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.
10 RAG Architecture Mistakes Fintechs Make in Their First Production Deployment
justsoftlab_x01 profile

10 RAG Architecture Mistakes Fintechs Make in Their First Production Deployment

#rag #fintech #machinelearning #postgres
2
Comments 2
17 min read
Postgres + pgvector vs Pinecone: A Production Benchmark to 50M Vector
justsoftlab_x01 profile

Postgres + pgvector vs Pinecone: A Production Benchmark to 50M Vector

#vectordatabase #postgres #rag #machinelearning
1
Comments
9 min read
Multimodal RAG with the Gemini API File Search Tool: A Developer Guide
pat_loeber profile

Multimodal RAG with the Gemini API File Search Tool: A Developer Guide

#api #gemini #rag #tutorial
91
Comments 6
6 min read
Beyond RAG: Why Knowledge Engineering Becomes the Real Moat in the Agent Era
_4f268336f6580845cdc475 profile

Beyond RAG: Why Knowledge Engineering Becomes the Real Moat in the Agent Era

#ai #machinelearning #rag #agents
6
Comments
7 min read
RAG Series (10): Hybrid Search — Retrieving More, Missing Less
wonderlab profile

RAG Series (10): Hybrid Search — Retrieving More, Missing Less

#rag #bm25 #langchain #ai
Comments
7 min read
Building a Secure RAG Pipeline on AWS: A Step-by-Step Implementation Guide
sathieshveera profile

Building a Secure RAG Pipeline on AWS: A Step-by-Step Implementation Guide

#aws #rag #security #tutorial
Comments
20 min read
Build Once, Sell Twice: caching LLM analysis with pgvector
bryanacosta profile

Build Once, Sell Twice: caching LLM analysis with pgvector

#ai #rag #postgres #performance
2
Comments
4 min read
AI Memory Is Kind of Broken. A Cambridge Researcher Proved It .
vektor_memory_43f51a32376 profile

AI Memory Is Kind of Broken. A Cambridge Researcher Proved It .

#ai #database #memory #rag
1
Comments
8 min read
RAG Chunk Boundary Bugs: Why Your Retriever Returns Half-Sentences
gabrielanhaia profile

RAG Chunk Boundary Bugs: Why Your Retriever Returns Half-Sentences

#rag #ai #llm #retrieval
Comments
9 min read
Reranker Fine-Tuning on Click Data: When Off-the-Shelf Stops Winning
gabrielanhaia profile

Reranker Fine-Tuning on Click Data: When Off-the-Shelf Stops Winning

#rag #ai #machinelearning #search
Comments
8 min read
Day 2 - RAG - What is Vector DB ?
indumathi__r profile

Day 2 - RAG - What is Vector DB ?

#ai #database #llm #rag
Comments
3 min read
Few-Shot Selection at Runtime: Why Static Examples Hurt Edge Cases
gabrielanhaia profile

Few-Shot Selection at Runtime: Why Static Examples Hurt Edge Cases

#ai #llm #promptengineering #rag
Comments
8 min read
Embedding Dimension Reduction: When 1536 256 Doesn't Hurt Recall
gabrielanhaia profile

Embedding Dimension Reduction: When 1536 256 Doesn't Hurt Recall

#rag #ai #embeddings #performance
Comments
8 min read
Vector Index Cold Start: Why Your First Query Takes 8 Seconds
gabrielanhaia profile

Vector Index Cold Start: Why Your First Query Takes 8 Seconds

#rag #ai #vectordatabase #database
Comments
9 min read
I Built a Moderation Agent That Refuses to Be Intelligent — Just Focused
alexandr_i_ffce3f9e072773 profile

I Built a Moderation Agent That Refuses to Be Intelligent — Just Focused

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