Access Liner's web search, scholar search, AI research, and citation APIs from Convex actions with streaming response aggregation.
npm install liner-convexConvex component for Liner search, quick answers, AI Search, and Deep Research
Use the Liner Convex component to call webSearch() from your actions, which provides structured web results with country/language filtering and date ranges. The component handles API authentication and returns parsed results ready for your application.
The scholarSearch() method accesses Liner's academic database, returning results with citation counts, authors, and journal metadata. This enables building research tools and citation analysis features in your Convex app.
Use aiSearch() or deepResearch() methods to get AI-generated answers with proper citations and references. The component aggregates streaming responses into structured data with reasoning, sources, and search steps.
The Liner component automatically parses Server-Sent Events from streaming endpoints like Quick Answer and Deep Research, returning aggregated results with text, references, and metadata instead of raw stream data.
The Liner Convex component automatically parses Server-Sent Events from streaming endpoints and returns aggregated results containing text, reasoning, references, and metadata. You get structured data instead of managing stream parsing yourself.
The Liner Convex component provides web search, academic scholar search, quick answers, AI search, and deep research capabilities. Each method returns structured results with citations, and you can filter by country, language, and date ranges.
The Liner Convex component stores your API key in Convex environment variables through the component configuration. Set LINER_API_KEY in your Convex dashboard or CLI, and the component handles authentication without exposing credentials to client code.
AI Search provides quick grounded answers with sources, while Deep Research generates comprehensive citation-rich reports. The Liner Convex component offers both regular and Pro versions of each, with Deep Research being more suitable for long-form research tasks.