We are pleased to announce that Jina AI’s Text Embeddings has been integrated into Eden AI API.
Jina AI is a leading company in the field of artificial intelligence, specializing in multimodal AI applications. Founded in 2020 and based in Berlin, Germany, Jina AI’s mission is to advance multimodal AI by developing tools and platforms that facilitate the processing and analysis of diverse data types, including text, images, and videos, through natural language processing, image and video analysis, and cross-modal data interaction
Their products and services include APIs for embeddings and prompt optimization, enterprise search solutions, and the open-source Jina framework for building multimodal AI services. The company provides solutions for enterprise search, re-ranking, and retrieval-augmented generation (RAG) solutions, aiming to improve search relevance and accuracy.
Eden AI offers Jina AI's Text Embeddings API on its platform amongst several other text technologies. We want our users to have access to multiple AI engines and manage them in one place so they can reach high performance, optimize cost and cover all their needs.
There are many reasons for using multiple AI APIs :
You need to set up an AI API that is requested if and only if the main AI API does not perform well (or is down). You can use the confidence score returned or other methods to check provider accuracy.
After the testing phase, you will be able to build a mapping of AI vendors' performance that depends on the criteria that you chose. Each data that you need to process will be then sent to the best API.
This method allows you to choose the cheapest provider that performs well for your data. Let's imagine that you choose Google Cloud API for customer "A" because they all perform well and this is the cheapest. You will then choose Microsoft Azure for customer "B", a more expensive API but Google performances are not satisfying for customer "B". (this is a random example)
This approach is required if you look for extremely high accuracy. The combination leads to higher costs but allows your AI service to be safe and accurate because AI APIs will validate and invalidate each other for each piece of data.
Jina AI was founded in 2020 and is headquartered in Berlin, Germany. Formerly working at Tencent, the founding team consisting of Dr. Han Xiao (CEO), Nan Wang (CTO) and Bing He (COO) decided to create a new open-source multimodal neural search solution.
Today, Jina AI focuses on areas like natural language processing, image and video analysis, and cross-modal data interaction. The company envisions paving the way towards the future of AI as a multimodal reality, addressing challenges in handling multimodal AI with pioneering tools and platforms. The company is venture-backed, having completed a Series A funding round and raising a total of USD 38M.
Jina AI offers embedding models with various specifications and through various channels. Aside from its most popular English model (jina-embeddings-v2-base-en), we also provide several bilingual models, covering German-English, Chinese-English and Spanish-English translations. Jina also offers a code model, used to create embeddings for 30 of the most popular programming languages. Additionally, we just released our brand-new ColBERT (jina-colbert-v1-en) model and our first reranking model (jina-reranker-v1-base-en).
Our models can be accessed either through our API, on AWS SageMaker, and as open-source through HuggingFace. What sets our models apart is first and foremost our context window of 8192 tokens, compared to the widely spread length of 512. By focusing on bilingual cases, our models also perform better on language-specific tasks than our competitors’ multilingual models.
Given the enormous potential of embeddings within applications such as RAG (Retrieval Augmented Generation), our customers cover a wide range of industries. The most popular fields that Jina users operate in are e-commerce, insurance services, healthcare, and matchmaking platforms. More specific applications might include information retrieval, recommendation systems, semantic clustering and bilingual translation.
Through our embeddings, customers are able to accurately encode information and increase the quality of matches to given queries. This directly impacts the quality of their services, leading to a lower need for revision and increasing the topline of their products.
We are excited to partner with Eden AI. Your approach to offering a single, streamlined API for multiple AI services resonates with us at Jina AI. By combining our forces, we can harness a wider range of AI capabilities, significantly boosting the value we provide to our users.
By teaming up, we aim to blend a wide array of AI features, directly boosting the capabilities of our embedding technologies. This partnership means our service users will gain access to enhanced, more efficient capabilities. We're excited about how this partnership will unlock new, efficient solutions tailored specifically for users of Jina AI and Eden AI.
Amongst the most recent releases we have worked on extending our offering to different parts of the RAG pipeline. By developing a ColBERT and reranker models, we have taken an additional step towards creating a complete offering that improves both the encoding and retrieval steps of RAG solutions.
In the near future, to increase our competitive advantage and showcase the quality of our models, we aim to release a new version of our embedding models which will directly compete with the most performing models on the market. With this new model, we aim to position ourselves at the forefront of AI development, opening up new business opportunities for our customers and further increasing the quality of their solutions.
To use Jina AI on Eden AI, you just need to access Eden AI's website and call the API:
Eden AI is the future of AI usage in companies. Our platform not only allows you to call multiple AI APIs but also gives you :
You can directly start building now. If you have any questions, feel free to chat with us!
Get startedContact salesDrop your email and we'll get back to you ASAP to answer any questions you have or just to say hi —we promise not to spam you!
-p-500.webp){kind=small}
-p-500.webp){kind=small}
.svg)
