Skip to main content
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.
The advanced_settings object on the Extract API lets you tune fetch behavior (cached vs live), excerpt sizing, and full content extraction. Most callers don’t need it — the defaults return focused excerpts from the cached index, which works well for the majority of tool-calling and research use cases.

Fields

Fetch Policy

The fetch_policy parameter controls when to return indexed content (faster) or fetch fresh content from the source (fresher). Fetching fresh content may take up to a minute and is subject to rate limits to manage the load on source websites.

Excerpt and Full Content Settings

Both excerpt_settings and full_content are configured inside the advanced_settings object. Enable full content with custom excerpt sizes:
Enable full content with default excerpts:
Notes:
  • When full_content is enabled, you’ll receive both excerpts and full content in the response
  • Excerpts are always focused on relevance; full content always starts from the beginning
  • Without objective or search_queries, excerpts will be redundant with full content. The request still succeeds, but may return less relevant content and may include a warning.
  • max_chars_total (top-level) controls total excerpt size but does not affect full content