RAG Pipeline Builder

Configure, preview, and export no-code RAG pipelines — Dify-style but code-first

Pipeline Stages

📄 Data Source
Files, URLs, or inline text to index
✂️ Chunking
Split documents into retrievable chunks
🔢 Embedding
Convert chunks to vectors
🔍 Retrieval
Dense, sparse, or hybrid search
🏆 Ranking
LLM or cross-encoder re-ranking
✨ Generation
Model, prompt, and self-correction config
🛡️ Guardrails
PII detection, cost cap, content filters
MeshFlow RAG supports HybridRetriever (BM25 + dense), LLMRanker, SelfCorrectingRAG with grade-threshold refinement, and full cache_control prompt caching.

Pipeline Preview

📄 Data Source
files: [], urls: [], inline: ""
✓
↓
✂️ Chunking
chunk_size: 500 · overlap: 50
✓
↓
🔢 Embedding
provider: built-in (char n-gram → numpy BoW → sentence-transformers)
✓
↓
🔍 Retrieval
strategy: dense · top_k: 5
!
↓
🏆 Ranking
ranker: none (skip)
!
↓
✨ Generation
model: claude-sonnet-4-6 · self-correct: off
!
↓
🛡️ Guardrails
pii_block: off · cost_cap: none
!

  


  
  

    
Configure: Data Source