🔥 Smart prompt comparison & evaluation tool using LLM-as-judge. Compare multiple prompts, get intelligent scoring, and find the best one.
Project description
promptdiff 🔥
Smart prompt comparison tool for LLM apps.
Install
pip install promptdiff
Usage
from promptdiff import compare_prompts
result = compare_prompts(
prompts=["p1", "p2", "p3"],
question="Your question",
context="your context"
)
print(result["best_prompt"])
Features
- 🚀 Compare multiple prompts instantly
- 🧠 Smart scoring with keyword matching
- 🤖 LLM-as-judge evaluation
- 💡 AI-generated explanations
- 🔄 RAG integration ready
Example Output
✅ BEST PROMPT: P2
💡 WHY THIS IS BEST:
1. Uses context effectively
2. Provides actionable recommendations
Requirements
- Python 3.8+
- Ollama running locally
- Local LLM model (mistral, neural-chat, etc.)
Documentation
- Full docs: GitHub
- Quick start: See QUICKSTART.md
- Advanced: See README_DETAILED.md
License
MIT
Made with 🔥 for prompt engineers
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 promptdiff_chiru-0.1.0.tar.gz.
File metadata
- Download URL: promptdiff_chiru-0.1.0.tar.gz
- Upload date:
- Size: 5.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
cc64bd6f8dfaf1dbf1c37e5814d28c5d57c2d789d9ba9cce4abb04e26c351084
|
|
| MD5 |
ed330722c60b6bcc99c3acc3149396a8
|
|
| BLAKE2b-256 |
3a9bb397d56f6106f051f4ddbd2d4b384961b80688bc11667743bde7b79aa901
|
File details
Details for the file promptdiff_chiru-0.1.0-py3-none-any.whl.
File metadata
- Download URL: promptdiff_chiru-0.1.0-py3-none-any.whl
- Upload date:
- Size: 3.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
8dfe09c9148221e2f85673851d7e2ca001c90cda31a7fc89cf7b8079b1061954
|
|
| MD5 |
2b126ed137beab1125d0fbf98f916596
|
|
| BLAKE2b-256 |
9a9f28a19a5896333fa3e076bec43618d15c3d1cb51ba465c8b8e77b08038d54
|