Spaces:
Sleeping
Sleeping
Refactor README.md by removing metadata and updating content
Browse filesRemoved metadata section and updated project background description.
README.md
CHANGED
|
@@ -1,18 +1,3 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: SQL Agent OpenEnv
|
| 3 |
-
emoji: 🗄️
|
| 4 |
-
colorFrom: blue
|
| 5 |
-
colorTo: purple
|
| 6 |
-
sdk: docker
|
| 7 |
-
pinned: false
|
| 8 |
-
tags:
|
| 9 |
-
- sql
|
| 10 |
-
- reinforcement-learning
|
| 11 |
-
- contextual-bandit
|
| 12 |
-
- linucb
|
| 13 |
-
- gepa
|
| 14 |
-
---
|
| 15 |
-
|
| 16 |
# SQL Agent OpenEnv
|
| 17 |
|
| 18 |
> **Origin:** This project is a port of [gepa-tuned-sql-agent](https://github.com/Ar9av/gepa-tuned-sql-agent) — originally built as a TypeScript/Next.js application — rewritten in Python (FastAPI + React/Vite) to match the OpenEnv format and deploy on Hugging Face Spaces.
|
|
@@ -28,7 +13,7 @@ An OpenEnv-compliant RL environment for SQL generation, featuring:
|
|
| 28 |
|
| 29 |
## Background
|
| 30 |
|
| 31 |
-
The original [gepa-tuned-sql-agent](https://github.com/Ar9av/gepa-tuned-sql-agent) explored three research ideas in a Next.js stack:
|
| 32 |
|
| 33 |
1. **Self-debug loop** — the agent critiques and fixes its own SQL errors without human intervention
|
| 34 |
2. **GEPA prompt evolution** — after user feedback, an LLM reflects on failures and evolves the system prompt
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# SQL Agent OpenEnv
|
| 2 |
|
| 3 |
> **Origin:** This project is a port of [gepa-tuned-sql-agent](https://github.com/Ar9av/gepa-tuned-sql-agent) — originally built as a TypeScript/Next.js application — rewritten in Python (FastAPI + React/Vite) to match the OpenEnv format and deploy on Hugging Face Spaces.
|
|
|
|
| 13 |
|
| 14 |
## Background
|
| 15 |
|
| 16 |
+
The original [gepa-tuned-sql-agent](https://github.com/Ar9av/gepa-tuned-sql-agent) explored three research ideas in a Next.js stack which i started keeping this hackathon in mind 1 week back and relaising the submission criteria had to migrate to python:
|
| 17 |
|
| 18 |
1. **Self-debug loop** — the agent critiques and fixes its own SQL errors without human intervention
|
| 19 |
2. **GEPA prompt evolution** — after user feedback, an LLM reflects on failures and evolves the system prompt
|