Inkline
Menu

RAG: advanced

Templates
RAG: advanced 16 items and 16 connections. Offline: ingestion Online: answering Quality question miss dense hits keyword hits top 5 chunks answer nightly User Answer in the chat Knowledge base Chunk + metadata Embed chunks Vector index Keyword index Input guard Semantic cache Hybrid retriever Cross-encoder rerank System prompt Chat model PII redaction LLM traces Groundedness eval
RAG: advanced — preview
Architecture

Production RAG: input guard, semantic cache, hybrid (vector + keyword) retrieval, cross-encoder reranking, a system prompt, PII redaction on the way out, and traces feeding groundedness evals.

What is inside

  • Hybrid retrieval + reranker
  • Guardrails in and out
  • Traces and evals
Use this template

Opens in the playground, no account needed. Sign up to save it.

Show the Inkline text
diagram architecture "RAG: advanced"
  direction down

  person user  "User"
  client reply "Answer in the chat"

  zone offline "Offline: ingestion" {
    corpus   docs  "Knowledge base"
    chunker  chunk "Chunk + metadata"
    embedder embed "Embed chunks"
  }
  vectordb vectors "Vector index"
  store    keyword "Keyword index"

  zone online "Online: answering" {
    guardrail inguard  "Input guard"
    cache     semcache "Semantic cache"
    retriever hybrid   "Hybrid retriever"
    reranker  rerank   "Cross-encoder rerank"
    prompt    system   "System prompt"
    llm       model    "Chat model"
    guardrail outguard "PII redaction"
  }

  zone quality "Quality" {
    tracer traces "LLM traces"
    eval   evals  "Groundedness eval"
  }

  docs     -> chunk -> embed
  embed    -> vectors
  chunk    -> keyword
  user     -> inguard  : question
  inguard  -> semcache
  semcache -> hybrid   : miss
  vectors  -> hybrid   : dense hits
  keyword  -> hybrid   : keyword hits
  hybrid   -> rerank
  rerank   -> model    : top 5 chunks
  system   -- model
  model    -> outguard
  outguard -> reply    : answer
  model    ~> traces
  traces   ~> evals    : nightly