# Mantium Documentation

> Mantium is a cloud platform for building with large language models and managing them at scale. We power innovative applications built with OpenAI, Eleuther, AI21, Hugging Face and Cohere.

## Guides
- [About Mantium](https://developer.mantiumai.com/docs/about-mantium.md): Mantium is an innovative data platform that integrates with state-of-the-art Language Models like OpenAI, Cohere, and others to deliver powerful transformations and enrichments on your datasets. We cater to software developers, data engineers, and data scientists, simplifying the data retrieval, analysis, and transformation process. Our primary goal is to help organizations unlock the full potential of their data by providing an intuitive, efficient, and secure platform for data-driven decision-making.
- [Getting Started](https://developer.mantiumai.com/docs/getting-started-1.md): Welcome to Mantium! This Getting Started guide will walk you through the initial steps to set up and begin using our powerful data platform. By following this guide, you'll be on your way to streamlining your data workflows and unlocking the potential of your data.
- [Core Concepts](https://developer.mantiumai.com/docs/getting-started.md): Mantium is a powerful data platform that streamlines data retrieval, analysis, and transformation. This Core Concepts page provides an overview of the main components and features of Mantium to help you better understand and utilize the platform.
- [Setup Connector Accounts](https://developer.mantiumai.com/docs/get-provider-api-keys.md)
- [Getting Started with Templates](https://developer.mantiumai.com/docs/getting-started-with-templates.md): With Templates, you can now jumpstart your application development process by selecting a preconfigured template tailored to your specific use case. We provide all the necessary components, including Data Sources, Datasets, Transforms, Vector Databases, and Plugin creation, to get you up and running in no time.
- [Building your Custom Application](https://developer.mantiumai.com/docs/build-your-custom-ai-application.md): This tutorial will walk you through the steps of building your own custom application in Mantium
- [Architecture](https://developer.mantiumai.com/docs/architecture.md): Mantium is an innovative architecture designed to simplify the process of document retrieval for various applications. It streamlines the traditional pipeline of information extraction and retrieval, significantly reducing the number of steps a user has to undertake.
- [Vector Databases](https://developer.mantiumai.com/docs/vector-databases.md)
- [How to use Mantium's ChatGPT Plugin to Access Deployed Apps](https://developer.mantiumai.com/docs/how-to-use-mantiums-chatgpt-plugin.md): This is a tutorial on how to use Mantium's ChatGPT Plugin to access deployed apps
- [How to Sign Up for Developer Access of ChatGPT Plugins](https://developer.mantiumai.com/docs/openai.md)
- [How to Create your own OpenAI Plugin with Mantium](https://developer.mantiumai.com/docs/how-to-create-a-plugin-end-to-end-tutorial.md)
- [How to Transform Datasets and Ship to Pinecone with Mantium](https://developer.mantiumai.com/docs/shipping-transformed-datasets-to-pinecone.md): Learn to import data from a data source, generate embeddings, and export the transformed data to Pinecone using Mantium.
- [How to Analyze Slack Conversations with Mantium](https://developer.mantiumai.com/docs/daily-summaries-of-slack-conversations-with-mantium.md): In this tutorial, you will learn how to analyze Slack conversations using Mantium's platform. By the end of this guide, you will be able to import messages from specific Slack channels, aggregate the text, generate summaries, and synchronize the data for real-time analysis or machine learning purposes.
- [How to Chat with your Data using Mantium](https://developer.mantiumai.com/docs/openai-plugins.md): In this tutorial, we'll guide you through the process of connecting your data in Mantium to OpenAI's ChatGPT Plugin. By doing so, you'll be able to interact with your data directly within the ChatGPT interface using the Mantium Plugin. Let's explore the steps to achieve this integration.
- [How to Chat with Your Notion Data Using Mantium & OpenAI ChatGPT Plugins](https://developer.mantiumai.com/docs/how-to-chat-with-your-notion-data-using-openai-chatgpt-mantium.md)
- [How to Summarize Arxiv Papers with Mantium](https://developer.mantiumai.com/docs/summarize-arxiv-papers.md)
- [How to Conduct Sentiment Analysis on Amazon Alexa Reviews with Mantium](https://developer.mantiumai.com/docs/sentiment-analysis-on-amazon-alexa-reviews.md)
- [How to Generate Marketing Ideas from a PowerPoint Presentation](https://developer.mantiumai.com/docs/how-to-generate-marketing-ideas-from-a-powerpoint-presentation.md)
- [How to Clean and Transform Your Hubspot Data](https://developer.mantiumai.com/docs/how-to-craft-personalized-emails-with-hubspot-data.md)
- [How to Summarize Large Texts from Audio Transcriptions Using Mantium](https://developer.mantiumai.com/docs/how-to-summarize-large-texts-from-podcast-transcriptions-using-mantium.md)
- [How to Import Zoom Recordings and Generate Summaries with Embeddings](https://developer.mantiumai.com/docs/mantium-zoom-integration-importing-zoom-recordings-and-generating-summaries-with-embeddings.md)
- [How to Summarize YouTube Videos in ChatGPT using Mantium Plugin Wizard](https://developer.mantiumai.com/docs/how-to-summarize-youtube-videos-in-chatgpt-using-mantium-plugin-wizard.md): In this tutorial, we will learn how to understand long YouTube videos, summarize the content, ask questions, and use the data to generate fresh content - all in ChatGPT. We are going to use the Mantium Plugin Wizard to build the ChatGPT Plugin in a few clicks.
