The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!
-
Updated
Nov 15, 2024 - Python
The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!
TensorZero creates a feedback loop for optimizing LLM applications — turning production data into smarter, faster, and cheaper models.
Notes for Machine Learning Engineering for Production (MLOps) Specialization course by DeepLearning.AI & Andrew Ng
Scaffolding for serving ml model APIs using FastAPI
Kafka variant of the MLOps Level 1 stack
A "production-ready" simple project template to quickly start an Artificial Intelligence (AI), Machine Learning (ML) and/or Data Science (DS) project with basic files, branches and directory structure.
Companion notebooks for blogs/tutorials on ML4Devs website.
Fast, private data connectors for AI ⚡️🤖
Build end-to-end Machine Learning pipeline to predict accessibility of playgrounds in NYC
🔥🔥🔥🔥🧊🔥🔥 A Data Platform for Monitoring and Detecting Anomalies in Real-Time.
Study notes and demos.
Code for "Training models when data doesn't fit in memory" post
In the first course of Machine Learning Engineering for Production Specialization, you will identify the various components and design an ML production system end-to-end: project scoping, data needs, modeling strategies, and deployment constraints and requirements; and learn how to establish a model baseline, address concept drift, and prototype…
Vehicle data classification (supervised, unsupervised learning)
An easy-to-use tool for making web service with API from your own Python functions.
This Repo contains a Box Detection Application capable of identifying box containers in conveyor belt pictures.
The work shown in this repository is part of the Udacity scholarship program in collaboration with Microsoft for Machine Learning Engineer Nanodegree.
Crack SWE (ML) / DS MAANG Interviews
In this repository I have explained different ML Algorithms with their code.
Add a description, image, and links to the ml-engineering topic page so that developers can more easily learn about it.
To associate your repository with the ml-engineering topic, visit your repo's landing page and select "manage topics."