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.
I built a private Copilot alternative that never lets your data leave your Microsoft 365 tenant
kaspars-sharepoint profile

I built a private Copilot alternative that never lets your data leave your Microsoft 365 tenant

#microsoft365 #ai #azure #rag
3
Comments
2 min read
Your Context Window Is Not a Knowledge Base
balrajola profile

Your Context Window Is Not a Knowledge Base

#ai #architecture #llm #rag
3
Comments 3
4 min read
Hybrid Search in RAG: Why Neither Keyword Search Nor Semantic Search Alone Is Good Enough
nikhil_ramank_152ca48266 profile

Hybrid Search in RAG: Why Neither Keyword Search Nor Semantic Search Alone Is Good Enough

#rag #bm25 #hybridsearch #semantic
Comments
13 min read
Building a RAG Document Q&A System with Hybrid Retrieval (No Embeddings API Needed)
hajirufai profile

Building a RAG Document Q&A System with Hybrid Retrieval (No Embeddings API Needed)

#ai #python #machinelearning #rag
Comments
6 min read
How to Evaluate Your RAG Pipeline
benchwright profile

How to Evaluate Your RAG Pipeline

#ai #rag #llm #machinelearning
Comments
7 min read
RAG SOTA: I Tested 7 Pipelines and Built SEQUOIA (Open Source)
__2ddbae6bb7d profile

RAG SOTA: I Tested 7 Pipelines and Built SEQUOIA (Open Source)

#rag #llm #ai #career
Comments 1
3 min read
RAG vs Fine-Tuning
webkmsyed profile

RAG vs Fine-Tuning

#ai #rag #machinelearning #llm
Comments
7 min read
Open Source LLM Spring 2026: What Changed in 2 Months
__2ddbae6bb7d profile

Open Source LLM Spring 2026: What Changed in 2 Months

#ai #machinelearning #rag #llm
Comments
2 min read
I Got Tired of Debugging Haystack RAG Pipelines Blind, So I Built a Diagnostics Engine
rautaditya2606 profile

I Got Tired of Debugging Haystack RAG Pipelines Blind, So I Built a Diagnostics Engine

#rag #python #opensource #genai
1
Comments
3 min read
How to Enforce Role-Based Data Access in AI Applications with Oracle Deep Data Security
mark_nelson_oracle profile

How to Enforce Role-Based Data Access in AI Applications with Oracle Deep Data Security

#ai #database #rag #security
Comments
34 min read
Your RAG Agent Is Retrieving the Wrong Chunk: 5 Failure Modes We Fix in Production
rishabh_jain_7087a66dbf50 profile

Your RAG Agent Is Retrieving the Wrong Chunk: 5 Failure Modes We Fix in Production

#ai #rag #machinelearning #programming
Comments
4 min read
WearEdge Pro: An OPEA Manufacturing Five-Agent Suite for Frontline Operators
ryan_hsu_wearedge profile

WearEdge Pro: An OPEA Manufacturing Five-Agent Suite for Frontline Operators

#opea #manufacturing #rag #edgeai
Comments
2 min read
SerpBase + LangChain: a 30-line DocumentLoader that calls Google
dodou88 profile

SerpBase + LangChain: a 30-line DocumentLoader that calls Google

#ai #python #rag #tutorial
2
Comments
3 min read
What Happens Inside an LLM During Inference: Tokens, KV Cache, and GPU Execution Explained
murali8k profile

What Happens Inside an LLM During Inference: Tokens, KV Cache, and GPU Execution Explained

#ai #python #machinelearning #rag
Comments
12 min read
Long-Context Models Killed RAG. Except for the 6 Cases Where They Made It Worse.
gabrielanhaia profile

Long-Context Models Killed RAG. Except for the 6 Cases Where They Made It Worse.

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