- [How to Chat with Technical Documentation using Mantium's Readme.io connector and Plugin Wizard](https://developer.mantiumai.com/docs/how-to-chat-with-technical-documentation-using-readmeio-mantium.md)
- [How to Build an Ecommerce ChatGPT Chatbot with Mantium](https://developer.mantiumai.com/docs/how-to-build-an-ecommerce-chatgpt-chatbot-with-mantium.md)
- [HubSpot](https://developer.mantiumai.com/docs/hubspot.md): The Hubspot Data Connector allows you to seamlessly integrate and synchronize data from your Hubspot account into Mantium. Hubspot is a popular inbound marketing, sales, and customer service platform that helps businesses grow better. With this data connector, you can access, analyze, and manipulate your Hubspot data.
- [Notion](https://developer.mantiumai.com/docs/notion.md): The Notion Data Connector enables seamless integration and synchronization of data from your Notion account into Mantium. Notion is a versatile workspace tool that combines notes, databases, wikis, and project management features into a single platform. With this data connector, you can access, analyze, and manipulate your Notion data, including pages, databases, and blocks, using Mantium's powerful suite of data transformations.
- [Readme](https://developer.mantiumai.com/docs/readme.md)
- [Slack](https://developer.mantiumai.com/docs/slack.md): The Slack Data Connector enables you to retrieve and analyze messages and metadata from Slack channels. This connector allows you to gain insights on communication patterns, collaboration, and user engagement within your organization.
- [Zoom](https://developer.mantiumai.com/docs/zoom.md): The Zoom Data Connector enables you to efficiently manage Zoom sessions by importing Zoom recordings, transcribing the audio, summarizing the content, combining the transcription and summary, and generating embeddings for the combined text. This connector allows you to gain insights on meeting effectiveness, streamline content organization, and enhance participant engagement within your organization.
- [File Upload](https://developer.mantiumai.com/docs/file-upload.md): The File Upload Data Connector allows users to manually upload a variety of file types for analysis and processing. This connector provides flexibility in importing and transforming data from different formats, making it easier to integrate and analyze data from multiple sources.
- [PDF (.pdf)](https://developer.mantiumai.com/docs/pdf.md): PDF file support information
- [Word Documents (.docx)](https://developer.mantiumai.com/docs/word-documents-docx.md): Mantium provides support for Word documents (DOCX)
- [PowerPoint (.pptx)](https://developer.mantiumai.com/docs/powerpoint.md): Mantium provides support for PowerPoint files (PPTX)
- [CSV (.csv)](https://developer.mantiumai.com/docs/csv-csv.md): CSV files are supported by Mantium CSV Data Connector.
- [Pinecone](https://developer.mantiumai.com/docs/pinecone.md): This guide will walk you through how to connect your Pinecone account to Mantium
- [Clean Wikipedia Text](https://developer.mantiumai.com/docs/clean-wikipedia-text.md): Clean Wikipedia text by removing multiple new lines, removing extremely short lines, adding paragraph breaks and removing empty paragraphs.
- [Coalesce Columns](https://developer.mantiumai.com/docs/coalesce-columns.md): Coalesce one or more columns into a Destination Column. This Transformation iterates through a dataset to fill out a new column. For each row in the Source Columns, the first cell value found that is not None will be returned to the new Destination Column. If all cell values are None, the Transformation will return None to the Destination Column. Note that the order of the Source Columns in your dataset matters for this Transformation. This can be particularly useful in data analysis and reporting, where missing data can skew results or make it difficult to draw accurate conclusions.
- [Columnize CSVs](https://developer.mantiumai.com/docs/columnize-csv.md): Convert comma-separated values into a dataset format of rows and columns that can be easily analyzed and manipulated.
- [Combine Columns](https://developer.mantiumai.com/docs/structure-texts.md): Create a new column by combining other columns using a String Template. Use the String Template to manipulate text according to a specific pattern or structure. The $column_<column_name> notation can be used to specify any column in your dataset.
- [Combine Rows](https://developer.mantiumai.com/docs/combine-rows.md): Aggregate data from multiple rows into a single row. This transformation is similar to a SQL group_by operator.
- [Convert Microsoft PowerPoint to Text](https://developer.mantiumai.com/docs/convert-microsoft-powerpoint-pptx-to-text.md): Convert Microsoft PowerPoint files (.pptx) to text which can be used for various purposes such as indexing, searching, or analyzing the content of the document. This enrichment is useful for applications that require the text content of a Microsoft PowerPoint file without the need for the original layout or formatting.
