Re-run ingest with new chunking parameters
Re-run ingest on an uploaded knowledge-base document with different chunking — re-splits, re-embeds, and re-indexes the document so retrieval shifts to the new chunk boundaries. Optional body sets chunk_size and chunk_overlap (overlap must stay smaller than size, else 422); a document still being processed 409s, and a legacy-flow upload 409s with a pointer to re-upload. Audit-logged with before/after chunk counts. Owner/admin/developer role.
Authorizations
Dashboard JWT token from Clerk
Headers
Stripe-style idempotency token. Pass a stable, client-generated value (1-255 chars) to dedupe retries on transient timeouts. The same key+credential+path replays the original response for 24h on 2xx (5min on 4xx, 30s on 5xx). Returns 409 if a concurrent request with the same key is already in flight; replayed responses include the Idempotency-Replay: true response header.
1 - 255Sandbox opt-in for Clerk-session-authenticated requests. Set to true to route the call through the test-mode pipeline: no real provider delivery, no credits deducted, response meta.test_mode: true. Ignored for live API keys (dv_live_sk_*) — server-to-server clients must use a test-prefixed key (dv_test_sk_*) to exercise sandbox. Test-prefixed keys unconditionally enable sandbox regardless of this header.
true, false Response
{ agent_id, document_id, rechunk } — the reindex result (new chunk_count) — in the standard { data, meta } envelope.