Search Endpoint
Performs semantic vector search across your project documentation and returns matching pages ranked by relevance score.
Queries are embedded into the same vector space used to index your docs, so the search understands intent — not just keywords. Ask a full natural-language question for best results.
Response shape: an array of results (title, section, slug, content snippet, URL, score), along with the original query, total count, and search duration. The snippet field is capped at 500 characters and is directly usable as LLM context.
Typical latency: 50-200ms for queries against projects under 10k pages. Latency scales sub-linearly with index size.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
querystringrequiredNatural language search query.
<= 500limitintegerMaximum number of results to return.
x >= 1, x <= 205Response
Search results
resultsarray<object>results.titlestringPage title.
results.sectionstringSection heading within the page (if applicable).
results.slugstringURL path to the page.
results.contentstringContent snippet (max 500 chars).
results.urlstring<uri>Full URL to the page.
results.scorenumber<float>Relevance score (cosine similarity, 0.0–1.0). Higher is better.
x >= 0, x <= 1querystringThe query that was searched.
totalintegerNumber of results returned.
durationMsintegerServer-side search execution time in milliseconds (excludes network round-trip).