Knowledge Base & RAG

What is Knowledge Base (RAG)?

RAG stands for Retrieval-Augmented Generation. In plain English: your AI agent reads your documents before answering any question, so it never makes things up. It only tells customers what's actually in your docs.

Without RAG, LLMs “hallucinate” — they confidently invent fake pricing, wrong policies, or made-up addresses. With RAG, your agent always grounds its answers in your real documents.

Video walkthrough — Setting up Knowledge Base

What Should You Upload?

Any information your agent needs to reference during a call. Common examples:

• Product catalogues — features, specs, SKUs, availability
• Pricing sheets — tiers, discounts, custom quotes
• FAQs — common customer questions and your answers
• Policies — refund, shipping, warranty, cancellation
• Company info — addresses, hours, team members
• Service menus — clinics, salons, restaurants

Supported Formats

Upload any of these directly from the Knowledge Base page:

• .pdf — text-based PDFs (scanned PDFs need OCR first)
• .docx — Microsoft Word documents
• .txt — plain text
• .md — markdown
• .csv — structured data (great for pricing tables)

Max file size: 10 MB per document. Total storage: 100 MB on Starter, 1 GB on Pro.

Uploading Documents

1. Go to the Knowledge Base page
2. Click + Upload Document
3. Drag and drop or select your file
4. Give it a descriptive name (“Apr 2026 Pricing” not “untitled”)
5. Add tags for organization (e.g., “pricing”, “policies”)
6. Click Upload. Vaaad AI automatically parses, chunks, and embeds the document in 10-30 seconds.

Linking Docs to Agents

Uploading isn't enough — you have to link docs to the agents that should use them. This lets different agents have different knowledge.

1. Open your agent and scroll to Linked Documents
2. Check the boxes next to relevant docs
3. Save. The agent will now retrieve from these docs during calls.

How Retrieval Works

During a call, here's what happens every time the user asks a question:

1. User says: “What's your 2BHK price?”
2. Vaaad translates and embeds the question (semantic search)
3. Searches your linked docs for the 2 most relevant chunks
4. Adds those chunks to the agent's context
5. Agent answers using only info from those chunks

If no relevant chunk is found (score below threshold), the agent says “I don't have that information, let me have our team follow up with you.” Never hallucinates.

Writing Documents That Work Well

Not all docs retrieve equally well. Tips for maximum accuracy:

• Use clear headings — “## Pricing” is better than “details”
• Keep related info together — don't split a product's specs across pages
• Write for Q&A — “Q: What's included in the Pro plan? A: ...” works great
• Use full sentences — avoid tables with no context (the table cells lose meaning)
• Avoid contradictions — if two docs say different prices, retrieval gets confused

Updating Documents

Prices changed? Edit the doc in-place from the Knowledge Base page. Vaaad re-embeds automatically — updates are live in under 30 seconds, across all linked agents. No need to re-link.

Limits

Next: Track campaign performance with Live Analytics →