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.
Using Vector Databases to Improve Drupal Search
joshua_wainaina_e8c1ad2f0 profile

Using Vector Databases to Improve Drupal Search

#ai #database #rag #search
1
Comments
4 min read
KoutenDB v0.9.0: From a Locality Experiment to a Testable Database
puffball1567 profile

KoutenDB v0.9.0: From a Locality Experiment to a Testable Database

#database #opensource #nim #rag
Comments
5 min read
Why RAG Docs Chatbots Answer Wrong: Embeddings, Chunking, and Context Fixes
tony_chen_2026 profile

Why RAG Docs Chatbots Answer Wrong: Embeddings, Chunking, and Context Fixes

#rag #python #ai #machinelearning
Comments
6 min read
Building a podcast summarizer in 20 lines of Python
roberttomko profile

Building a podcast summarizer in 20 lines of Python

#python #llm #rag #webdev
Comments
3 min read
Tracing ORAG's Path from Document Ingestion to Hybrid Retrieval
opengrowthai_dev profile

Tracing ORAG's Path from Document Ingestion to Hybrid Retrieval

#architecture #backend #go #rag
Comments
3 min read
Evolution of Language Models - Every LLM Breakthrough Was Just a Bug Fix
marjia_029 profile

Evolution of Language Models - Every LLM Breakthrough Was Just a Bug Fix

#ai #machinelearning #llm #rag
1
Comments 1
8 min read
Why your company's search bar can't find the answer that's right there
jc_marin profile

Why your company's search bar can't find the answer that's right there

#ai #rag #python #machinelearning
Comments
4 min read
5 Practical RAG Challenges and How to Mitigate Them
synfinity-dynamics-pvt-ltd profile

5 Practical RAG Challenges and How to Mitigate Them

#rag #ai #llm #machinelearning
5
Comments
5 min read
RAG Retrieval Gotchas at Scale: Practical Insights and Solutions
the-hive-collective profile

RAG Retrieval Gotchas at Scale: Practical Insights and Solutions

#rag #retrieval #scalability #ai
1
Comments
4 min read
RAG Beyond the Demo: Pipeline, Citations, Evaluation, and When Not to Bother
xinyangwuethz profile

RAG Beyond the Demo: Pipeline, Citations, Evaluation, and When Not to Bother

#rag #llm #embeddings #evaluation
Comments 2
7 min read
I Was Losing Track of My Own Job Applications — So I Built a Tool to Fix It
pratiekshaa profile

I Was Losing Track of My Own Job Applications — So I Built a Tool to Fix It

#ai #fullstack #rag #python
Comments
3 min read
Silent Drift: Why Re-Embedding Only on Count Changes Rots Your Semantic Index
futhgar profile

Silent Drift: Why Re-Embedding Only on Count Changes Rots Your Semantic Index

#aiagents #rag #embeddings #vectorsearch
Comments 1
8 min read
Why Most PDF Parsing Breaks the Moment Your Document Format Changes
thorns profile

Why Most PDF Parsing Breaks the Moment Your Document Format Changes

#ai #python #rag #datascience
Comments 1
3 min read
RAG Retrieval Accuracy: 38%. After the Fix: 87%. The Model Was Never Touched.
fagundesv profile

RAG Retrieval Accuracy: 38%. After the Fix: 87%. The Model Was Never Touched.

#rag #python #ai #datascience
1
Comments 1
3 min read
Understanding RAG Chunking: Fixed-Size, Overlapping, Semantic, and Sentence-Based Chunking with Python
jaganjrai profile

Understanding RAG Chunking: Fixed-Size, Overlapping, Semantic, and Sentence-Based Chunking with Python

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