arquero Connector for AI agents.

Yes. It processes arrays with thousands of rows in milliseconds because it runs locally on your machine rather than inside the AI client's context window.

The encoding happens entirely in your local memory. Your data is never sent to an external API for processing.

Label encoding assigns a unique number to each category (e.g., 1, 2, 3). One-Hot Encoder Engine creates separate binary columns for each category, which is often better for many machine learning models.

It works with any categorical string column. It will automatically detect the unique values in that column and create the appropriate binary features.

By performing the transformation locally and deterministically, it ensures that every row remains perfectly aligned with its original category without the risk of LLM errors.

No. The engine appends new binary columns (e.g., City_London, City_Paris) and preserves the original column so the AI can verify the encoding accuracy.

The engine processes them all instantly. However, be aware that a massively expanded JSON returned to the LLM may consume significant context tokens. Consider grouping rare categories before encoding.

Currently, the engine accepts one target column per execution for deterministic validation. The AI can chain multiple calls to encode several columns sequentially.