Generate Markdown-based agent tasks from NLP prompts with optional OpenAI enhancement.
Project description
Agentec
Generate Markdown-based agent tasks from NLP prompts with optional OpenAI enhancement.
Installation
pip install agentec
Usage
Basic Usage
agentec "Summarize product reviews"
With OpenAI Enhancement
Set your OpenAI API key for enhanced task descriptions:
export OPENAI_API_KEY="your-api-key-here"
agentec "Create a data analysis pipeline"
Or add it to a .env file in your current directory:
OPENAI_API_KEY=your-api-key-here
Features
- Generate structured task files from natural language prompts
- Optional OpenAI integration for enhanced, detailed task descriptions
- Saves tasks in Markdown format in your current directory under
tasks/ - Cross-platform compatibility - works on Windows, macOS, and Linux
- Simple CLI interface - just provide your prompt and go
Example Output
Basic Task (without OpenAI)
# Task: summarize_product_reviews
## Prompt
Summarize product reviews
Enhanced Task (with OpenAI)
# Task: summarize_product_reviews
## Prompt
Summarize product reviews
## Enhanced Task Description
### Overview
This task involves analyzing and summarizing product reviews to extract key insights...
### Objectives
- Extract key themes from customer feedback
- Identify common complaints and praise
- Provide actionable insights for product improvement
### Steps/Requirements
1. Collect product reviews from various sources
2. Clean and preprocess the review data
3. Apply sentiment analysis
...
Requirements
- Python 3.7+
- Optional: OpenAI API key for enhanced task generation
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Author
Ahmed Hanoon - ahmedhanoon02@gmail.com
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file agentec-0.1.0.tar.gz.
File metadata
- Download URL: agentec-0.1.0.tar.gz
- Upload date:
- Size: 5.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.9.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
1c86f1069cd37cd6532670a65e2c6b9befa32e7df53d1c5a29c0abf22409df66
|
|
| MD5 |
94da2083fa0a565876c9c7cdcbc69416
|
|
| BLAKE2b-256 |
2b05ac0f1f53e89dd84b468e60d698ec118e1ecff9fad8440253b74fc665b114
|
File details
Details for the file agentec-0.1.0-py3-none-any.whl.
File metadata
- Download URL: agentec-0.1.0-py3-none-any.whl
- Upload date:
- Size: 6.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.9.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
02fd259204e6da13e4d6f3998b66eb8e085efb237a6deec91fbbdf940f5d13a5
|
|
| MD5 |
6db49bed0cc4fb12bec757c4c9abdc3d
|
|
| BLAKE2b-256 |
2ea538ec5ecc1ccad58d7705fdcd2c4923eac09e2dc0a456059218177d4f9339
|