Release notes

September 14th, 2023 - GPT in Excel

Bug fix

We have fixed a bug that could cause the add-in sidebar to crash when you were editing cells while GPT in Excel executed tasks.

September 14th, 2023 - GPT for Sheets

Announcement

We've introduced new model settings:

• Custom instructions: Set specific preferences and roles for the model.
• Top P: Control creativity by limiting the model to the most likely words or phrases with values like 0.1 for more focused results.
• Frequency and Presence penalties: Reduce repetition with these OpenAI-specific settings.

September 14th, 2023 - GPT for Sheets and Docs

Improvement

The current model is now always included in the model status dropdown list at the top of the sidebar.

Bug fix

This release fixes an issue where the absence of the Anthropic version could lead to errors with Clause models.

September 12th, 2023 - GPT for Sheets

Improvement

We've modified GPT formula cache behavior to improve consistency and reduce unnecessary recalculations:

• When caching is enabled in your spreadsheet, formula refresh is now restricted to error cases.
• Caching is now formula-centric, and ignores sidebar settings. If the formula is unchanged, results are consistently retrieved from the cache.

September 6th, 2023 - GPT for Docs

Improvement

This release includes the following improvements:

• Model settings are now saved within the add-on, ensuring they are available when you reopen your document or use the add-on in a different document.
• We have renamed and improved the ability to attach custom instructions to prompts. Previously called Set behavior and configured per prompt, this feature is now named Custom instructions and can be found in the Model settings section. With this update, custom instructions are set at the model level and are now saved within the add-on along all other model settings.

• The Model list now shows only the models that are available to your currently set API keys.

• When you select a Claude model, the default value for Max response tokens is now set to 10000. This change is designed to maximize the benefits of Anthropic models' larger token capacity when transitioning from a model with a smaller capacity.

• text-ada-001, text-babbage-001 and text-curie-001 models, which will soon be retired by OpenAI, are demoted in GPT for Docs.

September 6th, 2023 - GPT for Sheets/GPT in Excel

Announcement

We have published a new template containing a comprehensive set of examples for major use cases. These examples are bundled into a spreadsheet that you can copy for Google Sheet

and into a downloadable workbook for Excel. Experience hands-on learning by copying and pasting the GPT formulas!

August 31st, 2023 - GPT in Excel

Improvements

We have added the following functions to GPT in Excel:

• GPT_SPLIT: Splits text semantically, e.g. by section, paragraph, customer. This function outputs all splits vertically in a column.

• GPT_HSPLIT: Splits text semantically, e.g. by section, paragraph, customer. This function outputs all splits horizontally in a row.
• GPT_EDIT: Applies edit instructions to the given text. The default task is to fix grammar and spelling.

We have also removed GPT_CONVERT from the list of available functions, because it was a duplicate of GPT_FORMAT. GPT_CONVERT remains usable by manually typing the function.

Bug fix

GPT_TAG and GPT_CLASSIFY now preserve the letter case of the tags and categories provided as input.

August 22nd, 2023 - GPT for Sheets

Improvement

We have removed duplicates and unused functions from the list of available functions:

• GPT_MAP: was identical to GPT_MATCH
• GPT_CONVERT: was identical to GPT_FORMAT
• GPT_CODE: was removed due to very low usage

GPT_MAP and GPT_CONVERT remain usable by manually typing the functions.

August 21st, 2023 - GPT for Sheets

Bug fix

This release restores compatibility for formulas containing the deprecated max_tokens parameter. These old formulas now execute successfully, however any value specified for  max_tokens will be ignored.

To configure this parameter, it is now recommended to use the sidebar setting Max response size.

August 18th, 2023 - GPT for Sheets

Bug fix

GPT_TAG no longer returns an error if the tag list is not specified through the optional tags parameter. If the parameter is left blank, relevant tags are automatically suggested.

August 18th, 2023 - GPT for Sheets and Docs

Bug fix

The model list now shows only the models that are available to your currently set API keys.

August 7th, 2023 - GPT for Sheets

Bug fix

GPT for Sheets now takes into account locale settings for all countries in sidebar examples.

August 7th, 2023 - GPT for Docs

Improvement

[insert] tags now work in documents containing tables with rows having varying column counts.

August 4th, 2023 - GPT for Docs

Announcement

Claude models are now available in GPT for Docs!

Enter an Anthropic key in the GPT for Docs add-on and start using claude-instant-1 and claude-2 to benefit from:

• Up to 100k tokens
• Performance on par with OpenAI models
• Affordable pricing: nearly 5 times cheaper than the 32K-context version of GPT-4

Price for 1 million tokens:

Improvements

You can now request a response in table format by specifying it in the prompt.

