Knowledge Base & RAG

Knowledge Base & RAG

The Knowledge Base is the foundation of your AI bot. Upload your organization’s real documents — the bot learns from this data and answers questions using a smart RAG (Retrieval-Augmented Generation) pipeline.

Uploading Documents

1. Go to Knowledge Base in the left menu.

2. Click Upload Document and select a file (PDF, DOCX, or TXT).

3. Wait for the system to process and index the document. Status will show Ready when complete.

4. Test the bot in the Test Bot panel on the right to verify the bot can answer questions from the uploaded document.

Plan Limits

Each plan has different document upload limits. Maximum file size is 10 MB per document across all plans. Check your current plan limits at Billing & Subscription.

• Free: Up to 3 documents
• Starter: Up to 10 documents
• Growth: Up to 100 documents
• Plus: Up to 200 documents
• Pro: Up to 500 documents
• Scale: Up to 2,000 documents
• Enterprise: Up to 5,000 documents

Multi-File Upload

v1.10.0

You can now upload multiple documents at once. Instead of adding files one at a time, select several PDF, DOCX, or TXT files in a single bulk upload. Each file is processed and indexed independently, and you receive a per-file result so you can see at a glance which documents succeeded and which need attention.

Tip

Bulk upload is ideal when you are migrating an existing knowledge base — gather your documents into one upload and let the system index them in parallel.

Downloading Documents

v1.10.0

You can download any document you have uploaded back to your machine — useful for auditing, sharing the source file, or moving content between workspaces. Downloads are authenticated and scoped to your organization, so only members of your team can retrieve your files. The download path is validated against the document record, which prevents path-traversal and guarantees you always receive exactly the file associated with a given document.

Create from Text

In addition to file uploads, you can create knowledge base entries directly from text:

1. Click Create from Text
2. Enter a Title for easy reference
3. Paste or type the content in the text editor
4. Click Save — the system will index immediately

This is useful for FAQs, policies, or any content you want to write directly without a file.

RAG Pipeline

When a user asks a question, the system processes it through a 4-step RAG pipeline:

1. Hybrid Search — Searches across all documents using both keyword and semantic vector search simultaneously, ensuring no relevant content is missed.

2. Query Rewriting — Rewrites the user’s question to be more precise and search-friendly, improving retrieval accuracy even when questions are vague.

3. Re-ranking — Scores and re-ranks retrieved document chunks by relevance, so the most relevant content is passed to the AI model first.

4. Generate Answer — The AI model generates a natural-language answer grounded in the retrieved content, with source references.

RAG Features

Feature	Description
Hybrid Search	Combines keyword + semantic vector search for higher recall
Query Rewriting	Auto-rephrases user questions to improve retrieval accuracy
Re-ranking	Cross-encoder re-ranking to surface the most relevant chunks
Smart Model Routing	Routes queries to the appropriate model based on complexity and cost

Guardrail Modes

Control how strictly the bot stays within the knowledge base:

Mode	Behavior
Strict	Bot answers only from uploaded documents. Refuses to answer if no relevant content found.
Hybrid	Bot primarily uses the knowledge base but may supplement with general knowledge when needed.
Open	Bot uses the knowledge base as context but can answer freely from its training data.

Tip

For customer support and internal helpdesks, Strict mode is recommended to prevent the bot from hallucinating or going off-topic.

Test Bot

Use the Test Bot panel to verify your knowledge base before going live:

• Type questions as a user would
• Check that answers are grounded in your documents
• Use the Source view to see which document chunks the bot retrieved
• Adjust guardrail mode and re-test if needed

Changes to the knowledge base take effect immediately in the Test Bot — no redeployment required.

KB Auto-Suggest Drafts

v1.6.0

The auto-suggest feature analyzes unanswered questions from the Analytics dashboard and automatically generates draft knowledge base articles to fill content gaps:

1. The system identifies topics from unanswered questions that have no matching document
2. It generates a draft document with suggested content based on the question patterns
3. Drafts appear in the Analytics → Unanswered section with a “Suggested Draft” badge
4. Review, edit, and publish the draft to immediately improve bot coverage

Cross-Lingual Search

v1.6.10

The RAG pipeline supports cross-lingual retrieval — visitors can ask questions in one language and receive answers sourced from documents written in a different language.

