Transformations – Mantium Skip to content

The power of transforms at your fingertips.

From basic editing like deleting or combining columns to more complex transforms like prompt writing and summarization, transforms take your base data source and create a dataset that is near limitless.

Sign up now

How do transforms work?

Wherever you’re starting from, transforms enable you to get the most out of your data. Add context, content, and columns. Enrich it with outside data or generate text using templates or custom prompts. Your imagination is the only limit.

Transforms at work

  1. From within a dataset select a transform.
  2. Configure the transform with a simple form.
  3. Test the transform to make sure it does what you want.
  4. Run the transform.

Transcribe Audio

Convert audio files into text using the OpenAI Whisper third-party service.

Generate Embeddings

Generate embeddings for text data using third-party LLMs (language models) such as OpenAI’s ada-2.

Clean Text

Clean the text in a specific column of a dataset.

Intuitive prompting icon

OpenAI Prompt

Generate text guided by a Prompt Template.

Columnize CSV

Turn a single line of CSV data into a structured dataset with individual columns.

Summarization

Summarize text using an LLM model and a prompt template.

Enriching your data

Mantium adds value to existing data by providing additional information or context, such as adding tags, labels, or categories to data, or by creating summaries.

Ready to get more from your data?

All the ways to transform your data

Enrichment

Transcribe Audio

Transcribe audio files into text.

Transformation

Clean Text

Clean the text in a specific column of a dataset

Transformation

Columnize CSV

Turns a single line of CSV data into a structured dataset with individual columns.

Transformation

Reformat CSV

Reformat CSV is used to reformat the CSV content with a different delimiter.

Transformation

Delete Columns

Used to delete one or more columns from a dataset.

Enrichment

Generate Embeddings

Generate embeddings for text data using third-party LLMs

Transformation

Combine Rows

Combine rows in a dataset based on a specified row group identifier.

Enrichment

PDF to Text

Used to convert a PDF file into a text-based column in a dataset.

Transformation

Split Text

Used to split text into smaller chunks so that each chunk is small enough for an AI model to process.

Transformation

Rename Column

Change the name of a specified column in a dataset.

Transformation

Create Column

Create a new column in a dataset based on existing column(s) and a specified function or formula.

Enrichment

Summarization

Produce a shorter version of a cell while preserving its important information.

Enrichment

Generate Text

Generate text guided by a Prompt Template.

Enrichment

Element Count

Count the number of elements by Count Type.

COMING SOON

Enrichment

Function Extraction

Extract functions from .py files.

Enrichment

Regex Extraction

Extract specific patterns from text data using regular expressions.

Enrichment

Categorical Encoding

Convert categorical data into numerical values for machine learning models.

Enrichment

Normalization

Standardize the scale of numeric features in a dataset to improve the performance of machine learning algorithms.

Enrichment

Deduplication

Identify and remove duplicate records from a dataset.

Enrichment

Date and Time Parsing

Convert date and time information into a standardized format.

Enrichment

Data Imputation

Fill in missing values in a dataset using various techniques such as mean, median, or mode.

Transformation

Merge Datasets

Combine two or more datasets based on common columns or keys.

Enrichment

Anomaly Detection

Identify unusual or suspicious patterns in data that deviate from the norm.

Enrichment

Geocoding

Convert addresses or location data into geographic coordinates (latitude and longitude).

Enrichment

Text Classification

Categorize text data into predefined groups or classes.

Enrichment

Keyword Extraction

Identify and extract relevant keywords from text data.

Enrichment

Topic Modeling

Identify and group documents or text data based on the topics they contain.

Enrichment

Entity Recognition

Extract entities such as names, organizations, dates, and locations from the text.

Enrichment

Language Detection

Identify the language of the text data automatically.

Enrichment

Sentiment Analysis

Analyze the sentiment of text data to categorize it as positive, negative, or neutral.

Transform your data.