notifications
News
Products
For Enterprises
Embeddings
World-class multimodal multilingual embeddings for search/RAG/agents.
Reranker
World-class neural retriever for maximizing search relevancy.
Reader
Read URLs or search the web, get better grounding for LLMs.
Segmenter
Segment long text into chunks and do tokenization.
For Power Users
PromptPerfect
Premier tool for prompt engineering
More power user tools
SceneXplain
Leading AI solution for image captions and video summaries
BestBanner
Blog to banner, without the prompts!
JinaChat
More modality, longer memory, less cost
Rationale
Ultimate AI decision-making tools
For Developers
DocArray
The data structure for multimodal data
Jina
Build multimodal AI applications on the cloud
More developer tools
CLIP-as-service
Embed images and sentences into fixed-length vectors with CLIP
Finetuner
Fine-tune embeddings on domain specific data for better search quality
JCloud
Deploy a local project as a cloud service. Radically easy, no nasty surprises.
LangChain-Serve
Langchain apps on production with Jina & FastAPI
VectorDB
A Python vector database you just need - no more, no less
DALL-E Flow
A human-in-the-Loop workflow for creating HD images from text
DiscoArt
Create compelling Disco Diffusion artworks in one line of code
ThinkGPT
Agent techniques to augment your LLM and push it beyond its limits
DevGPT
Your virtual development team
RunGPT
An open-source cloud-native of large multimodal models serving framework
Jerboa
An experimental finetuner for open-source LLMs
Company
About us
Contact sales
Intern program
Join us
open_in_new
Download logo
open_in_new

Your Search Foundation Supercharged.

handshakeContact
forumCommunity
Our customers

Newsroom

star
Featured
Press release
Reader-LM: Small Language Models for Cleaning and Converting HTML to Markdown
September 11, 2024 • 12 minutes read
star
Featured
Press release
Jina ColBERT v2: Multilingual Late Interaction Retriever for Embedding and Reranking
August 30, 2024 • 10 minutes read
Dark-themed coding interface displaying English and Japanese characters with "JINA COLBERT V2" highlighted in the center.
Tech blog
The What and Why of Text-Image Modality Gap in CLIP Models
August 26, 2024 • 13 minutes read
Futuristic black image with "modality gap" in 3D purple letters, additional text, and a dynamic glass sphere effect.
auto_storiesRead more
rss_feedRSS

For Enterprise

Our frontier models form the search foundation for high-quality enterprise search and RAG systems.

Embeddings

World-class multimodal multilingual embeddings for search/RAG/agents.

Reranker

World-class neural retriever for maximizing search relevancy.

Reader

Get LLM-friendly input from a URL or a web search, by simply adding r.jina.ai in front.

Segmenter

Segment long text into chunks and do tokenization.
Start instantly—no credit card or registration needed!
report_problemWe cannot generate an API key because we couldn't verify if you are human. If you believe this is an error, please contact us.
Contact
key
API Key & Billing
Embeddings
Reranker
Reader
Segmenter
Auto Fine-Tuning
verified_user
Integrate
home
Auto preview
forumRaise issuehelp_outlinefaq
Status
Returning data type
Besides the float, you can ask it to return as binary for faster vector retrieval, or as base64 encoding for faster transmission.
Example inputs
Change them and see how the response changes!
upload
Request
curl https://api.jina.ai/v1/embeddings \
	 -H "Content-Type: application/json" \
	 -H "Authorization: Bearer " \
	 -d '{
	"model": "undefined",
	"normalized": true,
	"embedding_type": "float",
	"input": [
		"A blue cat", 
		"A red dog", 
		"btw to represent image u can either use URL or encode image into base64 like below.", 
		"https://i.pinimg.com/600x315/21/48/7e/21487e8e0970dd366dafaed6ab25d8d8.jpg", 
		"R0lGODlhEAAQAMQAAORHHOVSKudfOulrSOp3WOyDZu6QdvCchPGolfO0o/XBs/fNwfjZ0frl3/zy7////wAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACH5BAkAABAALAAAAAAQABAAAAVVICSOZGlCQAosJ6mu7fiyZeKqNKToQGDsM8hBADgUXoGAiqhSvp5QAnQKGIgUhwFUYLCVDFCrKUE1lBavAViFIDlTImbKC5Gm2hB0SlBCBMQiB0UjIQA7"
    ]}'
Our Publications
Understand how our frontier search models were trained from scratch, check out our latest publications. Meet our team at EMNLP, SIGIR, ICLR, NeurIPS, and ICML!
schoolRead more
arXiv
September 07, 2024
Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models
arXiv
August 30, 2024
Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever
arXiv
June 21, 2024
Leveraging Passage Embeddings for Efficient Listwise Reranking with Large Language Models
ICML 2024
May 30, 2024
Jina CLIP: Your CLIP Model Is Also Your Text Retriever
arXiv
February 26, 2024
Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings
arXiv
October 30, 2023
Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents
EMNLP 2023
July 20, 2023
Jina Embeddings: A Novel Set of High-Performance Sentence Embedding Models
7 publications in total.

For Power Users

Auto prompt engineering for your daily productivity.
Assistant
Prompt optimization
Compare models
Deploy prompts
Multi-agent
question_answer

Daily dose of productivity.

Easily switch between content generation and prompt optimization, push your content quality to the next level.

Get started with PromptPerfect

For Developers

Over the years, we've developed a variety of open-source software to help developers build better GenAI and search applications faster.
Data Structure
Linux Foundation
Core
school
Graduated
Orchestration
Cloud Native
Kubernetes
Embedding Serving
Model Serving
Mid Size Model
science
Incubating
Embedding Tuning
Small Size Model
Prompt Serving
egg
Sandbox
Vector Database
archive
Archived
Prompt Tuning
Large Size Model
Build multimodal AI applications on the cloud open_in_new
Jina
The data structure for multimodal data open_in_new
DocArray
Langchain apps on production with Jina & FastAPI open_in_new
LangChain-Serve
A Python vector database you just need - no more, no less open_in_new
VectorDB
An open-source cloud-native of large multimodal models serving framework open_in_new
RunGPT
Fine-tune embeddings on domain specific data for better search quality open_in_new
Finetuner
A human-in-the-Loop workflow for creating HD images from text open_in_new
DALL-E Flow
Create compelling Disco Diffusion artworks in one line of code open_in_new
DiscoArt
Embed images and sentences into fixed-length vectors with CLIP open_in_new
CLIP-as-service
Deploy a local project as a cloud service. Radically easy, no nasty surprises. open_in_new
JCloud
Agent techniques to augment your LLM and push it beyond its limits open_in_new
ThinkGPT
Your virtual development team open_in_new
DevGPT
An experimental finetuner for open-source LLMs open_in_new
Jerboa
Offices
location_on
Berlin, Germany (HQ)
Prinzessinnenstraße 19-20, 10969 Berlin, Germany
Geschäftsanschrift: Leipzigerstr. 96, 10117 Berlin, Germany
location_on
Beijing, China
Level 5, Building 6, No.48 Haidian West St. Beijing Haidian, China
location_on
Shenzhen, China
402, Floor 4, Fu'an Technology Building, Shenzhen Nanshan, China
Search Foundation
Embeddings
Reranker
Reader
Segmenter
Get Jina AI API key
API Status
Company
About us
Contact sales
Newsroom
Intern program
Join us
open_in_new
Download logo
open_in_new
Terms
Terms & Conditions
Privacy
Manage Cookies
email
Jina AI GmbH © 2020-2024.