ai-agent

ptranking: Improve Ranking

Get ranking models with ptranking.
493 stars69 forksPythonGuide quality 8/10Updated 7/26/2022100% free · open source
What it does

Ptranking is a PyTorch-based library for learning to rank, which enables the development of custom ranking models for information retrieval and other applications.

When to use it
  • Building a search engine that requires a custom ranking algorithm
  • Developing a recommendation system that needs to prioritize items based on user behavior
  • Creating a question answering model that requires ranking potential answers
Ready-to-paste prompt
python ptranking/train.py -cfg configs/example.cfg -model ListingLR -data MovieLens -metric NDCG
Heads up: The library assumes that the PyTorch andtorchvision packages are installed and up-to-date, so ensure that you have the latest versions installed before using ptranking
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/ptranking && curl -fsSL https://workflowstacks.com/api/skills/ptranking/claude-skill -o ~/.claude/skills/ptranking/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How ptranking: Improve Ranking works
Codeflow
Free to inspect

Ptranking: Improve Ranking is mostly documents (16 doc files, 115 small scripts) — something you read, not something you run. There is nothing to install. Last commit 50 months ago, MIT license.

Size
Mostly documents
16 documents · 115 small scripts · days to read — use, don't read
Setup
Nothing to install
A guide / curated list. Just read it and follow the links.
Runs on
Nowhere — you read it
A reading resource, not a program.
Python 63%Jupyter Notebook 35%C 3%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    ptranking/__init__.py
    Inside ptranking/ — the main logic begins here
What's in each folder
ptranking/Core code — the actual logic115 files
docs/Documentation15 files
tutorial/Examples you can copy7 files
testing/Tests — proof it works29 files
img/Images & static assets2 files
READMEDocumentedMIT licenseLast update 50 mo ago
Quick Actions
Details
Creator
wildltr
Language
Python
Category
ai-agent
Published
9/15/2018

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.

Ready-to-run pack · one-time $29

Rank Tracker

A weekly email of where you actually rank on Google.

Includes the tested workflow and a written setup playbook. Needs: SerpAPI key (free tier).

See what you get