Peter Song

Peter Song is a machine learning, data engineer, and AI writer with a focus on practical ML workflows. He shares insights on machine learning, data tools, and MLOps.

Virtualenv vs Conda vs Poetry for Machine Learning

by

Environment management remains one of the most contentious topics in Python development, and machine learning amplifies the complexity. The choice between virtualenv, Conda, and Poetry profoundly impacts your workflow, dependency resolution, reproducibility, and deployment pipeline. While all three tools manage Python environments, their approaches differ fundamentally—especially for machine learning projects with complex dependencies like TensorFlow, … Read more

Using Local LLMs for Private Document Search

by

Privacy concerns around sensitive documents have made local AI solutions increasingly attractive. Whether you’re managing confidential business documents, personal medical records, legal files, or proprietary research, sending this information to cloud-based AI services poses significant risks. Local large language models (LLMs) combined with vector databases offer a powerful alternative: private, secure document search that never … Read more

How to Reduce VRAM Usage When Running LLMs Locally

by

Running large language models (LLMs) on your own hardware offers privacy, control, and cost savings compared to cloud-based solutions. However, the primary bottleneck most users face is VRAM (Video Random Access Memory) limitations. Modern LLMs can require anywhere from 4GB to 80GB of VRAM, making them inaccessible to users with consumer-grade GPUs. Fortunately, several proven … Read more

Best Local LLM for RAG (Retrieval-Augmented Generation)

by

Retrieval-augmented generation has transformed how we build intelligent systems that work with knowledge bases. By combining document retrieval with language model generation, RAG enables AI to answer questions grounded in specific sources rather than relying solely on training data. When implementing RAG locally, choosing the right language model becomes critical—you need a model that follows … Read more

Ollama vs LM Studio vs GPT4All: Which Is Best for Local LLMs?

by

The explosion of accessible local LLM tools has created both opportunity and confusion. Three platforms—Ollama, LM Studio, and GPT4All—have emerged as the leading solutions for running large language models on your own hardware. Each takes a fundamentally different approach to the same goal: making AI accessible without cloud dependencies. Choosing between them isn’t about finding … Read more

When NOT to Use Agentic AI (and What to Use Instead)

by

The excitement around agentic AI is palpable and justified. Systems that can autonomously pursue goals, chain together multiple actions, and adapt to changing circumstances represent a genuine leap forward in artificial intelligence capabilities. From autonomous coding assistants to customer service agents that handle complex multi-step inquiries, agentic AI promises to automate tasks that previously required … Read more

Running Multiple Local LLMs: Memory & Performance Optimization

by

The ability to run multiple local LLMs simultaneously unlocks powerful workflows that single-model setups cannot achieve. Imagine switching instantly between a coding specialist, a creative writing model, and a general conversation assistant without reloading—or running them concurrently for complex tasks requiring different expertise. Yet most guides focus on running a single model optimally, leaving users … Read more

Quantized LLMs Explained: Q4 vs Q8 vs FP16

by

Quantization has emerged as the breakthrough technique that makes running powerful language models on consumer hardware practical. Without quantization, a 7-billion parameter model would require 28GB of RAM at full precision—placing it beyond the reach of most users. With 4-bit quantization, that same model runs comfortably in 6GB, transforming accessibility completely. Yet despite its importance, … Read more

How to Serve Local LLMs as an API (FastAPI + Ollama)

by

Running large language models locally gives you privacy, control, and independence from cloud services. But to unlock the full potential of local LLMs, you need to expose them through a robust API that applications can consume reliably. Combining FastAPI—Python’s modern, high-performance web framework—with Ollama’s efficient LLM serving capabilities creates a production-ready API that rivals commercial … Read more

What Is an AI Agent? A Simple Explanation with Examples

by

The term “AI agent” has surged in popularity alongside recent advances in artificial intelligence, yet many people remain unclear about what distinguishes an agent from other AI systems. While chatbots and image generators have captured public imagination, AI agents represent a fundamentally different approach—one that promises to transform how we interact with technology by shifting … Read more