sql-agent / src

Commit History

Fix SVG download: use single quotes inside style attr, no duplicate style
964b628
Running
verified

DanielRegaladoCardoso commited on

Cap to top 30 categories, hide gr.File X button, single-row buttons, no duplicate title
7d5a424
verified

DanielRegaladoCardoso commited on

Result narration (Qwen-powered) + UI polish for upload area + dark-mode fixes
5ae5227
verified

DanielRegaladoCardoso commited on

Result narration (Qwen-powered) + UI polish for upload area + dark-mode fixes
7af78a0
verified

DanielRegaladoCardoso commited on

SQL self-correction: 3 retries with error context + GROUP BY rule in prompt
f5b7f67
verified

DanielRegaladoCardoso commited on

SQL self-correction: 3 retries with error context + GROUP BY rule in prompt
e6681c9
verified

DanielRegaladoCardoso commited on

SVG: standalone download (XML prolog, white bg, fixed dims) + Plotly first
0ac4ef2
verified

DanielRegaladoCardoso commited on

SVG: standalone download (XML prolog, white bg, fixed dims) + Plotly first
89360e0
verified

DanielRegaladoCardoso commited on

Better SQL prompt: column-name mapping rules + few-shot + distinct value hints
a7fa6d3
verified

DanielRegaladoCardoso commited on

Better SQL prompt: column-name mapping rules + few-shot + distinct value hints
b0a300f
verified

DanielRegaladoCardoso commited on

Pin kaleido==0.2.1 + native SVG fallback when kaleido fails
064c0d2
verified

DanielRegaladoCardoso commited on

UX: CSV/SVG download links, schema preview on load, cleaner SVG theme
a172c0c
verified

DanielRegaladoCardoso commited on

Load LoRA via PeftModel on top of standard base models (fixes r=16 vs r=8 mismatch)
1bbdff9
verified

DanielRegaladoCardoso commited on

Load LoRA via PeftModel on top of standard base models (fixes r=16 vs r=8 mismatch)
eb30a86
verified

DanielRegaladoCardoso commited on

Load LoRA via PeftModel on top of standard base models (fixes r=16 vs r=8 mismatch)
730b25d
verified

DanielRegaladoCardoso commited on

ZeroGPU best practice: load models at module level (cuda), inference only inside @spaces.GPU
420b1db
verified

DanielRegaladoCardoso commited on

ZeroGPU best practice: load models at module level (cuda), inference only inside @spaces.GPU
61aee8d
verified

DanielRegaladoCardoso commited on

ZeroGPU best practice: load models at module level (cuda), inference only inside @spaces.GPU
a57eca6
verified

DanielRegaladoCardoso commited on

ZeroGPU best practice: load models at module level (cuda), inference only inside @spaces.GPU
c2ac226
verified

DanielRegaladoCardoso commited on

Sequential model load/unload: keep peak VRAM at ~14GB
292fdf4
verified

DanielRegaladoCardoso commited on

Sequential model load/unload: keep peak VRAM at ~14GB
fab3ba1
verified

DanielRegaladoCardoso commited on

Initial deploy: Apple/Claude design, DuckDB, 3 trained LoRAs
a067ada
verified

DanielRegaladoCardoso commited on