# AI use cases for Reader (jina-ai/reader)

Repo: [jina-ai/reader](https://github.com/jina-ai/reader) | Use cases: 3 | Page: https://dedupedai.com/use-cases/jina-ai-reader/

Reader converts any URL into LLM-friendly markdown by prepending https://r.jina.ai/, and searches the web with https://s.jina.ai/, fetching the top results as markdown. It handles PDFs, Office documents and JavaScript heavy pages, has request headers for output format, waiting and token limits, and this repo is the open source branch you can self-host with Docker.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Turn any URL into LLM-ready markdown: https://dedupedai.com/use-cases/jina-ai-reader/turn-any-url-into-llm-ready-markdown-with-jina-reader/
- Search the web and read the top results: https://dedupedai.com/use-cases/jina-ai-reader/search-the-web-for-grounded-answers-with-jina-reader/
- Self-host Reader with Docker: https://dedupedai.com/use-cases/jina-ai-reader/self-host-jina-reader-with-docker/

## How to turn any URL into LLM-ready markdown with Reader

Repo: [jina-ai/reader](https://github.com/jina-ai/reader) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README

Prefix a URL with r.jina.ai to get clean markdown, with front matter or JSON when your pipeline needs structure.

**Who it is for:** A developer feeding articles, docs or PDFs to a model.

**The problem:** Raw HTML wastes tokens and confuses models.

**The outcome:** Markdown with a title and source header, YAML front matter, or JSON.

### Steps

1. Prepend https://r.jina.ai/ to the page URL and fetch it with curl
2. For YAML front matter run `curl -H 'X-Respond-With: frontmatter' 'https://r.jina.ai/https://example.com'`
3. For JSON output run `curl -H "Accept: application/json" https://r.jina.ai/https://en.m.wikipedia.org/wiki/Main_Page`
4. Add x-max-tokens to cap the size or x-retain-images none to drop images

### Prompt to paste into your agent

```text
Using jina-ai/reader, fetch each URL in <my list> through r.jina.ai with the X-Respond-With frontmatter header and save the markdown files for my RAG index.
```

### Caveat

Anonymous requests are the most rate limited; an API key raises the quota.

Risk, privacy: The hosted service fetches the URLs you send; self-host for internal or private pages.

Risk, legal: Respect each site's terms when converting its content.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/jina-ai-reader/turn-any-url-into-llm-ready-markdown-with-jina-reader/

## How to search the web and read the top results with Reader

Repo: [jina-ai/reader](https://github.com/jina-ai/reader) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README

Call s.jina.ai with a query to get the top 5 results already fetched and converted, optionally limited to certain sites.

**Who it is for:** Someone building a research agent that needs current information.

**The problem:** Search APIs return only titles and snippets, so the agent still has to fetch each page.

**The outcome:** Full text of the top results for a query, ready to put in a prompt.

### Steps

1. URL encode your query and prepend https://s.jina.ai/
2. Restrict to sites with the site parameter, for example `curl 'https://s.jina.ai/When%20was%20Jina%20AI%20founded%3F?site=jina.ai&site=github.com'`
3. Pass the returned markdown to your model as context
4. Keep the source URLs from each result so answers can be checked

### Prompt to paste into your agent

```text
With jina-ai/reader, query s.jina.ai for <my research question> limited to <two sites>, and summarize the results with their source URLs.
```

### Caveat

The README says search fetches the top 5 results, so expect slower responses than a snippet API.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/jina-ai-reader/search-the-web-for-grounded-answers-with-jina-reader/

## How to self-host Reader with Docker with Reader

Repo: [jina-ai/reader](https://github.com/jina-ai/reader) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Run the open source image locally so internal or high volume conversions do not go through the hosted service.

**Who it is for:** A team with private pages or strict data rules.

**The problem:** Sending internal URLs to a third party service may not be allowed.

**The outcome:** A local Reader at localhost:3000 that converts URLs to markdown.

### Steps

1. Pull the image with `docker pull ghcr.io/jina-ai/reader:oss`
2. Start it with `docker run --rm -p 3000:8081 ghcr.io/jina-ai/reader:oss`
3. Test it with `curl http://localhost:3000/https://example.com`
4. Add an S3 compatible bucket through the GCP_STORAGE environment variables if you want caching

### Prompt to paste into your agent

```text
Using jina-ai/reader, run the oss Docker image on port 3000, convert <an internal URL> to markdown with curl, and tell me how to stop the container.
```

### Caveat

The open source branch has no MongoDB storage layer and runs stateless unless you configure a bucket.

Risk, security: The local container has no rate limiting by default; do not expose it to the internet.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/jina-ai-reader/self-host-jina-reader-with-docker/
