---
name: bijection-jina
description: "Evaluate and integrate the Jina AI component with Bijection."
---

# Jina AI

Reader and search API integration

- Package: @bijectionhq/jina
- Category: Web & Search
- Status: Preview
- License: Apache-2.0
- Bijection source (repository access required): https://github.com/bijectionhq/jina/tree/5004a609664fddd7870de629d1b884d48af52fa0
- Upstream: https://github.com/adhishthite/convex-jina/tree/3c7d5806271f27a6f021873764ae8b5b88d0e61e
- Documentation: https://docs.bijection.com/components/using
- Directory: https://bijection.com/components/jina

## Get the source

Bijection repository access is required. Request access at https://bijection.com/contact.

```sh
git clone https://github.com/bijectionhq/jina.git
cd jina
git checkout 5004a609664fddd7870de629d1b884d48af52fa0
```

## Before using this component

Read the package README at the recorded revision for setup, dependencies, and API examples. Upstream documentation describes the original package and may differ from the Bijection adaptation. This is a source candidate for evaluation. Catalog inclusion does not establish npm availability or runtime qualification. Check compatibility with your SDK and deployment before adoption. External providers run their own compute.

## Integration workflow

1. Read the source README and package manifest at the recorded revision.
2. Confirm the required SDK, dependency availability, and runtime compatibility.
3. Follow the component's documented setup and configuration. Never invent an npm install command from a catalog package name.
4. Keep credentials in the project's existing secret store.
5. Follow the project's execution rules for verification and report what was actually checked.

## Original upstream skill

The following guidance describes convex-jina. Its installation commands and APIs refer to the upstream package. Evaluate compatibility with the Bijection source separately.


# convex-jina

## Instructions

Use convex-jina to convert any url to clean markdown and search the web with jina ai in convex, featuring reactive queries and durable caching. This Convex component integrates directly with your backend.

### Installation

```bash
npm install convex-jina
```

### Capabilities

- Convert web pages to clean markdown without HTML parsing complexity
- Cache API responses durably to reduce costs and improve performance
- Query web content reactively with automatic updates when data changes
- Integrate web scraping and search directly into Convex backend functions

## Examples

### how to scrape web pages in Convex application

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.

### add web search to Convex backend

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.

### cache external API responses in Convex

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.

## When NOT to use

- When a simpler built-in solution exists for your specific use case
- If you are not using Convex as your backend
- When the functionality provided by convex-jina is not needed

## Troubleshooting

**Does convex-jina work with any website URL?**

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.

**How does caching work with convex-jina?**

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.

**Can I use convex-jina for real-time web content monitoring?**

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.

**What Jina AI APIs does convex-jina support?**

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.

## Resources

- [npm package](https://www.npmjs.com/package/convex-jina)
- [GitHub repository](https://github.com/adhishthite/convex-jina)
- [Live demo](https://convex-jina-demo.vercel.app/)
- [Convex Components Directory](https://www.convex.dev/components/convex-jina)
- [Convex documentation](https://docs.convex.dev)