README.md

---
title: Task Prompting
emoji: 🚀
colorFrom: blue
colorTo: indigo
sdk: gradio
sdk_version: 6.11.0
app_file: app.py
pinned: false
---

# Task Prompting Tool

A tool designed for project managers and team leaders to generate developer-ready prompts. By providing a task description, specifying a field (e.g., Backend, Frontend), and uploading relevant context files, the underlying LLM (OpenAI or Google Gemini) will construct a comprehensive prompt ready to be handed to developers.

## Prerequisites

- Python 3.8+
- API keys for OpenAI and/or Google Gen AI.

## Setup Instructions

**1. Create Hand-configured Keys in `.env`**
Edit the `.env` file and insert your API keys and models as preferred:
```env
OPENAI_API_KEY="your-openai-api-key"
GOOGLE_API_KEY="your-google-api-key"
LLM_PROVIDER="google" # Options: "google" or "openai"
OPENAI_MODEL="gpt-4.1-mini"
GOOGLE_MODEL="gemini-3.1-flash-lite-preview"
```

**2. Setup Virtual Environment & Install Dependencies**
Open a terminal and run the following commands in the project directory:

```bash
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
```

## Running the Application

### Method 1: Using the UI (Recommended)
You can directly run the Gradio application to access the user interface.

```bash
source venv/bin/activate
python app.py
```
After executing, an interface will open at `http://127.0.0.1:7860/` by default. You can open your browser to this URL to interact with the Task Prompting Tool.

### Method 2: Running the API Server
If you'd like to integrate this logic into another system or frontend, run the FastAPI backend:

```bash
source venv/bin/activate
python api.py
```
The server will run at `http://0.0.0.0:8000`. 
- View API Documentation at `http://127.0.0.1:8000/docs` to test endpoints interactively.