Jina AI
App · AI Search & Memory · 4 actions
Read web pages as clean markdown, search the web, rerank documents, and classify text with Jina AI's Search Foundation APIs.
Actions
| Action | What it does |
|---|---|
| Classify text | Sort each piece of text into one of your own labels using Jina's zero-shot classifier: no training needed. |
| Read a URL | Fetch a web page through the Jina Reader and return it as clean, LLM-ready markdown: ideal for feeding a page into a later AI step. |
| Rerank documents | Reorder a list of documents by how relevant each one is to a query: useful for picking the best matches out of search or database results. |
| Search the web | Search the web through Jina and get back LLM-ready results. |
Classify text
Sort each piece of text into one of your own labels using Jina's zero-shot classifier: no training needed. Great for tagging, routing, or sentiment.
Inputs
- Texts
inputslistRequired - The list of text snippets to classify.
- Labels
labelslistRequired - The list of possible labels, for example 'Positive', 'Neutral', 'Negative'.
Outputs
resultslist- One prediction per input text, in order
tokensnumber- Tokens Jina counted for this request
Example output
{
"results": [
{
"index": 0,
"prediction": "Positive",
"score": 0.91,
"text": "I love this product, it works great!"
},
{
"index": 1,
"prediction": "Negative",
"score": 0.87,
"text": "The delivery was late and the box was damaged."
}
],
"tokens": 19
}Read a URL
Fetch a web page through the Jina Reader and return it as clean, LLM-ready markdown: ideal for feeding a page into a later AI step.
Inputs
- URL
urltextRequired - The web page to read, for example 'https://jina.ai'.
- Include links
with_linkstrue/false - Optional. Also return a list of the links found on the page.Default:
false. - Include images
with_imagestrue/false - Optional. Also return a list of the images found on the page.Default:
false. - Bypass cache
no_cachetrue/false - Optional. Fetch a fresh copy instead of Jina's cached version.Default:
false.
Outputs
contenttext- The page content as clean markdown
descriptiontext- The page's meta description, if any
imageslist- Images on the page. Empty unless 'Include images' is on.
linkslist- Links on the page. Empty unless 'Include links' is on.
titletext- The page's title
tokensnumber- Tokens Jina counted for this page
urltext- The URL that was read
Example output
{
"content": "Jina AI - Your Search Foundation, Supercharged.\n===============\nBest-in-class embeddings and rerankers...",
"description": "Best-in-class embeddings, rerankers, LLM-reader, web scraper, classifiers.",
"images": [
{
"text": "Jina logo",
"url": "https://jina.ai/Jina%20-%20Dark.svg"
}
],
"links": [
{
"text": "Contact sales",
"url": "https://jina.ai/contact-sales"
}
],
"title": "Jina AI - Your Search Foundation, Supercharged.",
"tokens": 1234,
"url": "https://jina.ai/"
}Rerank documents
Reorder a list of documents by how relevant each one is to a query: useful for picking the best matches out of search or database results.
Inputs
- Query
querytextRequired - The query to rank the documents against.
- Documents
documentslistRequired - The list of text documents to reorder by relevance.
- Top N
top_nnumber - Optional. Return only the top N most relevant documents.At least 1.
Outputs
resultslist- Documents ordered from most to least relevant
tokensnumber- Tokens Jina counted for this request
top_documenttext- The single most relevant document, for convenience
Example output
{
"results": [
{
"document": "Organic skincare for sensitive skin with aloe vera",
"index": 0,
"relevance_score": 0.9
},
{
"document": "Fragrance-free moisturizer for dry skin",
"index": 2,
"relevance_score": 0.8
}
],
"tokens": 15,
"top_document": "Organic skincare for sensitive skin with aloe vera"
}Search the web
Search the web through Jina and get back LLM-ready results. Returns titles, URLs, and snippets by default, or full page content when asked.
Inputs
- Search query
querytextRequired - What to search for, for example 'best vector databases'.
- Number of results
num_resultsnumber - Optional. How many results to return (1-20).From 1 to 20.
- Limit to site
sitetext - Optional. Restrict the search to one domain, for example 'https://jina.ai'.
- Country
countrytext - Optional. Two-letter country code to search from, for example 'US'.
- Include page content
include_page_contenttrue/false - Optional. Fetch the full markdown of each result page. Slower and uses far more tokens; off by default.Default:
false.
Outputs
resultslist- Search results, most relevant first
tokensnumber- Total tokens Jina counted across the results
Example output
{
"results": [
{
"content": "",
"description": "Our frontier models form the search foundation for high-quality enterprise search.",
"title": "Jina AI - Your Search Foundation, Supercharged.",
"url": "https://jina.ai/"
}
],
"tokens": 0
}