Latest in Building with LLMs

medium.com
134 words

RAG Retrieval-Augmented Generation

A deep-dive walkthrough of Retrieval-Augmented Generation for.NET developers covering RAG architecture, document ingestion and PDF/text…Continue...reading on Medium » A deep-dive walkthrough of Retrieval-Augmented Generation for.NET developers covering RAG architecture, document ingestion and PDF/text extraction, chunking…

dev.to
275 words

Unsloth + Ollama: Fine-Tune and Run Local LLMs

thousands of dollars on cloud LLM API tokens. Fine-tuning an 8B parameter model no longer requires a cluster...cloud compute budgets. By pairing Unsloth with Ollama, you can perform QLoRA local fine tuning on a consumer GPU using under 8GB of VRAM,…

174 words

What is Retrieval Augmented Generation (RAG)?

Retrieval Augmented Generation is a pipeline framework that retrieves information via an external...solutions struggle with knowledge retrieval. Retrieval Augmented Generation addresses this issue by separating...generation process. Learn more about what it takes to make RAG work and how…

Building with LLMs

Engineering LLM applications: RAG and vector search, prompt and context engineering, fine-tuning and evals, local LLMs and inference.

  • 3 Subtopics
  • 118 Tracked terms
  • Last 30 days Feed window

Inside Building with LLMs

RAG & Vector Search Retrieval-augmented generation, embeddings, chunking, vector databases, hybrid search, reranking and RAG architecture write-ups.
Prompt & Context Engineering Prompt engineering, context engineering, system prompts, structured output, function calling and prompt patterns.
Local LLMs & Inference Running models locally: Ollama, llama.cpp, vLLM, quantization, GPU inference serving, small language models and edge deployment.

What this topic collects on

An article joins this feed when it matches these terms. Each one is also a search of its own.

  • +78 more