DEV Community

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Why I stopped calling LLM APIs directly and built an Infrastructure Protocol

Why I stopped calling LLM APIs directly and built an Infrastructure Protocol

1
Comments
1 min read
Building an AI-Powered Personalized Learning Platform with FastAPI, PostgreSQL, and Mistral AI

Building an AI-Powered Personalized Learning Platform with FastAPI, PostgreSQL, and Mistral AI

3
Comments
2 min read
MCP Servers Explained: How AI Assistants Connect to Your Tools

MCP Servers Explained: How AI Assistants Connect to Your Tools

Comments
6 min read
Multi-LLM Orchestration in Production: Lessons from Running 16+ Models

Multi-LLM Orchestration in Production: Lessons from Running 16+ Models

Comments
6 min read
Building an AI-Powered CRM Chat Assistant with n8n and OpenRouter

Building an AI-Powered CRM Chat Assistant with n8n and OpenRouter

Comments
2 min read
Serving LLMs on IaaS: throughput vs latency tuning with practical guardrails

Serving LLMs on IaaS: throughput vs latency tuning with practical guardrails

Comments 1
9 min read
GeoSQL-Eval: Finally, a PostGIS Benchmark That Doesn’t Make Me Scream

GeoSQL-Eval: Finally, a PostGIS Benchmark That Doesn’t Make Me Scream

Comments
2 min read
Let's Build, Share and Deploy Agents: The Docker cagent Workshop

Let's Build, Share and Deploy Agents: The Docker cagent Workshop

Comments 1
3 min read
Semantic Caching in RAG Systems & AI Agents

Semantic Caching in RAG Systems & AI Agents

1
Comments 6
11 min read
I Asked the Same Question to 5 LLMs — The API Bill Ranged from $0.002 to $0.09

I Asked the Same Question to 5 LLMs — The API Bill Ranged from $0.002 to $0.09

Comments 2
4 min read
Creating Hierarchical AI Assistant Contexts: Global vs. Project-Specific Configurations

Creating Hierarchical AI Assistant Contexts: Global vs. Project-Specific Configurations

Comments
3 min read
How I saved $350 a month changing my EC2 instance

How I saved $350 a month changing my EC2 instance

1
Comments
4 min read
From LLM to Agent: How Memory + Planning Turn a Chatbot Into a Doer

From LLM to Agent: How Memory + Planning Turn a Chatbot Into a Doer

1
Comments
8 min read
Single-Pass RAG Is Dead — Here's What Replaced It in 2026

Single-Pass RAG Is Dead — Here's What Replaced It in 2026

Comments
5 min read
Why a 4B Parameter Model Now Beats GPT-3.5 — The 4 Techniques Behind Small Model Revolution

Why a 4B Parameter Model Now Beats GPT-3.5 — The 4 Techniques Behind Small Model Revolution

Comments
8 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.