This works through two mechanisms:

1. Query translation — The query rewrite service automatically translates non-English queries into English before searching, so English-language documents are discoverable regardless of the visitor’s language.
2. Wider search net — When the reranker is enabled, the system uses a lower initial similarity threshold to ensure cross-lingual and colloquial queries with lower cosine similarity but high semantic relevance are not filtered out before the reranker can evaluate them.

No configuration is needed — cross-lingual search is enabled by default when the RAG pipeline’s query rewriting and reranking features are active. If query translation is unavailable, the system falls back to searching with the original query. The improvement is especially noticeable for organizations with English-language knowledge bases serving multilingual visitors.

Tip

For best cross-lingual results, keep your knowledge base documents clear and well-structured. The query rewriter works best when document content uses standard terminology.

Import from URL

v1.15.0

Import content directly from any public URL. The system fetches the page, extracts readable text using smart content extraction, and indexes it as a knowledge base document.

1. Go to Knowledge Base and click Import from URL.

2. Paste the URL of the page you want to import.

3. The system fetches, extracts, and indexes the content automatically.

4. The document appears in your KB list with the source URL shown.

Note

URLs are validated against SSRF protection — only public URLs are allowed. Internal/private network addresses are blocked.

Auto-Refresh

v1.15.0

Enable auto-refresh on URL-imported documents to keep content up to date. The system periodically re-fetches the URL and updates the document if content has changed.

• Refresh interval is configurable per source
• Only changed content is re-processed (hash-based change detection)
• Failed fetches are logged without removing the existing document

Google Sheets Integration

v1.16.0

Connect your Google Sheets to automatically sync spreadsheet data into the knowledge base. Each row becomes a searchable document — ideal for product catalogs, FAQ lists, room directories, or any structured data.

1. Go to Settings → Integrations and click Connect Google Sheets.

2. Sign in with your Google account (read-only access to spreadsheets).

3. Paste the URL of the Google Sheet you want to sync.

4. Select which sheet tab and map columns: choose a Title column, Content columns, and an ID column for stable row identity.

5. Click Start Sync — the system imports all rows and indexes them as KB documents.

Tip

Choose a column with unique, stable values (like SKU or room code) as the ID column. This ensures edits update existing documents instead of creating duplicates.

Sync Behavior

Feature	Description
Auto-sync	Periodically checks for changes using hash-based detection
Row-level diff	Only re-processes changed or new rows
Row deletion	Missing rows are archived (not deleted), excluded from RAG
Rate limiting	250 requests/minute project-wide, 3 concurrent jobs per org

Plan Limits

Plan	Google Sheets Sources	Row Limit per Sheet
Free	0	—
Starter	3	500
Growth	10	2,000
Plus	25	5,000
Pro	50	10,000
Scale	100	50,000

RSS/Atom Feed Import

v1.16.0

Import blog articles, news feeds, or any RSS/Atom content source. The system parses the feed, fetches each article, and indexes the content as KB documents.

1. Go to Knowledge Base and click Import from RSS.

2. Enter the feed URL (RSS 2.0 or Atom 1.0).

3. Configure import options: max articles, content mode (full text or summary), auto-import toggle.

4. Click Import — the system fetches and indexes each article.

Feed Features

Feature	Description
Auto-import	Automatically imports new entries when they appear in the feed
HTTP caching	Uses ETag/Last-Modified to avoid re-downloading unchanged feeds
Content modes	Full text (fetches article URL) or Summary (uses feed description)
SSRF protection	Feed URLs pass through the same security guard as URL imports

Plan Limits

Plan	RSS Feed Sources
Free	0
Starter	3
Growth	10
Plus	20
Pro	30
Scale	50

Content Change Notifications

v1.16.0

Get notified when your imported content changes significantly. When a URL or Google Sheet source is refreshed and the content differs by more than 20%, the system sends an email notification to organization admins.

• Threshold: Configurable per organization (default: 20% content change)
• Rate limit: Maximum 1 notification per URL per 24 hours
• Recipients: All users with admin role in the organization
• Content: Email includes the source URL, change percentage, and a link to the KB dashboard

Note

Small changes (below the threshold) do not trigger notifications. This prevents noise from minor formatting updates.