Welcome to the future of database interactions! With Dataherald, you can transform how you extract insights from relational data using simple, natural language queries. This guide will walk you through setting up Dataherald and using its powerful components to streamline data querying in your organization.

What is Dataherald?

Dataherald is a natural language-to-SQL engine designed for enterprise-level question answering over relational data. It enables business users to extract insights from data without needing technical expertise. Imagine being able to ask your database questions like, “What were our sales last quarter?” and getting immediate answers without the intervention of a data analyst.

Key Components of Dataherald

This repository contains four main components, each serving a different purpose:

• Engine: The core natural language-to-SQL engine that can operate independently without user authentication.
• Enterprise: The API layer that incorporates authentication and organizational logic into Dataherald.
• Admin-console: A GUI front-end for configuration and observability of Dataherald, requiring both engine and enterprise to function.
• Slackbot: Interact with Dataherald through Slack, dependent on both the engine and enterprise components.

Getting Started: Running Dataherald Locally

Follow these steps to set up Dataherald on your local machine:

1. Set Environment Variables

Each service requires specific environment variables. Check the .env.example file in each service directory to create your local .env file with the necessary values. For the Next.js front-end, use .env.local.

2. Run Services

To run all services simultaneously, use the provided script located in the root directory:

bash sh docker-run.sh

This script sets up a common Docker network and runs each service in detached mode, allowing you to get started quickly.

Understanding the Code: An Analogy

Imagine you own a gigantic library (your relational database) filled with countless books (data). Now, you have a smart librarian (Dataherald) who understands plain English. When you ask this librarian a question, like “Show me all the detective novels published last year,” they don’t just grab a random book; they immediately find and retrieve exactly what you need. The process of converting your plain language request into a structured library query (SQL) is what Dataherald excels at. Each component mentioned (engine, enterprise, admin-console, slackbot) helps make the librarian more efficient and user-friendly.

Troubleshooting Tips

If you encounter issues during setup or while running the services, consider the following solutions:

• Ensure that all environment variables are correctly set in your .env file. A missing or incorrect value can cause service disruptions.
• Check the version compatibility of Docker as each component may rely on specific Docker features.
• If you have problems running the docker-run.sh script, verify that you have execution permissions. You can grant this with chmod +x docker-run.sh.
• For more insights, updates, or to collaborate on AI development projects, stay connected with fxis.ai.

Contributing to Dataherald

As an open-source project rapidly advancing in a dynamic field, Dataherald welcomes contributions. Whether it’s new features, infrastructure improvements, or enhanced documentation, your help is appreciated. For more details on how to contribute, refer to the CONTRIBUTING guide.

At fxis.ai, we believe that such advancements are crucial for the future of AI, as they enable more comprehensive and effective solutions. Our team is continually exploring new methodologies to push the envelope in artificial intelligence, ensuring that our clients benefit from the latest technological innovations.