These docs are built from the langchain-parallel repo and have not been verified for accuracy by the LangChain team.
For issues, please open an issue in the langchain-parallel repo.
Refer to the docs for a high-level guide on how to use each module. These reference pages contain auto-generated API documentation for each module, focusing on the "what" rather than the "how" or "why" (i.e. no end-to-end tutorials or conceptual overviews).
Parallel Web chat model integration.
Settings for excerpt extraction.
Settings for full content extraction.
Fetch policy for cache vs live content.
Domain allow/deny lists and freshness floor for web research.
Webhook config for a Parallel monitor.
Manage scheduled web monitors via the Parallel Monitor API (alpha).
Input schema for ParallelWeb search tool.
Parallel Search tool with web research capabilities.
One BYOMCP server description for a Task Run.
Input schema for :class:ParallelTaskRunTool.
Run a single Parallel Task synchronously and return the structured result.
High-level Runnable for Parallel deep-research tasks.
Batch task runner backed by the Task Group API.
High-level Runnable for the structured-batch enrichment pattern.
Webhook config for a FindAll run.
One boolean condition the API uses to filter candidates.
One entry in the FindAll exclude_list.
Input schema for :class:ParallelFindAllTool.
Run a Parallel FindAll discovery and return the matched candidates.
LangChain retriever that returns Parallel Search results as Documents.
Input schema for Parallel Extract Tool.
Parallel Extract Tool.
Build a TaskSpecParam dict from pydantic classes / schemas / text.
Verify a Parallel webhook signature (Standard Webhooks scheme).
Extract citations, low-confidence fields, and interaction_id.
Retrieve the Parallel API key from argument or environment variables.
Returns a configured sync OpenAI client for the Chat API.
Returns a configured async OpenAI client for the Chat API.
Returns a configured sync Parallel SDK client.
Returns a configured async Parallel SDK client.
