get_records_for_events
Retrieve raw event URLs and the event-structuring schema in one call, enabling a chatbot to extract and organize conference, workshop, meetup, and webinar details into structured documents.
Instructions
Fetch raw records + the Events prompt (event-structuring-v1.1.txt, events-v1.1 schema) so a chatbot can structure participatory events (conferences, workshops, meetups, webinars, summits, trainings).
Use this when you want to go from raw event URLs/titles to a structured event document in one AI round-trip. The chatbot should:
Read the event prompt_text (events-v1.1 schema and rules)
For each record, pin the target event (name, edition, location, domain) and hunt the official site's subpages (speakers, agenda, pricing, venue)
Extract fields following the events-v1.1 schema
Return ONE event JSON per record via submit_structured_events
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum raw records to fetch (default 10, max 25). | |
| source | No | Filter by scraper source field (e.g. "women_opportunities_aug_2026"). If None, all records in the collection. | |
| collection_name | No | Raw DB collection to read from. Defaults to "raw_urls" (the collection of URLs harvested from the women-opportunities text file); pass the pipeline collection name to reuse aggregation. | raw_urls |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||