RAG pipeline template

Retrieval-augmented generation end to end: ingest and embed documents offline, then retrieve, rerank and answer with citations.

Use this templateFree, opens in your browser. No sign-up.

RAG pipeline template
Ingestion (offline, on every document change)
Query (online, per question)
Evaluate
Sources: PDFs, wiki, tickets, Drive
Parse + clean (strip navigation, OCR scans)
Chunk: ~800 tokens, 15% overlap, keep headings
Embed each chunk (embedding model)
Vector store + metadata (source, date, access)
User question
Rewrite query using chat history
Hybrid search: vector + BM25, top 20
Rerank to top 5, filter by user access
LLM: answer only from context, cite sources
Answer + citations
Retrieval: recall@5 on 100 labeled questions
Answers: faithfulness + relevance (LLM-as-judge)
Track 'I don't know' rate, latency, cost per answer
Re-index when chunking or embedding model changes
RAG pipeline
similarity search
The RAG pipeline template as it opens in Kelvo: 11 boxes, 4 sticky notes and 10 links, in 3 sections.

What's on the board

Ingestion (offline, on every document change)
Sources: PDFs, wiki, tickets, Drive · Parse + clean (strip navigation, OCR scans) · Chunk: ~800 tokens, 15% overlap, keep headings · Embed each chunk (embedding model) · Vector store + metadata (source, date, access)
Evaluate
Retrieval: recall@5 on 100 labeled questions · Answers: faithfulness + relevance (LLM-as-judge) · Track 'I don't know' rate, latency, cost per answer · Re-index when chunking or embedding model changes
Query (online, per question)
LLM: answer only from context, cite sources · Rewrite query using chat history · Hybrid search: vector + BM25, top 20 · Rerank to top 5, filter by user access · User question · Answer + citations

How to use this template

  1. Click Use this template. It opens in the Kelvo app as a new board, saved in your browser.
  2. Double-click any box to change its text. Replace the examples with your own content.
  3. Sketch, then convert. Draw boxes and arrows with the pen, select the strokes and click Convert sketch: they become real boxes and links.
  4. Ask Kelvo right on the board (Pro). With Pro, type @kelvo and what you want in any box or text, for example “@kelvo add error handling”, and press Enter. The change is made there and the request disappears; ⌘Z undoes it.
  5. Keep the prompt next to the diagram. Add a code block from the Insert (+) menu for prompts, schemas or config, right beside the boxes they belong to.

Good for

  • ai
  • llm
  • rag
  • vector database
  • embeddings
  • Explaining an LLM feature's architecture to engineers and stakeholders
  • Deciding between prompting, retrieval and fine-tuning
  • Planning evaluations and risks before launch

Related templates

  • Prompting vs RAG vs fine-tuning template previewPrompting vs RAG vs fine-tuning

    A decision tree for choosing prompt engineering, RAG, fine-tuning or an agent, with a cost and speed comparison.

  • LLM agent loop template previewLLM agent loop

    How a tool-using agent plans, calls tools, observes results and updates memory until the goal is met, with guardrails.

  • Prompt design canvas template previewPrompt design canvas

    Design a production prompt piece by piece — role, context, task, constraints, examples, output format — plus test cases.

  • Model evaluation plan template previewModel evaluation plan

    Metrics, datasets, targets and owners for evaluating an LLM or ML model, plus the gate a release must pass.

  • AI guardrails & risk register template previewAI guardrails & risk register

    Input and output guardrails around an LLM call, with a risk register for hallucination, injection, leakage and bias.

  • Project status report template previewProject status report

    A weekly RAG status: schedule, budget and scope at a glance, workstream status, highlights, risks and decisions needed.

All ai and machine learning diagram templates · All templates

Use the RAG pipeline template