ar9avg commited on
Commit
805743c
·
unverified ·
1 Parent(s): 92cc088

Refactor README.md by removing metadata and updating content

Browse files

Removed metadata section and updated project background description.

Files changed (1) hide show
  1. README.md +1 -16
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