acadiaway/gemini_nl2sql

synatx 3

syntax2

syntax

adjust safety settings to allo responses

use Python for debug notifications to be displayed

pipeline with the bug messages for Google API -v3 syntax

pipeline with the bug messages for Google API -v2

pipeline with the bug messages for Google API

using Gemini NL2SQL

use API Qwen model

use API access instaed of downloding the model

Switch to HF Inference API approach - eliminate model loading

app.py original

app.py test db access

defog/sqlcoder-7b switch txt-2-SQL model

Simplify Dockerfile, use /tmp/cache/huggingface, preload model in pipeline.py

Remove invalid cache_dir from vLLM preload to fix TypeError

Preload model in Dockerfile and pipeline.py to fix PermissionError

Dockerfile permission for cache 777 and no locking

requirements.txt lower ver torch down 2.7.1

syntax err

Dockerfile pipeline.py requirements.txt optized parallelism

Update requirements.txt

Fix SyntaxError in pipeline.py by completing f-string prompt

Update Dockerfile to use python:3.12-slim for vllm==0.10.1 compatibility

Update Dockerfile and requirements.txt to resolve torch/vllm dependency conflict

Initial Streamlit template setup with vLLM

initial commit

Duplicate from streamlit/streamlit-template-space