in this category

LLM & Integration

Large language models, ChatGPT, Claude, GPT-4, prompt engineering, and LLM integration patterns

58 posts

LLM & IntegrationSeptember 28, 202619 min
Claude Inline Tools Beta: What Actually Ships (2026)
Claude's inline tools beta adds tools mid-conversation without busting the prompt cache. I traced exactly when each SDK shipped it, wire format included.
LLM & IntegrationSeptember 25, 202617 min
Claude Opus 5.5 tool_choice 400: 3 SDKs Tested (2026)
Claude Opus 5.5 rejects forced tool_choice with a 400. I captured what the AI SDK, LangChain and the raw SDK actually send, and built a preflight check.
LLM & IntegrationJuly 14, 202614 min
MCP Goes Stateless: The 2026-07-28 Spec Explained
MCP's July 28, 2026 spec goes stateless and ships Enterprise-Managed Authorization. Here's what changes, what breaks, and new security risks to plan for.
LLM & IntegrationJuly 8, 202617 min
Semantic Cache for LLM Calls with Redis Vector Sets (2026)
Build a semantic cache for LLM calls with Redis 8's native VADD/VSIM vector sets in Node.js and TypeScript — cache hits on paraphrases, not just exact text.
LLM & IntegrationJune 30, 202612 min
Cosine Similarity vs Dot Product for Embeddings (2026)
Cosine similarity vs dot product for embeddings, with runnable TypeScript. Learn when to normalize, why they match for unit vectors, and which to pick.
LLM & IntegrationJune 28, 202616 min
Token-Aware Text Chunking for RAG in TypeScript (2026)
Token-aware text chunking for RAG in TypeScript: recursive splitting with @langchain/textsplitters and js-tiktoken, plus chunk size and overlap tuning.
LLM & IntegrationJune 25, 202617 min
Count Tokens in TypeScript: Fit the Context Window (2026)
Count OpenAI tokens in TypeScript with gpt-tokenizer - no WASM, no API key. Count chat messages accurately and trim history to fit the model context window.
LLM & IntegrationJune 20, 202615 min
Test Vercel AI SDK Code with MockLanguageModelV3 (2026)
Unit-test Vercel AI SDK v6 code in TypeScript with MockLanguageModelV3 - no API key, no cost. Mock generateText, tool calls, and streaming in Vitest.
LLM & IntegrationJune 17, 202615 min
LLM Fallback Routing: Survive an AI Model Recall (2026)
When the US government pulled Claude Fable 5 offline, single-provider apps broke. Build a multi-provider LLM fallback chain that survives a model recall.
LLM & IntegrationMay 5, 202610 min
Building Smarter Apps with the OpenAI API
Build smarter apps with the OpenAI API: chat completions, vision, embeddings, function calling, and assistants. Patterns, runnable code, and real cost tips.
LLM & IntegrationApril 4, 202610 min
Vibe Coding Explained: The Future of AI-Assisted Development
Vibe coding: Andrej Karpathy's AI-assisted dev approach — describe what you want in plain English, let the model write the code. When it works vs. not.
LLM & IntegrationMarch 25, 202610 min
AI Study Tools 2026: The Ultimate Guide for Smarter Learning
AI study tools 2026: ChatGPT, Gemini, Perplexity, Claude, Notion AI, Wolfram Alpha, Otter.ai, NotebookLM. Which tool wins for research, notes, and review.

Every post in LLM & Integration (58)