OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Db Gpt Hub

Db Gpt Hub is an open-source Python repository of models, datasets and fine-tuning techniques for improving language-model performance on Text-to-SQL, with related fine-tuning material for semantic understanding and graph-query generation.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Db Gpt Hub — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you need a source-based Python workflow for adapting and evaluating an LLM on SQL-generation tasks, or want to explore its related semantic-understanding and graph-query tracks.

Who it is for

  • Developers adapting language models to generate SQL from natural-language requests.
  • Researchers or practitioners preparing structured-query data and comparing fine-tuning approaches.
  • Teams exploring language-model fine-tuning for semantic understanding or graph-query generation.

Documented uses

  • Preprocess Text-to-SQL training and development data.
  • Configure supervised fine-tuning for a selected model and dataset.
  • Generate predictions from a configured model and checkpoint.
  • Evaluate Text-to-SQL results using execution accuracy.
  • Explore related Text2NLU and Text2GQL fine-tuning workflows.
Before you choose

Requirements & limits

The public GitHub repository is available under the MIT license. The documented setup uses Git, Conda and Python 3.10.

  • The README describes a multi-stage development workflow: data preprocessing, fine-tuning, prediction and evaluation.
  • The example configuration uses CodeLlama-13B-Instruct with LoRA, but settings such as the model, dataset, sequence lengths and training parameters are configurable.
  • The repository reports execution-accuracy baselines across multiple models and methods; results may depend on the selected model, dataset and configuration.
  • The project is a Python repository and toolkit, not a hosted Text-to-SQL application.

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 the Text-to-SQL Python package

Create the documented Conda environment and install the repository's SQL module in editable mode.

Before you start

  • Git
  • Conda
  • Python 3.10

Steps

  1. Clone the DB-GPT-Hub repository and change into its directory.

  2. Create and activate a Conda environment named dbgpt_hub with Python 3.10.

  3. Change into src/dbgpt_hub_sql and install the module with pip install -e .

Expected outcome

The Text-to-SQL module is installed in the activated environment for further configuration.

Guide limitations

  • This setup sequence does not by itself configure a model or dataset, train a model, generate predictions or evaluate results.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
eosphoros-ai/DB-GPT-Hub · Official homepage title · retained in its source language
How we review sourcesSuggest a correction