The Readme Data Connector in Mantium is a powerful tool that allows you to seamlessly integrate your documentation data with the Mantium platform. This connector enables you to extract valuable data from your Readme projects, including project details, category information, and document content.

By connecting Readme with Mantium, you can leverage the advanced data processing and AI capabilities of Mantium to analyze and transform your Readme data. For example, you can perform text analysis on your documentation, generate summaries of lengthy documents, extract keywords, and much more. This can provide valuable insights into your documentation, such as identifying common themes, understanding the impact of changes over time, and discovering areas for improvement.

Furthermore, the Readme Data Connector supports re-syncing, allowing you to keep your data in Mantium up-to-date with your latest Readme content. With support for API configuration, you can also customize the connector to suit your specific needs.


Re-SyncingYes1 Hour, 12 Hour, 24 Hour, Weekly, Monthly
HistoryYesEntire History
FieldsYesproject_name, project_subdomain, project_base_url, category_title, category_slug, category_version, category_createdAt, category_type, category__v, doc_id, doc_title, doc_slug, doc_excerpt, doc_body, doc_createdAt, doc_updatedAt, doc_body_html, doc__v
API ConfigurableYesContact Us

Setup Instructions:

To set up the Data Connector with Mantium, follow these steps:

  1. Log in to your Mantium account.
  2. Click on "Connectors" on the left-side navigation bar.
  3. At the top right corner, click on Add Connector and then select
  4. Enter your API key in the provided field.
  5. Click Save. The Data Connector will be added to your list of connected data sources.

Recommended Transformations:

Based on the data headers provided, here are some recommended transformations that can be performed using Mantium:

  • Token Count: Analyze the frequency of words in the doc_title, doc_excerpt, and doc_body columns.
  • Generate Text: Create a human-readable summary of each row using the doc_title, doc_excerpt, and doc_body columns.
  • Summarization: Summarize long text fields in the doc_body column.
  • Create Column: Create new columns based on existing data, such as extracting keywords or mentions from the doc_body column.
  • Rename Column: Rename columns for easier understanding or to comply with specific naming conventions.
  • Split Text: Split the project_base_url column into separate domain and path columns.
  • PDF to Text: If the doc_body column contains PDF files, extract the text from these files.
  • Combine rows: Merge rows with related data or concatenate text from multiple rows into a single row.
  • Generate Embeddings: Create embeddings for text fields like doc_title and doc_body to use for machine learning or clustering purposes.
  • Delete Columns: Remove unnecessary columns that are not needed for analysis.
  • Reformat CSV: Adjust the CSV format as required, including delimiters and encoding.
  • Columnize CSV: Convert a single column of CSV data into multiple columns for easier analysis.
  • Transcribe Audio: If the doc_body column contains audio files, transcribe the audio into text.
  • Clean Text: Remove unwanted characters or formatting from the doc_title, doc_excerpt, and doc_body columns.