For AI agents: a documentation index is available at https://docs.parallel.ai/llms.txt. The full text of all docs is at https://docs.parallel.ai/llms-full.txt. You may also fetch any page as Markdown by appending
.md to its URL or sending Accept: text/markdown.Overview
The/v1beta/findall/runs/{findall_id}/events endpoint provides real-time updates on candidates as they are discovered and evaluated using Server-Sent Events (SSE). Run, candidate, and schema events are delivered in chronological order with event_id, timestamp, type, and data. Error events instead contain type and error.
Resumability: Use the last_event_id query parameter to resume after disconnections. Each run, candidate, or schema event has an event_id. The /result endpoint returns the ID of the latest persisted event as last_event_id; heartbeat status events are generated in memory and are not used for that result cursor. If no ID is supplied, the stream starts from the beginning.
Duration: Streams remain open while the run is active or until an optional timeout is reached. timeout is measured in seconds and must be between 0 and 6,000, inclusive. A findall.status heartbeat is sent every 10 seconds to keep connections alive.
Accessing the Event Stream
Event Types
The SSE endpoint emits the following event types:For a complete guide to candidate object structure, states, and fields, see Candidates.
Event Payloads
findall.status — Heartbeat of FindAllRun object every 10 seconds, or when FindAll status changes.Related Topics
- Preview: Test queries with 5–10 evaluated candidates before running full searches
- Generators and Pricing: Understand generator options and pricing
- Enrichments: Extract additional structured data for matched candidates
- Extend Runs: Increase match limits without paying new fixed costs
- Webhooks: Configure HTTP callbacks for run completion and matches
- Run Lifecycle: Understand run statuses and how to cancel runs
- API Reference: Complete endpoint documentation