Fix developer portal search
Hybrid semantic + keyword search that actually finds the page.
Your docs search is keyword-only: a developer searching "rotate credentials" gets nothing because the page says "regenerate API keys." They give up, file a ticket, or worse, conclude the feature does not exist.
BeforeQuery combines pgvector semantic search with full-text ranking (RRF fusion), so intent matches even when words do not. Ship it as a search bar, sidebar, or Cmd+K modal through the Website Widget, or call the Search API to power your own UI.
How it works
- 1Index your docs site — content is chunked, embedded, and full-text indexed.
- 2Queries run semantic vector search and full-text ranking in parallel, fused with RRF.
- 3Ship the UI as a widget search bar, sidebar, or Cmd+K modal — or call the Search API for your own frontend.
- 4Results carry relevance scores and link to the exact page and section.
What you get
Features that make it work
Frequently asked questions
Why is hybrid search better than keyword search?
Semantic vector search matches meaning ('rotate credentials' finds 'regenerate API keys'), while full-text ranking rewards exact terms like error codes and flag names. Reciprocal rank fusion combines both, so you get the strengths of each.
Can I keep my own search UI?
Yes. The public Search API returns top chunks with relevance scores for any query, so you can power your existing search box, autocomplete, or docs UI with hybrid retrieval underneath.
Is this search-only or does it answer questions too?
Both. The same index powers hybrid search and full RAG chat — you can offer a search bar for lookups and an 'Ask AI' mode for synthesized, cited answers, from one integration.
How long does setup take?
Most teams are live the same day. You connect a source — a docs URL, GitHub repo, Notion workspace, or a file upload — and BeforeQuery crawls, normalizes, chunks, and embeds the content automatically. The website widget is a single script tag, and the Slack/Discord bots install in a few clicks. There is no model to fine-tune and no infrastructure to run.
Are answers backed by citations?
Yes. Every answer includes a structured citations list with the URL, title, and excerpt of each source used, and the answer text cites sources inline. Users can click through to verify any claim against the original document — which is what makes the answers trustworthy enough for support, sales, and internal use.
Is my content used to train AI models?
No. Your indexed content, embeddings, and conversations are isolated to your workspace and are only used to answer your own questions. Content is never shared across customers, and data is encrypted at rest and in transit. Enterprise plans add OIDC/SAML SSO, audit logs, and data-residency options.
Which knowledge sources can I connect?
18+ source types: websites, GitHub, GitLab, Notion, Confluence, Google Drive, SharePoint, Shopify, Zendesk, Jira, Linear, Salesforce, Slack, Discourse, Stack Overflow, YouTube, OpenAPI specs, and direct file uploads (PDF, Markdown, TXT, HTML). Sources sync on a schedule, and GitHub/GitLab can re-index automatically via webhooks on every push.
What happens when the AI is not confident in an answer?
Answers are confidence-scored. When retrieval confidence falls below your threshold, BeforeQuery returns a transparent, configurable fallback — typically pointing users to your support channel — instead of guessing. Those unanswered questions are logged in knowledge gap analytics so you can close the gap in your docs.
Related use cases
Unblock developers integrating your API
Answer auth, webhook, and SDK questions with code-aware AI.
Put your docs inside the IDE via MCP
Cursor, Claude, and other MCP clients answer from your docs.
Q&A over your OpenAPI reference
Ask 'which endpoint updates a subscription?' and get the answer.
Ready to fix developer portal search?
Connect your knowledge sources and see cited AI answers in minutes — free, no credit card required.
Get Started Free