Starting April 29, 2025, Gemini 1.5 Pro and Gemini 1.5 Flash models are not available in projects that have no prior usage of these models, including new projects. For details, see Model versions and lifecycle.
Stay organized with collections
Save and categorize content based on your preferences.
Implement regex-based sentence splitting for function completion.
You can query a model directly and test the results returned when using
different parameter values with the Cloud console, or by calling the
Vertex AI API directly.
I've been asked to finish work on this function that splits sentences into a list. Unfortunately, I've been specifically told to use regex for this, with extra requirements explained in the function's docstring. Regex is a pain in the butt at the best of times - could you complete this code for me? Everything you need should be inside the snippet.
importredefsplitSentences(sentences):""" Splits a string of sentences into a list. Each sentence is period-separated, save for cases where the phrases "Mr." or "Ms." are used, since those don't end a sentence. """sentenceList=[]# missing code herereturnsentenceList
Response
importredefsplitSentences(sentences):""" Splits a string of sentences into a list. Each sentence is period-separated, save for cases where the phrases "Mr." or "Ms." are used, since those don't end a sentence. """sentenceList=[]sentenceEnders=r'(?<!Mr)\.(?<![A-Z][a-z]\.)(?<![A-Z][a-z][a-z]\.)(?<=\.|\?)\s'sentenceList=re.split(sentenceEnders,sentences)returnsentenceList
TLDR: The code splits a string into a list of sentences using regex. The regex was corrected to accurately identify sentence endings while excluding abbreviations like "Mr." and "Ms.".
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-26 UTC."],[],[],null,["Implement regex-based sentence splitting for function completion.\n\n|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| You can query a model directly and test the results returned when using different parameter values with the Cloud console, or by calling the Vertex AI API directly. - For an example of using the Vertex AI API, see [Quickstart using the Vertex AI API](/vertex-ai/generative-ai/docs/start/quickstarts/api-quickstart). - To view this sample in the Cloud console: [Go to Google Cloud console](https://console.cloud.google.com/vertex-ai/generative/language/prompt-examples/Regex%20completion%20and%20explanation) \u003cbr /\u003e ||\n| |-------------------------------------------------------------------------------------------------------------------------------------------------------| | **System instructions** | | Include a TLDR of what the code does and what fixes you made at the end of your response. Each explanation shouldn't be more than two sentences long. | Prompt Freeform I've been asked to finish work on this function that splits sentences into a list. Unfortunately, I've been specifically told to use regex for this, with extra requirements explained in the function's docstring. Regex is a pain in the butt at the best of times - could you complete this code for me? Everything you need should be inside the snippet. import re def splitSentences(sentences): \"\"\" Splits a string of sentences into a list. Each sentence is period-separated, save for cases where the phrases \"Mr.\" or \"Ms.\" are used, since those don't end a sentence. \"\"\" sentenceList = [] # missing code here return sentenceList Response import re def splitSentences(sentences): \"\"\" Splits a string of sentences into a list. Each sentence is period-separated, save for cases where the phrases \"Mr.\" or \"Ms.\" are used, since those don't end a sentence. \"\"\" sentenceList = [] sentenceEnders = r'(?\u003c!Mr)\\.(?\u003c![A-Z][a-z]\\.)(?\u003c![A-Z][a-z][a-z]\\.)(?\u003c=\\.|\\?)\\s' sentenceList = re.split(sentenceEnders, sentences) return sentenceList TLDR: The code splits a string into a list of sentences using regex. The regex was corrected to accurately identify sentence endings while excluding abbreviations like \"Mr.\" and \"Ms.\". | |------------------------|----------------------| | **Model:** | gemini-1.5-flash-002 | | **Temperature:** | 0.2 | | **Max output tokens:** | 8192 | | **TopK:** | 40.0 | | **TopP:** | 0.95 | |"]]