Saba Sturua
@jupyterjazz
Followers
203
Following
297
Media
7
Statuses
88
RT @michael_g_u: Resolution is important for image embeddings - especially for visual document retrieval. jina-embeddings-v4 supports input….
jina.ai
Image resolution is crucial for embedding visually rich documents. Too small and models miss key details; too large and they can't connect the parts.
0
2
0
RT @michael_g_u: Our paper "Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models" has been accepted at the Robust….
arxiv.org
Many use cases require retrieving smaller portions of text, and dense vector-based retrieval systems often perform better with shorter text segments, as the semantics are less likely to be...
0
18
0
I just integrated jina-embeddings-v4 with vLLM, and throughput doubled compared to inference via transformers (tested on Flickr data, 2k text/images). Instructions on the model page:.
0
5
15
RT @bo_wangbo: jina-embeddings-v3 + jina-clip-v2 + jina-colbert-v2 + colpali + dse = jina-embeddings-v4 😇. https://….
0
33
0
RT @karpathy: This is interesting as a first large diffusion-based LLM. Most of the LLMs you've been seeing are ~clones as far as the core….
0
2K
0
RT @bo_wangbo: Great work from MMTEB team! We have 3 contributors from @JinaAI_ ! @michael_g_u @jupyterjazz @isabelle_mohr.
0
5
0
Looking forward to ECIR!.
Our submission to ECIR 2025 on jina-embeddings-v3 has been accepted! 🎉.At the ECIR Industry Day @jupyterjazz takes the stage to share how we train the latest version of our text embedding model. More details:
0
0
3
RT @JinaAI_: At #EMNLP2024 Miami next week? Join us on November 14, 2024, from 10:30 AM to 12:00 PM (Miami Time) for a BoF session on Embed….
0
9
0
Proud to share our latest work: jina-embeddings-v3💥. We've developed a multilingual text embedding model with task-specific LoRA adapters, supporting Matryoshka representations. For more details:
Finally, jina-embeddings-v3 is here! A frontier multilingual embedding model with 570M parameters, 8192-token length, achieving SOTA performance on multilingual and long-context retrieval tasks. It outperforms the latest proprietary models from OpenAI and Cohere, and outperforms
0
0
4
RT @JinaAI_: 🚀Jina Reranker v2 is here! The best-in-class reranker for Agentic RAG. Featuring cross-lingual retriev….
jina.ai
Jina Reranker v2 is the best-in-class reranker built for Agentic RAG. It features function-calling support, multilingual retrieval for over 100 languages, code search capabilities, and offers a 6x...
0
31
0
Clip your schedules for next week because Andreas and I will present our latest text&image embedding model with advanced text capabilities 😉. Paper: 🤗: API:
jina.ai
Top-performing multimodal multilingual long-context embeddings for search, RAG, agents applications.
Get ready for the next MLOps Community Mini Summit!. Join us on Wednesday, June 12th, at 17:00 UK time for "Fresh Data, Smart Retrieval: Milvus & Jina CLIP Explained."
0
5
13
RT @JinaAI_: Together with the research team @BAAIBeijing (the creator of bge-m3 embeddings), we are excited to rel….
huggingface.co
0
29
0
RT @YourAnonTV: 🚨Anonymous PR/#OpGeorgia. - To the protesters in Georgia, we have heard your plea for help. Take heart and take to your str….
0
1K
0
Our work on bilingual embedding models ⬇️.
How did we train DE-EN, ES-EN & ZH-EN bilingual embeddings with 8192-token length? Is a bilingual model superior to a multilingual one? How do they perform on out-of-domain data? Find out in our latest publication. 👇.
0
0
3
RT @JinaAI_: Our open-source bilingual Spanish-English embedding model is now ready for download through @huggingface. Start using it right….
huggingface.co
0
6
0
RT @JinaAI_: Im Geiste von JFK’s “Ich bin ein Berliner” Aussage veröffentlichen wir unser zweisprachiges deutsch-englisches Embedding-Model….
jina.ai
Jina AI introduces a German/English bilingual embedding model, featuring an extensive 8,192-token length, specifically designed to support German businesses thriving in the U.S. market.
0
1
0
RT @JinaAI_: Learn the history of text embeddings with our exclusive infographic poster, illustrating the groundbreaking evolution over the….
0
13
0
RT @ClementDelangue: If you need help on embeddings and multimodal for enterprise, these folks know what they're talking about: https://t.c….
0
20
0
RT @JinaAI_: 🎉What a week! Our Embedding API is here! 8192 token-length, same performance as OpenAI text-embeddings-ada002 but up to 50x ch….
jina.ai
Top-performing multimodal multilingual long-context embeddings for search, RAG, agents applications.
0
8
0