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.
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
- Click Use this template. It opens in the Kelvo app as a new board, saved in your browser.
- Double-click any box to change its text. Replace the examples with your own content.
- Sketch, then convert. Draw boxes and arrows with the pen, select the strokes and click Convert sketch: they become real boxes and links.
- 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.
- 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
A decision tree for choosing prompt engineering, RAG, fine-tuning or an agent, with a cost and speed comparison.
LLM 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
Design a production prompt piece by piece — role, context, task, constraints, examples, output format — plus test cases.
Model 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
Input and output guardrails around an LLM call, with a risk register for hallucination, injection, leakage and bias.
Project 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