Merge pull request austinLorenzMccoy#1 from austinLorenzMccoy/backend-revamp

Backend: migrate to pydantic-settings, update Groq model, add env ign…

Author: austinLorenzMccoy

.gitignore

@@ -121,6 +121,7 @@ celerybeat.pid
 
 # Environments
 .env
+backend/.env
 .venv
 env/
 venv/

app.py

@@ -0,0 +1,7 @@
+# Copy this file to .env and fill in the values
+APP_NAME=Text-to-SQL Backend
+SQLITE_PATH=../student.db
+
+# Groq settings
+GROQ_API_KEY="your_groq_api_key_here"
+GROQ_MODEL="llama-3.3-70b-versatile"

backend/.env.example

@@ -0,0 +1,134 @@
+# Text-to-SQL Backend (FastAPI + Groq)
+
+A modular FastAPI backend that converts natural language to SQL for the `STUDENT` table in `student.db` and executes queries safely.
+
+## Project Structure
+
+```
+backend/
+  app/
+    api/v1/
+      __init__.py
+      routes.py           # /health, /students, /sql, /nl2sql
+    core/
+      config.py           # Settings via Pydantic + .env
+      logging.py          # Basic logging setup
+    models/
+      schemas.py          # Pydantic models
+    services/
+      db.py               # SQLite access helpers
+      nl2sql.py           # Google Gemini integration
+    utils/
+      sql_cleaner.py      # Remove markdown, enforce semicolon
+    __init__.py
+    main.py               # FastAPI factory + include router
+  tests/
+    conftest.py           # Temp DB per test session
+    test_health.py
+    test_students.py
+    test_sql_cleaner.py
+    test_run_sql.py
+    test_nl2sql_endpoint.py
+  .env.example
+  api_demo.py
+  pyproject.toml
+  setup.py
+  README.md
+```
+
+## Requirements
+
+- Python 3.9+
+- Conda (for environment management)
+- SQLite database at `TextToSQLapp/student.db` (already in repo)
+
+## Quickstart (Conda + Uvicorn)
+
+```bash
+# from repo root
+# Option A: create from environment.yml
+conda env create -f backend/environment.yml
+conda activate text2sql-backend
+
+# Option B: create manually
+# conda create -n text2sql-backend python=3.11 -y
+# conda activate text2sql-backend
+# pip install -e backend[dev]
+
+# prepare env
+cp backend/.env.example backend/.env
+# then edit backend/.env and set GROQ_API_KEY
+
+# run API
+uvicorn app.main:app --reload --port 8000 --app-dir backend
+```
+
+Open: http://127.0.0.1:8000/docs
+
+## Endpoints
+
+- GET `/api/v1/health` → `{ "status": "ok" }`
+- GET `/api/v1/students` → list students
+- POST `/api/v1/sql` → body `{ "sql": "SELECT ...;" }`
+- POST `/api/v1/nl2sql` → body `{ "question": "..." }` returns `{ "sql": "...;" }`
+
+## Curl Demo
+
+```bash
+python backend/api_demo.py
+```
+
+Or manually:
+
+```bash
+curl http://127.0.0.1:8000/api/v1/health
+curl http://127.0.0.1:8000/api/v1/students
+curl -X POST http://127.0.0.1:8000/api/v1/sql \
+  -H 'Content-Type: application/json' \
+  -d '{"sql":"SELECT COUNT(*) FROM STUDENT;"}'
+
+curl -X POST http://127.0.0.1:8000/api/v1/nl2sql \
+  -H 'Content-Type: application/json' \
+  -d '{"question":"How many entries of records are present?"}'
+```
+
+## Testing & Coverage
+
+```bash
+# from backend/
+pytest
+# or with full output
+pytest -q --cov=app --cov-report=term-missing --cov-report=xml:coverage.xml
+```
+
+The test suite uses a temporary SQLite database and does not touch your real `student.db`.
+
+## Configuration
+
+Configuration is handled by `app/core/config.py` using Pydantic BaseSettings:
+
+- `APP_NAME` (default: Text-to-SQL Backend)
+- `SQLITE_PATH` (default: student.db)
+- `GROQ_API_KEY` (required for /nl2sql)
+- `GROQ_MODEL` (default: llama-3.1-70b-versatile)
+
+Env file: `backend/.env` (copy from `.env.example`).
+
+## Notes on NL→SQL
+
+- `app/services/nl2sql.py` integrates Groq via its OpenAI-compatible Chat Completions API.
+- `app/utils/sql_cleaner.py` strips markdown and enforces trailing semicolon.
+- Tests mock the model so CI can run without an API key.
+
+## Developing
+
+- Linting (optional):
+  ```bash
+  pip install ruff
+  ruff check backend/app
+  ```
+
+- Packaging:
+  - `pyproject.toml` defines project metadata, test, and coverage settings.
+  - `setup.py` provided for compatibility.
+

