DEV Community

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Tackle High Token Usage with GraphRAG
apoorva_sachan profile

Tackle High Token Usage with GraphRAG

#devchallenge #llm #performance #rag
1
Comments
4 min read
High-Value If, Low-Value Foreach: Why Agents Trade in Judgment Structures, Not Models
suhui profile

High-Value If, Low-Value Foreach: Why Agents Trade in Judgment Structures, Not Models

#ai #agents #llm #mcp
2
Comments
23 min read
How to build a production RAG pipeline in Python (without a vector database)
ayinedjimi-consultants profile

How to build a production RAG pipeline in Python (without a vector database)

#python #ai #llm #tutorial
1
Comments
5 min read
ModelChain: Measurable LLM Router with Adaptive Model Selection, Real-Time Scoring, Budget Guards and Failover for Node.js, Edge and Browser
davcavalcante profile

ModelChain: Measurable LLM Router with Adaptive Model Selection, Real-Time Scoring, Budget Guards and Failover for Node.js, Edge and Browser

#showdev #ai #javascript #llm
Comments 1
3 min read
My AI Agent Kept Lying to Me. Then It Tried to Trick Me.
mariatanbobo profile

My AI Agent Kept Lying to Me. Then It Tried to Trick Me.

#ai #llm #devops #hermes
Comments 2
5 min read
Como treinei uma IA de suporte com histórico real de atendimento: da conversa bruta ao RAG em produção
gaabrielbrocco profile

Como treinei uma IA de suporte com histórico real de atendimento: da conversa bruta ao RAG em produção

#ai #rag #llm #datascience
1
Comments 1
11 min read
Stop Burning Cash on Long-Context RAG: Ephemeral Prompt Caching with Spring AI and JTokkit
machinecodingmaster profile

Stop Burning Cash on Long-Context RAG: Ephemeral Prompt Caching with Spring AI and JTokkit

#java #ai #llm #systemdesign
Comments 1
2 min read
The Daimon Java SDK: Chat, Stream, and Query Memory from 3 Lines of Java
sonicboom15 profile

The Daimon Java SDK: Chat, Stream, and Query Memory from 3 Lines of Java

#ai #java #llm #tutorial
Comments
5 min read
Show HN: Needle distilled Gemini tool calling en 26M parámetros — lectura técnica sin hype
jtorchia profile

Show HN: Needle distilled Gemini tool calling en 26M parámetros — lectura técnica sin hype

#spanish #espanol #typescript #llm
Comments
9 min read
Stop Burning Tokens on Chat / Agent Loops — Here's What Actually Works
lililililili profile

Stop Burning Tokens on Chat / Agent Loops — Here's What Actually Works

#ai #llm #webdev #agents
Comments 1
6 min read
When the LLM Refuses: A Fallback Chain That Salvages Most Refusals
sm1ck profile

When the LLM Refuses: A Fallback Chain That Salvages Most Refusals

#ai #llm #python
Comments 1
5 min read
Welcome to the Slop KPI Era: How Tokenmaxxing Is Making AI Worse
mishlan profile

Welcome to the Slop KPI Era: How Tokenmaxxing Is Making AI Worse

#ai #llm #mcp #agents
1
Comments
4 min read
Your RAG Pipeline Is Failing 40% of Queries. Here's the Fix.
spicykim profile

Your RAG Pipeline Is Failing 40% of Queries. Here's the Fix.

#rag #ai #llm #machinelearning
Comments
2 min read
Inworld TTS Paralinguistic Tags Don't Work — Here's What Does
sm1ck profile

Inworld TTS Paralinguistic Tags Don't Work — Here's What Does

#ai #tts #llm #voice
Comments 1
4 min read
Qwen3.7 Max vs Open-Weight LLMs: Practical Migration Notes
alanwest profile

Qwen3.7 Max vs Open-Weight LLMs: Practical Migration Notes

#ai #llm #opensource #machinelearning
2
Comments
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.