DEV Community

#rag

Retrieval augmented generation, or RAG, is an architectural approach that can improve the efficacy of large language model (LLM) applications by leveraging custom data.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
RAG Without a Vector Database: My Production Assistant Runs on MariaDB and 10 Lines of Cosine Similarity
sunny_dagar_9dc293f7ebf1d profile

RAG Without a Vector Database: My Production Assistant Runs on MariaDB and 10 Lines of Cosine Similarity

#ai #rag #php
1
Comments
2 min read
Your agent already has the answer. You are paying it to look again.
tom_jones_230c4659491adcd profile

Your agent already has the answer. You are paying it to look again.

#discuss #ai #rag #architecture
3
Comments 2
13 min read
RAG Architecture Beyond the Demo: Retrieval, Thai Chunking, and Production Boundaries
dev_next4i profile

RAG Architecture Beyond the Demo: Retrieval, Thai Chunking, and Production Boundaries

#rag #knowledgemanagement #llm #next4i
Comments 1
7 min read
TrustGraph 2.9: A Config-Driven Workbench, Leaner Core, and Smarter Catalog Loading
jackcolquitt profile

TrustGraph 2.9: A Config-Driven Workbench, Leaner Core, and Smarter Catalog Loading

#ai #opensource #aiops #rag
6
Comments 1
6 min read
LangChain vs LlamaIndex vs Chonkie: same 94-page PDF
aidevhub profile

LangChain vs LlamaIndex vs Chonkie: same 94-page PDF

#ai #llm #machinelearning #rag
Comments
7 min read
From a Test-Suite Trace to a Search Signal: the Bootstrap Pipeline Story
mansio profile

From a Test-Suite Trace to a Search Signal: the Bootstrap Pipeline Story

#search #rag #codearchitecture #testing
7
Comments 11
9 min read
Not All Multilingual Embedding Models Are Equal — Testing 5 of Them
rit_the_coder profile

Not All Multilingual Embedding Models Are Equal — Testing 5 of Them

#ai #machinelearning #rag #python
Comments
14 min read
My retrieval counted the same text three times
ashish_sinha_5241c7673d93 profile

My retrieval counted the same text three times

#rag #python #ai #database
Comments 22
4 min read
macOS Keychain Support for Electron Apps: A Game Changer for Secure A…
felipejac profile

macOS Keychain Support for Electron Apps: A Game Changer for Secure A…

#agents #api #rag
Comments
2 min read
From Demo to Production: The Guardrails That Make an AI Agent Safe to Ship
sunny_1024k profile

From Demo to Production: The Guardrails That Make an AI Agent Safe to Ship

#aiagents #llm #rag #microsoft
1
Comments 1
4 min read
What Retrieval Still Hasn't Decided
shinpr profile

What Retrieval Still Hasn't Decided

#ai #rag #llm #machinelearning
2
Comments 11
11 min read
The Negative Test That Passed for the Wrong Reason
kaziava profile

The Negative Test That Passed for the Wrong Reason

#debugging #llm #rag #testing
4
Comments 19
4 min read
6 Node.js Tenant Guardrails for Cheap Invoice RAG (Count Embeddings and LLM Spend)
finnianfox8297 profile

6 Node.js Tenant Guardrails for Cheap Invoice RAG (Count Embeddings and LLM Spend)

#node #rag #sre
Comments
8 min read
"I Was Too Embarrassed to Ask What RAG Means, So I Wrote This Instead"
thesnehamk profile

"I Was Too Embarrassed to Ask What RAG Means, So I Wrote This Instead"

#ai #beginners #llm #rag
Comments
5 min read
RAG - Async Pipelines, MCP
ramya_perumal profile

RAG - Async Pipelines, MCP

#ai #rag #nlp
1
Comments
3 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.