cd /news/artificial-intelligence/rag-sota-i-tested-7-pipelines-and-bu… · home topics artificial-intelligence article
[ARTICLE · art-16906] src=dev.to ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

RAG SOTA: I Tested 7 Pipelines and Built SEQUOIA (Open Source)

A developer benchmarked seven RAG configurations against real-world banking documents, technical manuals, and internal wikis, finding that Twitter-hyped "graph RAG" approaches like LightRAG performed poorly. The engineer built and open-sourced SEQUOIA, a pipeline combining RAPTOR tree clustering with step-back prompting, which achieved 0.84 precision and 0.79 recall at 450ms latency—outperforming classical and hybrid RAG systems. SEQUOIA Pro, which adds multi-query retrieval and context compression, reached 0.87 precision and 0.82 recall at 680ms latency, though the basic version was identified as the production sweet spot.

read2 min views14 publishedMay 28, 2026

After 20+ hours of compute time on local hardware, I benchmarked 7 RAG configurations against real-world tasks. The results surprised me — and changed how I think about retrieval architecture.

RAG is everywhere in 2026. Everyone claims their pipeline is "SOTA," but most benchmarks use toy datasets. I wanted to see what actually works when you have:

Method Approach Score
No-RAG
Direct LLM generation Baseline
Classical RAG
Dense retrieval (BGE-small + FAISS) Poor
Hybrid RAG
BM25 + Dense + RRF fusion + cross-encoder reranker Moderate
LightRAG
Key-value extraction graph + dense hybrid Disappointing
PageIndex
Two-stage hierarchical retrieval Okay
GraphRAG
Entity graph + dense fallback Complex
Agentic RAG
Multi-step reasoning pipeline Slow, expensive
SEQUOIA
RAPTOR tree + step-back prompting Best
SEQUOIA Pro
Multi-query + rerank + compression SOTA

The Twitter-hyped "graph RAG revolution" didn't hold up on real data. LightRAG produced what I call "procedural warming" — it looks sophisticated but retrieval quality was mediocre. Academic benchmarks ≠ production reality.

Most RAG systems fail because they retrieve on the literal query. Step-back prompting (rewriting the query into a more general form before retrieval) improved recall by ~15% across the board. Combined with RAPTOR tree clustering, it creates a retrieval hierarchy that actually makes sense.

I used a local model for summarization and judging. Slightly weaker than GPT-4, yes, but the relative rankings between methods stayed consistent. This means you can prototype and benchmark without burning API credits.

User Query
    ↓
Step-back Prompting (generalize)
    ↓
RAPTOR Tree Retrieval (hierarchical clusters)
    ↓
Rerank + Context Compression
    ↓
Local LLM Generation

RAPTOR = Recursive Abstractive Processing for Tree-Organized Retrieval. Cluster leaf nodes, summarize upward, retrieve at multiple levels of abstraction.

Step-back = Before searching, ask: "What is the general principle behind this specific question?"

On my test set (banking documents, technical manuals, internal wikis):

Method Precision Recall Latency
Classical RAG 0.62 0.58 120ms
Hybrid RAG 0.71 0.65 340ms
LightRAG 0.59 0.61 890ms
SEQUOIA 0.84
0.79
450ms
SEQUOIA Pro 0.87
0.82
680ms

SEQUOIA Pro trades some latency for accuracy. SEQUOIA (basic) is the sweet spot for production.

Everything is open source:

🔗 github.com/Diyago/rag-benchmark

I'm extending SEQUOIA with:

I write about practical AI/ML from inside a bank — RAG systems, LLM deployment, team management, and what actually works vs. what's just hype.

Telegram channel (Russian, technical): AI.Insaf

Have you benchmarked RAG on real data? What surprised you? Drop a comment or reach out on Telegram.

Эта статья также опубликована в Telegram-канале AI.Insaf — про AI/ML из банковской практики, бенчмарки и управление DS-командами.

Подписывайтесь на канал для оперативных разборов и практических кейсов: https://t.me/ai_tablet

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @bge-small 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/rag-sota-i-tested-7-…] indexed:0 read:2min 2026-05-28 ·