backend/README.md

@@ -0,0 +1,27 @@
+#!/usr/bin/env python3
+"""
+Simple demo commands to exercise the FastAPI backend.
+Run the server first:
+
+  uvicorn app.main:app --reload --port 8000
+
+Then run:
+
+  python backend/api_demo.py
+"""
+import subprocess
+
+BASE = "http://127.0.0.1:8000/api/v1"
+
+
+def run(cmd: list[str]):
+    print("$", " ".join(cmd))
+    out = subprocess.run(cmd, capture_output=True, text=True)
+    print(out.stdout or out.stderr)
+
+
+if __name__ == "__main__":
+    run(["curl", f"{BASE}/health"])  # Health
+    run(["curl", f"{BASE}/students"])  # List students
+    run(["curl", "-X", "POST", f"{BASE}/sql", "-H", "Content-Type: application/json", "-d", '{"sql":"SELECT COUNT(*) FROM STUDENT;"}'])
+    run(["curl", "-X", "POST", f"{BASE}/nl2sql", "-H", "Content-Type: application/json", "-d", '{"question":"How many entries of records are present?"}'])

backend/api_demo.py

@@ -0,0 +1,3 @@
+__all__ = [
+    "main",
+]

backend/app/__init__.py

@@ -0,0 +1,42 @@
+from fastapi import APIRouter, HTTPException
+from typing import List
+
+from ...models.schemas import NLQuery, SQLQuery, QueryResult, Student
+from ...services import db as db_service
+from ...services import nl2sql as nl2sql_service
+from ...utils.sql_cleaner import clean_sql_query
+
+router = APIRouter()
+
+
+@router.get("/health")
+def health() -> dict:
+    return {"status": "ok"}
+
+
+@router.get("/students", response_model=List[Student])
+def list_students() -> List[Student]:
+    try:
+        rows = db_service.fetch_all("SELECT NAME, CLASS, SECTION, MARKS FROM STUDENT;")
+        return [Student(name=r[0], class_name=r[1], section=r[2], marks=r[3]) for r in rows]
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+@router.post("/sql", response_model=QueryResult)
+def run_sql(query: SQLQuery) -> QueryResult:
+    try:
+        rows = db_service.fetch_all(query.sql)
+        return QueryResult(rows=rows)
+    except Exception as e:
+        raise HTTPException(status_code=400, detail=str(e))
+
+
+@router.post("/nl2sql", response_model=SQLQuery)
+def nl_to_sql(payload: NLQuery) -> SQLQuery:
+    try:
+        raw = nl2sql_service.generate_sql(payload.question)
+        cleaned = clean_sql_query(raw)
+        return SQLQuery(sql=cleaned)
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))

backend/app/api/v1/__init__.py

@@ -0,0 +1,28 @@
+from functools import lru_cache
+from pydantic import Field
+from pydantic_settings import BaseSettings, SettingsConfigDict
+from dotenv import load_dotenv
+
+# Load .env early
+load_dotenv()
+
+
+class Settings(BaseSettings):
+    app_name: str = Field("Text-to-SQL Backend", env="APP_NAME")
+    sqlite_path: str = Field("student.db", env="SQLITE_PATH")
+
+    # Groq (primary)
+    groq_api_key: str | None = Field(default=None, env="GROQ_API_KEY")
+    groq_model: str = Field("llama-3.1-70b-versatile", env="GROQ_MODEL")
+
+    # Deprecated/unused (kept for compatibility)
+    google_api_key: str | None = Field(default=None, env="GOOGLE_API_KEY")
+    gemini_model: str = Field("gemini-1.5-flash", env="GEMINI_MODEL")
+
+    # Pydantic v2 settings config
+    model_config = SettingsConfigDict(env_file=".env", case_sensitive=False)
+
+
+@lru_cache(maxsize=1)
+def get_settings() -> Settings:
+    return Settings()