Convert any URL to clean markdown and search the web with Jina AI in Convex, featuring reactive queries and durable caching.
npm install convex-jinaRead any URL as clean markdown and search the web - with durable caching and reactive queries, powered by Jina AI.
Use convex-jina to read any URL and convert it to clean markdown within your Convex functions. The component handles the HTTP requests to Jina AI Reader API and provides durable caching so repeated requests don't hit rate limits or incur additional costs.
The convex-jina component wraps Jina AI Search API to perform web searches directly from your Convex mutations and queries. Results are cached and can be accessed reactively, enabling real-time search features in your application.
convex-jina automatically caches all Jina AI API responses in your Convex database. This prevents duplicate API calls for the same URL or search query, reducing costs and improving response times for your users.
convex-jina uses Jina AI Reader API which can process most publicly accessible websites and convert them to clean markdown. However, some sites with heavy JavaScript rendering or access restrictions may not work perfectly. The component handles errors gracefully and provides fallback mechanisms.
convex-jina stores all API responses in your Convex database with configurable TTL. When you request the same URL or search query, it returns cached results instead of making new API calls. This reduces costs and improves performance while keeping data fresh through automatic expiration.
Yes, convex-jina supports reactive queries through Convex's subscription system. You can set up queries that automatically update your frontend when cached web content changes or when new search results are available, enabling real-time monitoring dashboards.
convex-jina wraps both Jina AI Reader API for converting URLs to markdown and Jina AI Search API for web search functionality. Both APIs are integrated with Convex's reactive system and include built-in caching and error handling.