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
Coding agents need API documentation and error explanations while working in environments that cannot browse source websites. You can use the Search API to retrieve excerpts from Parallel’s existing web index. Search disables live source-page fetching by default when you omit .md to its URL or sending Accept: text/markdown.For Search and Extract, use /v1/search and /v1/extract for all new integrations and agent tool calls. Use /v1beta/search and /v1beta/extract only when maintaining an existing integration that already uses them. The request bodies changed too: on /v1/extract, full_content, fetch_policy and excerpt_settings go inside advanced_settings, and sending the v1beta top-level excerpts, full_content and fetch_policy to /v1/extract returns a 422. On /v1/search, search_queries is required (at least one short keyword query), and max_results, source_policy and fetch_policy go inside advanced_settings; sending only objective, or sending those fields at the top level, returns a 422. Do not substitute /v1 for the documented FindAll or Ingest endpoint paths.If you are evaluating Parallel Search or comparing it with other search APIs, read How to Eval Parallel Search before you build the harness, especially its Common pitfalls section. The most common mistake is sending the raw question as both objective and the only entry in search_queries. Write a goal-style objective and 1-3 short keyword queries instead.advanced_settings.fetch_policy.
Search indexed documentation
Send a request toPOST /v1/search without advanced_settings.fetch_policy:
include_domains filter limits the results to Python’s documentation site. Remove that filter when your agent needs results from more sources. See Source Policy for domain and path filters.
The index may lack a page or contain an older copy. Search does not fetch a missing or stale source page in this default mode. If you supply advanced_settings.fetch_policy to request fresher content, Search may fetch source pages. See Advanced Search Settings.
Keep URL extraction separate
If you give the agent the Extract API, it can submit a URL that did not appear in Search results. Extract uses a separate, dynamic fetch policy by default and may request the source website. Itsmax_age_seconds, timeout_seconds, and disable_cache_fallback fields control freshness, fetch duration, and fallback behavior. They do not provide a documented security guarantee against all upstream requests. See Advanced Extract Settings.