Tag: Big data
-
Microservices for machine learning
Posted on August 7, 2025, Level intermediate Resource Length medium
Learn how author scaled my ML-powered finance tracker by breaking a monolithic design into microservices for better performance, maintainability, and deployment. Author's finance tracker project started with a simple idea: automatically categorize bank transactions using a text classification model. Author trained a basic logistic regression model on my transaction history, wrapped it in a Flask API, and called it done. By Ramya Boorugula.
Tags microservices machine-learning big-data cloud agile
-
Apache Airflow for MLOPS and ETL - Description, benefits and examples
Posted on July 24, 2025, Level intermediate Resource Length long
Apache Airflow is a leading open-source tool for workflow orchestration, designed to manage complex tasks in Python. Developed by Airbnb and now part of the Apache Software Foundation, it's widely adopted for its flexibility and scalability in data engineering workflows. By Rost Glukhov.
Tags apache open-source analytics big-data data-science
-
How to develop a RAG system using Node.js
Posted on July 20, 2025, Level beginner Resource Length medium
In this blog post, we'll build a simplified but powerful RAG system using Node.js and OpenAI's GPT model, perfect for developers curious to bridge the gap between raw LLM power and domain-specific intelligence. By Deep Panchal.
Tags nodejs app-development frontend web-development big-data
-
Evogene and Google Cloud unveil foundation model for generative molecule design
Posted on June 18, 2025, Level beginner Resource Length long
Evogene and Google Cloud are accelerating life science discovery with ChemPass AI, a generative AI foundation model focused on small-molecule design. Launched in May, this collaboration dramatically reduces the time and cost associated with identifying novel drug candidates and crop protection agents. ChemPass AI's core strength lies in its ability to simultaneously optimize multiple critical properties – potency, toxicity, stability, and bioavailability – within a single molecule generation cycle, surpassing previous approaches. By Antoine Tardif.
Tags cloud data-science gcp big-data google
-
Anonymize RAG data in IBM Granite and Ollama using HCP Vault
Posted on June 8, 2025, Level beginner Resource Length long
In this summary, we explore how IBM Granite and Ollama can be integrated with HCP Vault to handle sensitive data effectively. The method involves configuring vaults to mask or tokenize data before passing it to the LLMs, ensuring that personal identifiable information (PII) is protected. By Rosemary Wang.
Tags ibm big-data ai data-science devops
-
Introducing KBLaM: Bringing plug-and-play external knowledge to LLMs
Posted on May 20, 2025, Level beginner Resource Length medium
Large language models (LLMs) have demonstrated remarkable capabilities in reasoning, language understanding, and even creative tasks. Yet, a key challenge persists: how to efficiently integrate external knowledge. By Taketomo Isazawa.
Tags azure cloud ai cio big-data
-
Retrieval Augmented Generation (RAG) tutorial for beginners
Posted on May 9, 2025, Level beginner Resource Length medium
Retrieval-augmented Generation (RAG) is an AI approach that improves machine understanding and response accuracy. By integrating traditional AI language models with real-time retrieval of relevant external data, RAG bridges knowledge gaps, enabling more precise and contextually rich answers. By Vidhi Gupta.
Tags machine-learning data-science big-data ai learning
-
Learnings from a machine learning engineer — data
Posted on May 5, 2025, Level beginner Resource Length long
Practical insights for a data-driven approach to model optimization. By David Martin.
Tags machine-learning data-science big-data how-to learning
-
Raspberry Pi AI camera explained: What it is & how to use it
Posted on April 24, 2025, Level beginner Resource Length long
The Raspberry AI Camera is a high-resolution visual sensor with a neural processing unit (NPU). This hardware makes it perfect for AI vision capabilities—such as object detection, pose estimation, and semantic segmentation—and lets it process images/videos on-device. By Thomas Dyan.
Tags big-data machine-learning ai robotics python
-
How gen AI is helping drive vehicle autonomy
Posted on April 12, 2025, Level beginner Resource Length long
AI can be a key enabler in overcoming technological hurdles to vehicle autonomy by generating synthetic datasets, for example. Collaboration within the autonomous vehicle industry is key to harnessing the potential of gen AI, while addressing associated risks. By Maria Alonso, Alex Koster and Paul Jordan.
Tags ai miscellaneous analytics big-data robotics
-
AI-driven weather prediction breakthrough reported
Posted on April 8, 2025, Level beginner Resource Length medium
Researchers say Aardvark Weather uses thousands of times less computing power and is much faster than current systems. By Rachel Hall and Ian Sample.
Tags ai agile miscellaneous analytics big-data cio data-science
-
Seven essential big data analytics tools every business needs in 2025
Posted on March 5, 2025, Level beginner Resource Length medium
Data floods in by the second, fueling every facet of business operations. Yet, raw data offers little value on its own — this is where big data analytics tools step in, transforming numbers into actionable insights. By Irina Prevalova.
Tags analytics cloud big-data database