We have also significantly improved response insertion, including in the following situations:

• Inline
• Inside tables
• Inside lists
• At the end of a document
• After a text selection, even in a table

August 2nd, 2023 - GPT in Excel

Bug fix

We fixed a bug where editing a formula would block all GPT executions.

August 1st, 2023 - GPT in Excel

Improvement

When launching GPT in Excel for the first time, you are now presented with a set of examples to help you understand what you can do with it.

Click on Try this example, to import the full example into a cell and see it in action!

Bug fix

In this version, the GPT formula controls options now works reliably even on a large number of selected cells.

July 28th, 2023 - GPT for Sheets

Improvement

All the examples in the GPT functions list now automatically adjust the separator to your spreadsheet’s locale settings.

July 27th, 2023 - GPT in Excel

Bug fix

We have fixed a bug that prevented use of GPT functions when a workbook containing GPT formulas was shared.

July 26th, 2023 - GPT in Excel

Announcement

We're excited to share that our free trial now offers 300 credits, allowing you to perform 300 free executions in GPT in Excel.

July 25th, 2023 - GPT in Excel

Bug fix

GPT_TAG and GPT_CLASSIFY will not hallucinate tags or categories anymore. They will return results from the provided list of categories or tags, if any.

July 25th, 2023 - GPT for Sheets

Improvements

This release comes with the following improvements:

• text-ada-001, text-babbage-001 and text-curie-001 models, which will soon be retired by OpenAI, are demoted in GPT for Sheets. You can still find them at the bottom of the Model menu.
• Longer responses allowed for Anthropic models: up to 100k tokens, around 75000 words (English)

July 18th, 2023 - GPT in Excel

Announcement

We just lowered our prices: you can now buy 5x more credits for the same price as before!

July 18th, 2023 - GPT for Sheets

Improvement

GPT_EXTRACT now outputs to a single cell when the value for the parameter to_extract is a single cell or a string

July 14th, 2023 - GPT for Sheets

Improvement

The model list now only displays the models that are available to your API keys.

July 14th, 2023 - GPT for Docs

Bug fix

We have fixed an issue that prevented GPT for Docs from properly saving API keys.

July 13th, 2023 - GPT in Excel

Announcement

We just released more ways to configure settings and control your GPT formulas::

• Configure settings from the sidebar and they will apply to new formulas in your workbook
• Control formula execution: pause calculation, refresh in one click, replace formulas by results for easier reuse

Discover these features, along with usage tips, in the brand new version of GPT in Excel sidebar!

July 12th, 2023 - GPT for Sheets

Announcement

You can now use Claude models from Anthropic in GPT for Sheets!

Simply enter an Anthropic key in the GPT for Sheets add-on and start using claude-instant-1 or claude-2 to benefit from:

• Up to 100k tokens
• Performance on par with OpenAI models
• Affordable pricing: nearly 5 times cheaper than the 32K-context version of GPT-4

Price for 1 million tokens:

Bug fixes

• The formula replacement tool now displays the number of formulas replaced in near real time, updating the count every 7 seconds during processing.
• If GPT_EXTRACT cannot find the value to extract, it will return blank instead of a REF error.

March 11th, 2023 - Lots of improvements

• GPT_TABLE and GPT_EXTRACT now work better with table headers
• GPT_CLASSIFY can now use the text-embedding-ada-002 model for classification, which will prevent GPT from inventing unwanted categories. To use it, simply specify the model in the function parameter
• GPT_TAG has a new top_k parameter which allows you to control the maximum number of tags to be returned
• Quotation marks are better handled so that they are not trimmed when they’re wanted
• Errors of authorization linked to multiple account should be better handled

March 6th, 2023 - Small improvements

We’ve made improvements to GPT_FILL, GPT_TABLE and GPT_EXTRACT

March 2nd, 2023 - ChatGPT turbo, baby!

OpenAI released the new chatgpt gpt-3.5-turbo model last night, and it is now the default model in in all functions of GPT for Sheets and Docs. Enjoy 10x cheaper costs, faster and better quality responses.

We turbo released this, so if it breaks anything, (1) we’re sorry and (2) please let us know here

Other improvements:

• Specifying tags in GPT_TAG is now optional: GPT_TAG will come up with tags on its own
• GPT_TAG and GPT_CLASSIFY output in lowercase if categories are lowercase
• We now automatically detect fine-tuned model most frequent separators
• A few other details that make the overall experience better

February 24th, 2023 - Map values with GPT_MAP

New functions:

• GPT_MAP which enables you to map the values of two columns to find the best matches. You can use it to map different spellings or even categories that are semantically related. This function uses the text-ada-002-embeddings model which is extremely fast and very cheap
• GPT_TREE which is more of an experimental function to generate trees of content in your spreadsheet.

