pyod
model.nvim
pyod | model.nvim | |
---|---|---|
7 | 3 | |
7,962 | 264 | |
- | - | |
7.5 | 9.6 | |
4 days ago | 11 days ago | |
Python | Lua | |
BSD 2-clause "Simplified" License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
pyod
-
A Comprehensive Guide for Building Rag-Based LLM Applications
This is a feature in many commercial products already, as well as open source libraries like PyOD. https://github.com/yzhao062/pyod
-
Analyze defects and errors in the created images
PyOD
-
Multivariate Outlier Detection in Python
Check out the algorithms and documentation in this toolkit. It’ll give you a list of methods to read up on to understand their mechanisms. https://github.com/yzhao062/pyod
- Pyod – A Comprehensive and Scalable Python Library for Outlier Detection
- Predictive Maintenance and Anomaly Detection Resources
-
[D] Unsupervised Outlier Detection - Advise Requested
The source code and documentaion of PyOD is the best survey about OOD. Besides, the normalized flow and VQVAE are also feasible.
- PyOD: ~50 anomaly detection algorithms in one framework.
model.nvim
-
A Comprehensive Guide for Building Rag-Based LLM Applications
For local stuff with a handful of documents, you can even just throw it into a json and call it a day. The similarity search is as simple as an np.dot: https://github.com/gsuuon/llm.nvim/blob/main/python3/store.p...
-
Show HN: Script to Auto-Generate Commit Messages with AI
My plugin is here: https://github.com/gsuuon/llm.nvim -- one of the "starter prompts" is commit message, so with vim-fugitive I open up the git status window, stage my changes, press 'cc', then ':Llm commit\ message' (or just ':Llm mess' tab complete). Then I make changes as needed. I notice that normally it fails to capture my intent for larger changes (things that should be refactor for example get labeled as feat), and readme only changes are sometimes not labeled as 'docs' correctly.
Here's where the commit message prompt is: https://github.com/gsuuon/llm.nvim/blob/2d771cc882ad9edd8011...
-
Burnout Because of ChatGPT?
I plug it directly into my editor (via https://github.com/gsuuon/llm.nvim) and have it fill out code for me. I write what I want with comments and ask it to fill the rest - if it's straightforward enough it basically always works. I also get it to write commit messages (based on git diff) - though I need to improve my prompt a bit as it gets verbose and I end up rewriting it most of the time. I was working on trying to feed it things like hover and tree-sitter information before I got distracted, but that'd be another power boost as well whenever I get around to it.
What are some alternatives?
tods - TODS: An Automated Time-series Outlier Detection System
llama-hub - A library of data loaders for LLMs made by the community -- to be used with LlamaIndex and/or LangChain
isolation-forest - A Spark/Scala implementation of the isolation forest unsupervised outlier detection algorithm.
go.nvim - A feature-rich Go development plugin, leveraging gopls, treesitter AST, Dap, and various Go tools to enhance the dev experience.
alibi-detect - Algorithms for outlier, adversarial and drift detection
neoai.nvim - Neovim plugin for intracting with GPT models from OpenAI
pycaret - An open-source, low-code machine learning library in Python
llmflows - LLMFlows - Simple, Explicit and Transparent LLM Apps
anomalib - An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.
llm-applications - A comprehensive guide to building RAG-based LLM applications for production.
stumpy - STUMPY is a powerful and scalable Python library for modern time series analysis
vectara-answer - LLM-powered Conversational AI experience using Vectara