OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Data Agents

DAT (Data Ask Tool)

DAT (Data Ask Tool) is an open-source Java framework for building natural-language data-querying applications with pre-modeled data, semantic models, LLM-based SQL generation and database execution. It provides a CLI for local project development and an SDK-oriented framework that developers can adapt into custom interfaces or services.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

DAT (Data Ask Tool) — OpenViST project profile in Data Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use DAT when natural-language access needs to be tied to pre-modeled enterprise data and a team wants to develop its own interface or service around the framework.

Who it is for

  • Data engineers building custom data assistants
  • Data analysts working with semantic models and business data
  • Developers creating web, workflow, OpenAPI or MCP interfaces for data querying

Documented uses

  • Translate natural-language questions into database queries
  • Represent entities, dimensions and measures in semantic models
  • Add business context, synonyms and prior question-answer pairs for retrieval-augmented querying
  • Create a foundation for custom data-questioning applications
Before you choose

Requirements & limits

The repository is public and identified as open source under the Apache-2.0 license. The documented setup uses the DAT CLI and local Java-based development.

  • The project expects semantic and data modeling rather than an unconfigured natural-language database connection.
  • Supported database examples include MySQL, PostgreSQL, Oracle and DuckDB.
  • The architecture supports pluggable database, LLM and embedding components through SPI-based extension points.
  • Teams can build their own web UI or expose services through the documented SDK, OpenAPI or MCP paths.
  • RAG-related capabilities depend on configured embedding and vector-storage components such as DuckDB, Weaviate or PGVector.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up a DAT project with a configured data source

Create a local DAT project and connect it to a database and language model.

Before you start

  • Java 17 or newer
  • A DAT CLI release
  • MySQL, PostgreSQL, Oracle or DuckDB
  • An LLM provider and API configuration

Steps

  1. Install the DAT CLI by downloading and extracting the release archive, then add its bin directory to PATH.

  2. Run dat init and provide the project name, description and database type.

  3. Edit the generated dat_project.yaml with the database URL and credentials, LLM provider settings and embedding provider.

  4. Create semantic model definitions in the models/ directory.

Expected outcome

A locally initialized DAT project with configured data and model settings ready for the next documented project stage.

Guide limitations

  • This setup recipe does not document a completed query run or deployment.
  • The project requires suitable database, LLM and embedding configuration for its intended workflow.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Retrieval-augmented applications

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
DAT (Data Ask Tool)Translate natural-language questions into database queriesCloud, Self-hosted, ServerThe repository is public and identified as open source under the Apache-2.0 license. The documented setup uses the DAT CLI and local Java-based development.
Db GptAsk natural-language questions over connected data sources.Cloud, Self-hosted, ServerThe project is publicly available as an open-source repository and is identified as MIT-licensed. Its documented one-line installer targets macOS and Linux; the supplied evidence does not establish pricing or account requirements.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
3 October 2026
Original website title
hexinfo/dat · Official homepage title · retained in its source language
How we review sourcesSuggest a correction