DB-GPT-Hub
Repository for DB-GPT models, datasets, and techniques aimed at Text-to-SQL performance enhancement.
GraphCanon updated 3w · GitHub synced 3w
Decision brief
DB-GPT-Hub offers resources for improving DB-GPT's Text-to-SQL capabilities through fine-tuning techniques and relevant datasets.
Good fit when
- Use when you need to improve Text-to-SQL performance specifically with the DB-GPT model, as this repository is specialized for enhancing its functionalities.
- Prefer it if you are engaged in projects requiring conversion of natural language queries into SQL syntax where domain-specific enhancements can leverage pre-existing fine-tuning methods.
Avoid when
- Avoid using when your project does not involve the DB-GPT model, as resources and techniques here are tailor-made for this specific model.
- Do not utilize if you require immediate results without the need for model customization or performance enhancement through fine-tuning.
Observed Jul 15, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (387d since push)
- As of 3w
- Provenance
- Not a fork · Organization account
- As of 3w
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install DB-GPT-HubSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Includes models, datasets, fine-tuning methods to improve DB-GPT performance in converting natural language queries into SQL.
Capability facts
- Languages
- python
Source: github.language · Jul 24, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Jul 24, 2026)
```python from dbgpt_hub_sql.data_process import preprocess_sft_dataSource link
Tags
README
3.2 Quick Start
Firstly, install dbgpt-hub with the following command
pip install dbgpt-hub
Then, set up the arguments and run the whole process.
from dbgpt_hub_sql.data_process import preprocess_sft_data
from dbgpt_hub_sql.train import start_sft
from dbgpt_hub_sql.predict import start_predict
from dbgpt_hub_sql.eval import start_evaluate
For agents
This page has a .md twin and JSON over the API.