| capture_screenshot_url |
– |
Screenshot a page as base64 JPEG. Use when the page must be seen rather than read.
Input schema
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri"
},
"return_url": {
"type": "boolean",
"default": false,
"description": "Return URLs instead of base64 images."
},
"firstScreenOnly": {
"type": "boolean",
"default": false,
"description": "Capture only the first screen instead of the full page. Faster."
}
},
"additionalProperties": false
}
|
| deduplicate_strings |
– |
Select the top-k semantically distinct strings from a list, dropping near-duplicates.
Input schema
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"strings"
],
"properties": {
"k": {
"type": "integer",
"minimum": 1,
"description": "How many to keep. Omit to pick k automatically from diminishing returns."
},
"strings": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 1000,
"minItems": 1,
"description": "Strings to deduplicate, up to 1000."
}
},
"additionalProperties": false
}
|
| extract_pdf |
– |
Extract figures, tables and equations from a PDF as images, by arXiv id or URL.
Input schema
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"id": {
"type": "string",
"description": "arXiv id, e.g. '2301.12345'. Give id or url."
},
"url": {
"type": "string",
"format": "uri",
"description": "PDF URL. Give id or url."
},
"type": {
"type": "string",
"description": "Comma-separated types to keep: figure, table, equation. Default all."
},
"max_edge": {
"type": "number",
"default": 1024,
"description": "Longest image edge in pixels, default 1024."
}
},
"additionalProperties": false
}
|
| guess_datetime_url |
– |
Guess when a page was published or last updated, with a confidence score. Checks HTTP headers, metadata, Schema.org, visible dates, feeds and sitemaps.
Input schema
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri"
}
},
"additionalProperties": false
}
|
| primer |
– |
Current time, user location and network environment for the session. Use before answering anything time- or location-dependent.
Input schema
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}
|
| read_url |
– |
Fetch a URL (page or PDF) as clean markdown. Pass `question` to get only the passages answering it instead of the whole page - far cheaper than reading the f...
Input schema
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"url"
],
"properties": {
"ocr": {
"type": "boolean",
"description": "Read the rendered page as an image with jina-ocr-v1 instead of its HTML. Use for scanned documents and PDFs whose text is not in the markup, and to keep formulas and table structure. Parses ONE page per call, page 1 unless `page` says otherwise, and costs about 40x the tokens per page, so leave off unless the HTML path has failed you."
},
"url": {
"anyOf": [
{
"type": "string",
"format": "uri"
},
{
"type": "array",
"items": {
"type": "string",
"format": "uri"
},
"maxItems": 5,
"minItems": 1
}
],
"description": "Page or PDF URL, or up to 5 URLs to read in parallel."
},
"page": {
"type": "integer",
"minimum": 1,
"description": "Which page the OCR pass should parse, 1-based. Needs `ocr`; the HTML path returns the whole document at once."
},
"topk": {
"type": "integer",
"maximum": 50,
"minimum": 1,
"description": "Passages to return, default 1. Needs `question`."
},
"question": {
"type": "string",
"description": "Return only the passages answering this question, instead of the full body. Omit for the whole page."
},
"chunk_size": {
"type": "integer",
"maximum": 4096,
"minimum": 1,
"description": "Passage size in words, default 100. Larger gives more surrounding context, smaller pinpoints the answer. Comparable across scripts. Needs `question`."
},
"withAllLinks": {
"type": "boolean",
"description": "Also return every link on the page."
},
"withAllImages": {
"type": "boolean",
"description": "Also return every image on the page."
}
},
"additionalProperties": false
}
|
| search_arxiv |
– |
Search arXiv preprints (physics, maths, CS, quantitative biology and finance).
Input schema
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"query"
],
"properties": {
"num": {
"type": "integer",
"default": 10,
"maximum": 10,
"minimum": 1
},
"tbs": {
"type": "string",
"description": "Age limit: qdr:h, qdr:d, qdr:w, qdr:m, qdr:y (hour to year)."
},
"query": {
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
},
"maxItems": 5,
"minItems": 1
}
]
}
},
"additionalProperties": false
}
|
| search_images |
– |
Search the web for images. Returns base64 JPEGs by default.
Input schema
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"query"
],
"properties": {
"gl": {
"type": "string",
"description": "Country code, e.g. 'de'."
},
"hl": {
"type": "string",
"description": "Language code, e.g. 'zh-cn'."
},
"num": {
"type": "integer",
"default": 10,
"maximum": 10,
"minimum": 1
},
"tbs": {
"type": "string",
"description": "Age limit: qdr:h, qdr:d, qdr:w, qdr:m, qdr:y (hour to year)."
},
"query": {
"type": "string"
},
"location": {
"type": "string"
},
"return_url": {
"type": "boolean",
"default": false,
"description": "Return URLs and metadata instead of base64 images."
}
},
"additionalProperties": false
}
|
| search_jina_blog |
– |
Search Jina AI's news and blog at jina.ai/news: product announcements, model releases, technical write-ups.
Input schema
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"query"
],
"properties": {
"num": {
"type": "integer",
"default": 30,
"maximum": 100,
"minimum": 1
},
"tbs": {
"type": "string",
"description": "Age limit: qdr:h, qdr:d, qdr:w, qdr:m, qdr:y (hour to year)."
},
"query": {
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
},
"maxItems": 5,
"minItems": 1
}
]
}
},
"additionalProperties": false
}
|
| search_ssrn |
– |
Search SSRN working papers (social science, economics, law, finance, management).
Input schema
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"query"
],
"properties": {
"num": {
"type": "integer",
"default": 10,
"maximum": 10,
"minimum": 1
},
"tbs": {
"type": "string",
"description": "Age limit: qdr:h, qdr:d, qdr:w, qdr:m, qdr:y (hour to year)."
},
"query": {
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
},
"maxItems": 5,
"minItems": 1
}
]
}
},
"additionalProperties": false
}
|
| search_web |
– |
Search the web. Returns titles, URLs and search-engine snippets.
Input schema
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"query"
],
"properties": {
"gl": {
"type": "string",
"description": "Country code, e.g. 'de'."
},
"hl": {
"type": "string",
"description": "Language code, e.g. 'zh-cn'."
},
"num": {
"type": "integer",
"default": 10,
"maximum": 10,
"minimum": 1
},
"tbs": {
"type": "string",
"description": "Age limit: qdr:h, qdr:d, qdr:w, qdr:m, qdr:y (hour to year)."
},
"query": {
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
},
"maxItems": 5,
"minItems": 1
}
]
},
"location": {
"type": "string"
}
},
"additionalProperties": false
}
|
| sort_by_relevance |
– |
Rerank documents by relevance to a query, using Jina Reranker.
Input schema
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"query",
"documents"
],
"properties": {
"query": {
"type": "string"
},
"top_n": {
"type": "integer",
"minimum": 1
},
"documents": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 1024,
"minItems": 1,
"description": "Documents to rank, up to 1024."
}
},
"additionalProperties": false
}
|