- [Convert Microsoft Word to Text](https://developer.mantiumai.com/docs/convert-microsoft-word-docx-to-text.md): Convert Microsoft Word files (.docx) to text which can be used for various purposes such as indexing, searching, or analyzing the content of the document. This enrichment is useful for applications that require the text content of a Microsoft Word file without the need for the original layout or formatting.
- [Convert PDF to Text](https://developer.mantiumai.com/docs/pdf-to-text.md): Convert PDF files to text which can be used for various purposes such as indexing, searching, or analyzing the content of the PDF document. This enrichment is useful for applications that require the text content of a PDF file without the need for the original layout or formatting.
- [Count Elements](https://developer.mantiumai.com/docs/token-count.md): Count individual elements within text, such as words, characters or tokens. This can be particularly helpful for tasks such as checking the length of an article or essay, analyzing the readability of a document, or simply getting a quick overview of the amount of text that needs to be translated, edited or summarized.
- [Delete Columns](https://developer.mantiumai.com/docs/delete-columns.md): Streamline your dataset by removing unnecessary columns. This can reduce storage requirements which can be helpful when working with large datasets.
- [Detect PII](https://developer.mantiumai.com/docs/pii-detection.md): Detect whether Personally Identifiable Information (PII) is present in text by returning True or False. PII is any data that can be used to identify a specific individual, such as their name, address, social security number, or email address. PII can be sensitive and its exposure can lead to privacy breaches, identity theft, and other forms of fraud. By using this Enrichment, organizations can scan their text data for PII and take appropriate measures to safeguard it. This can help prevent data breaches and protect the privacy of individuals. Use the Prompt Template to guide the PII detection. The $field_source_column notation specifies the source column and the $column\_<column_name> notation specifies all other columns in your dataset.
- [Extract Python Classes](https://developer.mantiumai.com/docs/extract-python-classes.md): Extract classes and functions from a Python codebase. This Enrichment is useful in scenarios such as documentation generation, debugging, and code analysis. It allows you to separate and analyze the classes and functions separately, making it easier to identify problems or perform deeper analysis.
- [Generate Embeddings](https://developer.mantiumai.com/docs/generate-embeddings.md): Generate numerical representations of text, also known as embeddings, that can be used for tasks such as text classification, similarity analysis, and clustering. Embeddings capture the meaning and context of text in a way that can be processed by machine learning algorithms. They are commonly used in vector databases to enable efficient similarity search and retrieval of similar items.
- [Generate Text](https://developer.mantiumai.com/docs/generate-text.md): Generate text for various purposes, such as summarizing information, answering questions, or creating natural language responses. Use the Prompt Template to guide the text generation. The $field_source_column notation specifies the source column and the $column\_<column_name> notation specifies all other columns in your dataset.
- [Mask Entities](https://developer.mantiumai.com/docs/mask-entities.md): Protect sensitive information by replacing entities with a placeholder value. This helps to prevent disclosure of sensitive information while maintaining the overall context of the text.
- [Normalize Text](https://developer.mantiumai.com/docs/clean-text-copy.md): Normalize text to make it easier to read and analyze for further processing. With this Transformation, you can normalize whitespace, fix unicode characters, lowercase text, and much more.
- [Reformat CSV](https://developer.mantiumai.com/docs/reformat-csv.md): Reformatting comma-separated values using `|` between cells and `.` between lines can make it more interpretable by Large Language Models.
- [Remove Entities](https://developer.mantiumai.com/docs/remove-entities.md): Remove entities in text
- [Rename Column](https://developer.mantiumai.com/docs/rename-column.md): Rename one or more columns to improve clarity and consistency. Use this Transformation when combining multiple datasets or when working with data from different sources. By renaming columns to a consistent format, you can ensure that they are compatible and can be properly merged or analyzed together.
- [Split Text](https://developer.mantiumai.com/docs/split-text.md): When working with Enrichments that require input text in smaller chunks, Split Text can be used to break down the text into smaller parts.
- [Summarize Text](https://developer.mantiumai.com/docs/summarization.md): Generate a shorter version of text while preserving its important information. Quickly understand the content of a long text, such as a news article or a research paper. This enrichment can also help reduce the number of words in your original text while retaining the most important points in a clear and concise manner. Use the Prompt Template to guide the text generation. The $field_source_column notation specifies the source column and the $column\_<column_name> notation specifies all other columns in your dataset.
- [Transcribe Audio](https://developer.mantiumai.com/docs/transcribe-audio.md): Transcribe recorded meetings, speeches, or interviews into text, making it easier to reference and search for specific information. This Enrichment can also be used to create closed captions for videos or to transcribe audio content for individuals who are deaf or hard of hearing. By converting audio into text, other Enrichments can perform various tasks on the text such as sentiment analysis, topic modeling, and speech recognition.
- [Mantium Security Statement](https://developer.mantiumai.com/docs/mantium-security-statement.md)