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

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Cheap RAG in Go with Gemini File Search: no vector DB, two calls, one hosted store

Cheap RAG in Go with Gemini File Search: no vector DB, two calls, one hosted store

34
Comments 4
14 min read
ChaosCypher v0.4.3: When a Clean Restart Lost More Work Than a Crash

ChaosCypher v0.4.3: When a Clean Restart Lost More Work Than a Crash

Comments
5 min read
Your RAG Finds the Documents. But Which Ones Should Reach the LLM?

Your RAG Finds the Documents. But Which Ones Should Reach the LLM?

10
Comments
3 min read
Your AI cited a real file. It still lied to you.

Your AI cited a real file. It still lied to you.

Comments
6 min read
Retrieval overlap went up 13 points by promoting sentences to paragraphs

Retrieval overlap went up 13 points by promoting sentences to paragraphs

1
Comments 2
4 min read
Build a Multi-Agent RAG Legal Assistant with LangGraph, FastAPI, and Streamlit (Beginner Guide)

Build a Multi-Agent RAG Legal Assistant with LangGraph, FastAPI, and Streamlit (Beginner Guide)

Comments
8 min read
Jev in Depth: Can It Reshape Agent Search?

Jev in Depth: Can It Reshape Agent Search?

Comments
7 min read
RAG ranking is not the same as judging with Jev

RAG ranking is not the same as judging with Jev

1
Comments 3
9 min read
Building a Simple RAG System with Python, ChromaDB and Gemini

Building a Simple RAG System with Python, ChromaDB and Gemini

Comments
2 min read
"I Was Too Embarrassed to Ask What RAG Means, So I Wrote This Instead"

"I Was Too Embarrassed to Ask What RAG Means, So I Wrote This Instead"

Comments
5 min read
My AI agent failed obvious tasks, and 49% fewer retrieval misses changed how I debugged it

My AI agent failed obvious tasks, and 49% fewer retrieval misses changed how I debugged it

Comments
6 min read
Bringing scattered sources into a single search — the unified knowledge workspace UseSources

Bringing scattered sources into a single search — the unified knowledge workspace UseSources

Comments
12 min read
Retrieval Latency Budgets in RAG Pipelines: Vector Search, Reranking, and the Timeout Cascade Problem

Retrieval Latency Budgets in RAG Pipelines: Vector Search, Reranking, and the Timeout Cascade Problem

Comments
6 min read
Inyecté memoria 1.112 veces y no sé si sirvió para algo

Inyecté memoria 1.112 veces y no sé si sirvió para algo

Comments
4 min read
Base, Chat and Reasoning Models: How Are They Different?

Base, Chat and Reasoning Models: How Are They Different?

Comments 1
3 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.