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.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.Overview
This guide walks through building an interactive research application using interactions. By chaininginteraction_id values across requests, each follow-up question automatically has the full context of prior turns — so you can drill deeper into a topic without restating what was already researched.
Example: Multi-Turn Research Session
Consider a research session where each question builds on the last:- “Which country won the most Winter Olympics gold medals in 2026?” — initial broad question
- “How many medals did they win?” — a follow-up that only makes sense with context from step 1
- “How does that compare to the second place country?” — drills deeper into the same thread
Building a Research Chat Loop
Wrap the interaction pattern in a loop to create a fully interactive research agent. Each user question chains off the previous answer’s context.Next Steps
- Deep Research: Comprehensive single-turn research — includes an example of chatting with deep research results
- Interactions: Full reference for the
interaction_idandprevious_interaction_idfields - Enrichment: Structured data enrichment
- Streaming Events: Monitor long-running research tasks in real time