumes that the source keyword is in B1.

Translate keywords

Goal: Translate a list of keywords to several languages to capture traffic in multiple geographies.

Example:

1=TRANSLATE_OPENAI(A2,"Spanish",1,200)

Add new columns with the languages you want to translate to. In this example, we added additional columns for Japanese and Arabic.

Details:

  • Assumes that A2 contains the keyword.
  • Set a temperature of 1, to account for nuances and idiomatic expressions
  • Set max_tokens high enough to translate longer sentences.

Translate keywords



Other OpenAI guides

Have a look to other Marketing use cases for ChatGPT