We’ve also added a GTP function for those who find the letter T faster than the letter P! 😊

Fine-tuned models:

You can now use your fine-tuned models in GPT for Sheets! Simply specify your model in the model parameter of your GPT function.

We will automatically recognize or add the stop sequence of your prompt.

Improvements:

• Datetimes are now better handled. (the devil really is in the details)
• We now better handle incorrect values in all parameters
• GPT_CONVERT now works better
• The default max_tokens parameter has been increased to 500 in order to avoid to many cut responses

February 20th, 2023 - Real numbers and dates

The devil is in the details!

ChatGPT outputs pure text by default. When this text contains numbers or dates, we want them as numbers or date objects in our spreadsheets in order to be able to operate on them.

GPT for Sheets now correctly recognises numbers and dates before writing them to your spreadsheet. This makes it much more usable to work with tables of data.

February 14th, 2023 - Improved parsing

We have improved parsing of input in the prompts sent to OpenAI which will result in better quality output.

We have also improved our preset prompts in GPT for Docs for better output quality.

February 8th, 2023 - Added examples

We’ve added an examples template spreadsheet directly accessible from the add-on menu.

Replacing formulas now works on all GPT functions.

February 6th, 2023 - Improved error messages

We’ve made error messages easier to understand which should help you understand what to do when you input a parameter incorrectly, hit a rate limit, expire your free trial or when OpenAI servers are unavailable.

January 31th, 2023 - New preset functions!

GPT for Sheets

• Woohoo! We just released a bunch of new functions that will make it much easier to make some frequent operations without writing any prompt:
  • GPT_TAG to apply tags. Simple and easy
  • GPT_CODE to generate code in your spreadsheet. Yes some people want to do this!
  • GPT_EDIT to edit text. By default it fixes spelling and grammar
  • GPT_EXTRACT to extract things like email addresses or companies from a paragraph. Works remarkably well
  • GPT_CONVERT to convert cells and ranges from one format to another: html, json, json-ld, nl-json, tables, csv, markdown. Incredibly powerful
  • GPT_SUMMARIZE to quickly summarize some text
  • GPT_TRANSLATE to quickly translate some text
  • GPT_CLASSIFY to classify into a single category (different from GPT_TAG where multiple tags can apply)
  • and finally GPT_CREATE_PROMPT which will help you create a prompt from many different cells and ranges in your spreadsheet by just listing them one by one as arguments
• Fix a bug when the value parameter of GPT_LIST was empty
• Improvements to prompt and response parsing that make our functions more robust
• Changed the default cache setting to disabled for new users, and automatically enable it after 100 executions

January 26th, 2023

GPT for Sheets

• GPT_LIST now supports a range as a prompt. This makes it much easier to give write a good, specific, and detailed prompt.
• Replace formula with values now works on GPT_FILL
• We now check if you’re the owner of the spreadsheet before you can set an API key
• We have switched the order of parameters in all functions: max_tokens now comes before model, since:
  • tweaking the max_tokens parameter is actually useful and needs to be done frequently for longer-form content
  • there is very little reason to use another model than the default which is text-davinci-003.

GPT for Docs

• OpenAI responses are correctly split in paragraphs when relevant
• New tooltips have been added to the interface

January 24th, 2023

GPT for Sheets

The GPT function can now take range as prompt. This is a huge improvement, and makes it much easier to give write a good, specific, and detailed prompt.

January 20th, 2023

GPT for Sheets

We’ve released a new magical function: GPT_FILL ! This one is really incredible to see in action. All you need to do is feed it some example rows and it will fill a range intelligently. Super useful for cleaning lists, where the right prompt can be difficult to put together.

First release of GPT for Docs!

• You can now use the add-on from Google Docs, which is much more suitable for long-form content
• You can type your prompt directly in the document or in the prompt box

January 18th, 2023

GPT for Sheets

This update brings two cost management features:

• Replacing formulas with values, from the Extensions menu: once you’re satisfied with the answers of GPT, you should replace the formulas with values so that they never get recalculated.
• Cache management: we now cache answers of the same prompt by default for a duration of roughly 6 hours. This means that every answer you get will be reused if you ask the same question again or the formula gets recalculated will help lower your OpenAI costs. You can of course disable the cache if you prefer to explore variations rapidly and do not want to reuse answers. The cache is per spreadsheet.

January 12th, 2023

GPT for Sheets

We’ve released a new function: GPT_LIST !

It makes it as simple as pie to get one item per cell when you want multiple items at once, like “5 taglines for an ice-cream shop”.

January 7th, 2023

GPT for Sheets first release!

It all started with a simple GPT function. The little function that could.