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.
Retrieval-Augmented Self-Recall — What the Comments Taught Me (RE-call v0.3)
gde03 profile

Retrieval-Augmented Self-Recall — What the Comments Taught Me (RE-call v0.3)

#ai #rag #opensource #programming
1
Comments
6 min read
Retrieval-Augmented Self-Recall — Part 5: The Gap Threshold That Didn't Transfer
gde03 profile

Retrieval-Augmented Self-Recall — Part 5: The Gap Threshold That Didn't Transfer

#ai #rag #machinelearning #programming
1
Comments
4 min read
Retrieval-Augmented Self-Recall — Part 3: Teaching RAG to Say \"I Don't Know\
gde03 profile

Retrieval-Augmented Self-Recall — Part 3: Teaching RAG to Say \"I Don't Know\

#ai #rag #llm #programming
1
Comments
5 min read
Retrieval-Augmented Self-Recall — Part 4: Benchmarking Retrieval *and* Honesty
gde03 profile

Retrieval-Augmented Self-Recall — Part 4: Benchmarking Retrieval *and* Honesty

#ai #rag #testing #programming
1
Comments
4 min read
Retrieval-Augmented Self-Recall — Part 6: The Fine-Tune That Did Nothing, and Shipping It as an MCP Server
gde03 profile

Retrieval-Augmented Self-Recall — Part 6: The Fine-Tune That Did Nothing, and Shipping It as an MCP Server

#ai #rag #mcp #machinelearning
1
Comments
4 min read
Your RAG System Is Lying To You About That Table
saksheessawant profile

Your RAG System Is Lying To You About That Table

#discuss #ai #rag #llm
13
Comments 2
4 min read
A Chinese 8B model beat the Western 8B models at Japanese RAG. I still wouldn't put it in the default deployment — and that distinction is the point.
elvisyao007 profile

A Chinese 8B model beat the Western 8B models at Japanese RAG. I still wouldn't put it in the default deployment — and that distinction is the point.

#llm #rag #machinelearning #japan
Comments
4 min read
RAG should never be your default
chou_500 profile
Chou

RAG should never be your default

#rag #llm #ai
Comments
3 min read
Building a Grounded RAG Assistant: Why Citation Enforcement Matters More Than Retrieval
naeem_rashidi_cd35cf30315 profile

Building a Grounded RAG Assistant: Why Citation Enforcement Matters More Than Retrieval

#ai #rag #llm #webdev
Comments 2
1 min read
KoutenDB: Data Locality as a First-Stage Retrieval Index
puffball1567 profile

KoutenDB: Data Locality as a First-Stage Retrieval Index

#database #search #rag #llm
Comments
6 min read
The Source-of-Truth Problem Every Enterprise AI Team Faces
karan2598 profile

The Source-of-Truth Problem Every Enterprise AI Team Faces

#ai #llm #rag #brainpackai
1
Comments
3 min read
RAG is for finding. Full context is for deciding.
evgenii-slepinin profile

RAG is for finding. Full context is for deciding.

#ai #rag #python #machinelearning
4
Comments
4 min read
Why my first RAG layer starts in Postgres, not in a standalone vector database
rkrisa profile

Why my first RAG layer starts in Postgres, not in a standalone vector database

#ai #rag #postgres #architecture
Comments
3 min read
Beyond Chatbots: Wrapping My RAG Agent in an MCP Server
sri_d_6dfd4d31319a6389eaa profile

Beyond Chatbots: Wrapping My RAG Agent in an MCP Server

#agents #ai #mcp #rag
1
Comments 6
2 min read
Moonshot AI's Kimi K3 Is Here: A 2.8 Trillion Parameter Open MoE Model That Pushes Long-Context AI Forward
sraurora profile

Moonshot AI's Kimi K3 Is Here: A 2.8 Trillion Parameter Open MoE Model That Pushes Long-Context AI Forward

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