Overview

Max is designed to seamlessly connect to a wide range of data sources, enabling users to explore, analyze, and extract insights from their data effortlessly. Max does not perform direct data extraction or ETL (Extract, Transform, Load) processes. Instead, Max adds Datasets, which form a Semantic Layer that describes the data in ways that are easy for language models to understand. This allows Max to guide users through their data intuitively. Each Connector in Max can have multiple Datasets, enabling users to organize and structure their data effectively.

This article explains how Max connects to different data sources, the types of data it supports, and how Datasets simplify interaction with the data.

Key Concepts

• Connector: The feature in Max that interfaces with various data sources, pulling the necessary metadata and context.
• Dataset: The Semantic Layer in Max that describes and organizes data from a Connector in a way that is easy for Max’s language models to understand. One Connector can contain multiple Datasets.

Why Connect to Data with Max?

Max’s ability to connect to multiple data sources eliminates the need for manual data exploration. By organizing data into Datasets, users can:

• Leverage the power of natural language processing (NLP) to ask questions about their data.
• Gain insights from data without needing to understand its technical complexities.
• Combine metadata from multiple sources for comprehensive analysis.
• Empower non-technical users to interact with data without needing to perform SQL queries or manual data manipulation.

Supported Data Sources

Max supports direct connections to a variety of popular databases and file-based formats, allowing users to integrate the data they need. The key supported sources include:

1. Databases:

   • Snowflake
   • Redshift
   • BigQuery
   • Databricks
   • PostgreSQL
   • Microsoft Azure

2. File-Based Sources:

   • CSV: Structured data stored in comma-separated value files.
   • Parquet: Columnar storage files optimized for big data use cases.

How Max Connects to Data

Max connects to data using Connectors, which interface with the data source, and creates Datasets that describe and organize the data in a way that Max’s language models can understand. Here’s how the process works:

1. Authentication: Max requires authentication to ensure secure access to your data source. This can be done via API credentials, database logins, or other secure methods depending on the source.

2. Dataset Creation: After connecting to the data source via a Connector, one can create Datasets that describe the data’s structure and semantics. These Datasets allow Max to interpret and respond to natural language queries.

Data Security and Privacy

Max takes data security seriously and follows industry best practices to ensure that data is handled securely:

• Access Controls: Role-based access control (RBAC) allows administrators to control who can access and modify data connections and Datasets.
• On-Premise and Cloud Deployment: Max can be deployed either on-premise or in the cloud, ensuring that businesses with strict data residency or compliance requirements can securely connect their data sources.

Conclusion

Max’s ability to connect to key databases and file-based sources, along with its use of Datasets as a Semantic Layer, offers a powerful approach to data analysis. By describing data in ways that are easily understood by language models, Max allows businesses to leverage their data for insights, reporting, and decision-making without needing to perform complex queries or manual ETL work. Max ensures that working with data is simple, secure, and intuitive for both technical and non-technical users.

For more detailed instructions on connecting Max to your data and creating Datasets, visit the Data Connector Guide or reach out to our support team for assistance.