HYBRID SEARCH

Retrieval that understands intent and respects keywords

BeforeQuery combines semantic vector search with full-text ranking and fuses the results — so "rotate credentials" finds the page titled "regenerate API keys," and an exact error code still matches exactly.

Start Free Search API

Capabilities

How retrieval works

The pipeline behind every answer, search box, and bot

Meaning, not keywords

Semantic Search

Best-in-class semantic index over every passage
Matches paraphrases, synonyms, and vague phrasing
Cross-language matching for multilingual teams
Heading-aware chunking preserves context
Query rewrite catches misspellings and jargon

Precision when it counts

Keyword Search

Exact matches for error codes and identifiers
Product names and API terms rank correctly
No fuzziness on literal queries
Runs in the same store as your semantic index
Fast enough for autocomplete surfaces

Best of both, scoped right

Fusion & Scoping

Reciprocal rank fusion merges both result sets
Source-group filters scope retrieval by product or version
Document visibility rules applied at query time
Top-k control per request
Exposed via Search API, widget, bots, and MCP

One pipeline everywhere

The search behind everything

The same hybrid retrieval powers grounded answers, the widget's search mode, the public Search API, MCP's search_docs, and the Ask portal. Improve your content once and every surface gets better — there is no separate search product to tune.

Grounding on every answer, with the source paragraph shown
Standalone search results with relevance scores
Scoped retrieval via source groups (product, version, region)
Restricted documents included only for authorized members
Search analytics feed the knowledge-gap report

POST /api/v1/public/knowledge-bases/:knowledgeBaseId/search

{
"query": "rotate credentials",
"top_k": 5
}

// → chunks ranked by fused score
{
"results": [
  {
    "title": "Regenerate API keys",
    "url": "https://docs.example.com/api-keys",
    "score": 0.91,
    "excerpt": "To regenerate a key, open Settings..."
  }
]
}

What teams say

Deployed in production.

“Deployed on our docs site in an afternoon. Every answer shows the source, and the abstention gate means we've never had a customer complain about a made-up answer.”

Priya Nair

Head of Customer Support · Supabase

“The knowledge base connected to our Slack, Confluence, and helpdesk in one setup. On-call teams get the same grounded answer whether they ask in chat, in the widget, or from Cursor.”

Tom Richter

IT Operations Manager · Grafana Labs

“The gap analytics turned into a real docs backlog. Deflection went up because we finally knew which pages were missing — the AI told us.”

Ana Castillo

VP of Customer Experience · Clerk

Frequently Asked Questions

Common questions about Hybrid Search

Vector search excels at meaning but blurs exact identifiers; keyword search nails identifiers but misses paraphrases. Fusing both with reciprocal rank fusion means "pump won't prime" and "ERR_4012" both retrieve the right page.

Pages are normalized from HTML to markdown, then chunked heading-aware so each chunk carries coherent context, then indexed into both a semantic index and a keyword index in the same store. Fusion picks the best chunks from either.

Yes. Source groups let you scope retrieval by product line, version, or region, and client keys can enforce allowed groups — narrowing what an integration can retrieve, never widening it.

Yes. Documents marked restricted are only retrievable by authorized workspace members; public-facing surfaces retrieve only from public documents.

Yes. The public Search API returns ranked passages with scores and URLs — teams use it for docs search bars, related-articles surfaces, and custom UIs, independent of the Assistant chat.

Search that finds what users mean

Index a source and try hybrid search on your own content in minutes.

Get Started Free