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.
When Good RAG Systems Fail (And How Production Teams Prevent It)
surajrkhonde profile

When Good RAG Systems Fail (And How Production Teams Prevent It)

#ai #rag #beginners #software
4
Comments 2
9 min read
Production RAG at Scale: Architecture Patterns for 1M+ Documents
courtgpt profile

Production RAG at Scale: Architecture Patterns for 1M+ Documents

#ai #rag #production #engineering
Comments
4 min read
Building a Document-RAG Agent on GCP's Agent Development Kit (ADK)
dalenguyen profile

Building a Document-RAG Agent on GCP's Agent Development Kit (ADK)

#ai #rag #agents #gcp
2
Comments
14 min read
Building RAG that doesn't hallucinate
anubhav_verma_c15696e7d7b profile

Building RAG that doesn't hallucinate

#ai #rag #genai #llama
2
Comments
4 min read
Where Does RAG Actually Cost You Money? I Decided to Stop Guessing.

Debunks the myth that embeddings drive up bills
surajrkhonde profile

Where Does RAG Actually Cost You Money? I Decided to Stop Guessing.

#rag #llm #backend #ai
10
Comments 4
4 min read
Why Organizations Forget Even When Nothing Is Deleted
valerykot profile

Why Organizations Forget Even When Nothing Is Deleted

#discuss #ai #llm #rag
5
Comments 22
2 min read
Your baseline scored 0.000. That's a broken harness, not a result.
jacksonxly profile

Your baseline scored 0.000. That's a broken harness, not a result.

#rag #llm #testing #ai
Comments 3
4 min read
I Was Optimizing Ranking While the Real Problem Was Selection
valerykot profile

I Was Optimizing Ranking While the Real Problem Was Selection

#ai #rag #machinelearning #software
4
Comments 4
2 min read
Qdrant vs Pinecone: Self-Hosted Vector Search for Production RAG
faisal_nadeem_752520c3e03 profile

Qdrant vs Pinecone: Self-Hosted Vector Search for Production RAG

#vectordatabase #rag #programming #ai
Comments 3
11 min read
RAG Chunking Strategy: How to Preserve Context Instead of Destroying It
faisal_nadeem_752520c3e03 profile

RAG Chunking Strategy: How to Preserve Context Instead of Destroying It

#ai #rag #machinelearning #programming
Comments
12 min read
How Japan’s Research Labs Are Building RAG Systems That Actually Work — And What Western Teams Keep Getting Wrong
xu_xu_b2179aa8fc958d531d1 profile

How Japan’s Research Labs Are Building RAG Systems That Actually Work — And What Western Teams Keep Getting Wrong

#ai #programming #knowledgegraph #rag
1
Comments
4 min read
Replacing Cross-Encoder Reranking with a Weighted Hybrid Score
felipearaujobs profile

Replacing Cross-Encoder Reranking with a Weighted Hybrid Score

#ai #nlp #performance #rag
Comments
5 min read
1st post
fareed_sheikh profile

1st post

#rag #website #ai #webdev
Comments 1
1 min read
Phase 4: Retrieval Quality & Grounded Answers

Why closest matches aren't always relevant
surajrkhonde profile

Phase 4: Retrieval Quality & Grounded Answers

#ai #beginners #programming #rag
6
Comments 10
12 min read
Why Most RAG Systems Fail in Production: The Hidden Architecture Problems Behind AI Search
damir-karimov profile

Why Most RAG Systems Fail in Production: The Hidden Architecture Problems Behind AI Search

#ai #rag #llm #vectordatabase
3
Comments 5
12 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.