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 an LLM response fails validation, feed the error back into the retry

When an LLM response fails validation, feed the error back into the retry

2
Comments 3
2 min read
GitHub Optimizes AI Agent Workflows, AGENTS.md for Consistent LLM Ops, Opus PR Reviewer

GitHub Optimizes AI Agent Workflows, AGENTS.md for Consistent LLM Ops, Opus PR Reviewer

Comments
3 min read
Why RAG Pipelines Fail on East African Documents — and the Document Intelligence Engine I Built to Fix It

Why RAG Pipelines Fail on East African Documents — and the Document Intelligence Engine I Built to Fix It

Comments 2
6 min read
Slack AI assistant for engineering: RAG, pgvector, and the parts that broke

Slack AI assistant for engineering: RAG, pgvector, and the parts that broke

Comments
6 min read
One Ruler to Measure Them All: How Language Affects LLM Quality

One Ruler to Measure Them All: How Language Affects LLM Quality

Comments
2 min read
Phase 1: Document Ingestion - The Hidden Complexity Before Embeddings

Phase 1: Document Ingestion - The Hidden Complexity Before Embeddings

2
Comments
20 min read
AI Conf 2026: Classic ML Is Dead, Everyone's Building Agents

AI Conf 2026: Classic ML Is Dead, Everyone's Building Agents

1
Comments
2 min read
One Ruler to Measure Them All: How Language Affects LLM Quality

One Ruler to Measure Them All: How Language Affects LLM Quality

1
Comments
2 min read
Rethinking Enterprise AI: Why GraphRAG is the Missing Link

Rethinking Enterprise AI: Why GraphRAG is the Missing Link

1
Comments
2 min read
Why Most RAG Pipelines Fail in Production

Why Most RAG Pipelines Fail in Production

Comments
8 min read
The Vector Database Index for RAG (2026)

The Vector Database Index for RAG (2026)

Comments
2 min read
I Gave an AI Full Access to My Startup and Asked It to Destroy Me

I Gave an AI Full Access to My Startup and Asked It to Destroy Me

Comments
10 min read
Pensieve — Memory Management for AI Agents That Actually Forget

Pensieve — Memory Management for AI Agents That Actually Forget

Comments
9 min read
RAG SOTA, Agent Harnessing, and Langfuse Observability for AI Frameworks

RAG SOTA, Agent Harnessing, and Langfuse Observability for AI Frameworks

Comments
3 min read
Stale RAG vs. expensive RAG: how to cache RAG context without serving outdated answers

Stale RAG vs. expensive RAG: how to cache RAG context without serving outdated answers

2
Comments
7 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.