EEdna MainaOct 7 · 8 min readWhy We Chose Groq for High-Speed Text and Voice Processing.In conversational customer service, latency is the difference between trust and abandonment. When a member sends a question to their financial cooperative over WhatsApp, they expect an experience thatqdrant.hashnode.dev
1101_TheorySep 13 · 9 min readYour RAG Pipeline Doesn't Need More Retrieval, It Needs Better DecisionsFull Agentic RAG Collection 10 practical LangGraph architectures Get the Full Agentic RAG Collection Free Agentic RAG Fundamentals 4 practical notebooks Get the Free Notebooks Most RAG tutorials folloagenticragpatterns.hashnode.dev
MManu ShuklaAug 21 · 13 min readGroq retired llama-3.3-70b-versatile on 16 August 2026 and points production teams at a Preview modelGroq retired llama-3.3-70b-versatile on 16 August 2026 and points production teams at a Preview model Summary. On 16 August 2026 Groq shut down llama-3.1-8b-instant and llama-3.3-70b-versatile for freecorpit.hashnode.dev
AAsad IbrahimAug 10 · 6 min readHow I Cut My Voice Agent’s Groq API Usage by ~70% Without Changing the ModelA few weeks ago, I added a small AI voice assistant called Jarvis to my portfolio website. The setup was intentionally simple: Groq handled text generation, while the browser’s Web Speech API handled asadibrahim.hashnode.dev
MManu ShuklaJul 30 · 14 min readMeta shut down its Llama API in 2026: migrate your app and compare host costsMeta shut down its Llama API in 2026: migrate your app and compare host costs Summary. Meta shut down its hosted Llama API on 6 July 2026, and requests to the old endpoint now return a sunset responseecorpit.hashnode.dev
SShravan RevannaJul 7 · 6 min readI custom-built a skill for my Echo Dot that never rejects a question and controls my entire home - it runs on Groq now (gpt-oos 120b model)TL;DR — Stock Alexa says "Hmm, I don't know that" constantly. So I built a custom skill that hands my questions to Groq and answers in ~0.8 seconds — no more dead ends. And because it runs on a little1blog.shravanrevanna.me
PPratik R. MandgeJul 3 · 2 min read🚀 My First AI WhatsApp Bot – A Beginner-Friendly ProjectArtificial Intelligence is changing the way businesses interact with customers. To understand how AI automation works in the real world, I built my first AI-powered WhatsApp Bot. The goal was simple: pratikm363.hashnode.dev
JJeremy LongshoreJul 1 · 4 min readNixtla Repo: Zero to v0.2.0 with a Working Search-to-Slack PluginNew repo. Empty directory. By end of day: v0.2.0 tagged, a working plugin shipping, and a GitHub Pages site live. Repository Initialization The Nixtla Claude Code plugins workspace needed proper infrajeremylongshore.hashnode.dev
JJeremy LongshoreJul 1 · 10 min readDeterministic First, LLM Second: An Advisory CI Pre-ScreenThe old PR review system ran Gemini on every submission to the claude-code-plugins repo. It broke every time — quota errors, timeout, malformed JSON, the works. On 2026-05-15 I shipped a replacement ajeremylongshore.hashnode.dev
OOnkar KJun 29 · 5 min readPart 3: Tool Calling & CLI Chatbots🛠️ Pre-Flight Configuration Tech Stack: TypeScript, Bun/Node.js, Groq SDK (groq-sdk), Tavily SDK(@tavily/core) Prerequisites: Valid Groq and tavily API Keys, basic understanding of environment varionkark.hashnode.dev
