Jina AI (@JinaAI

Jina AI

2,266 posts

Jina AI

@JinaAI_

Your Search Foundation, Supercharged! (acquired by @elastic Oct. 2025)

San Francisco, CA

Joined March 2020

Jina AI
@JinaAI_
Sep 11, 2024
Announcing reader-lm-0.5b and reader-lm-1.5b, jina.ai/news/reader-lm… two Small Language Models (SLMs) inspired by Jina Reader, and specifically trained to generate clean markdown directly from noisy raw HTML. Both models are multilingual and support a context length of up to
Reader-LM: Small Language Models for Cleaning and Converting HTML to Markdown
From jina.ai
Jina AI
@JinaAI_
Aug 14, 2024
Based. Semantic chunking is overrated. Especially when you write a super regex that leverages all possible boundary cues and heuristics to segment text accurately without the need for complex language models. Just think about the speed and the hosting cost. This 50-line,
Jina AI
@JinaAI_
Feb 14, 2025
Introducing jina-deepsearch-v1, it search, read, reason, search, read, reason, search, read, reason, search, read, reason, search, read, reason, search, read, reason, search, read, reason, search, read, reason, search, read, reason, search, read, reason, ... 🔄 until the
00:00
Jina AI
@JinaAI_
Oct 30, 2024
curl docs.jina.ai This is our Meta-Prompt. It allows LLMs to understand our Reader, Embeddings, Reranker, and Classifier APIs for improved codegen. Using the meta-prompt is straightforward. Just copy the prompt into your preferred LLM interface like ChatGPT, Claude, or
00:00
Jina AI
@JinaAI_
Sep 18, 2024
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
00:00
Jina AI
@JinaAI_
Jan 15, 2025
Dear Readers, you'll ❤️ this: Introducing ReaderLM-v2, a 1.5B small language model for HTML-to-Markdown conversion and HTML-to-JSON extraction with exceptional quality. Thanks to the new training paradigm and higher-quality training data, ReaderLM-v2 is a significant leap forward
GIF
Jina AI
@JinaAI_
Oct 25, 2023
Introducing jina-embeddings-v2, the world's first open-source model boasting an 8K context length. Matching the prowess of OpenAI's proprietary models, now accessible on @huggingface, signaling a significant milestone in the landscape of text embeddings. jina.ai/news/jina-ai-l…
Jina AI
@JinaAI_
Apr 13, 2024
WE R OPEN SAUCE!
GitHub - jina-ai/reader: Convert any URL to an LLM-friendly input with a simple prefix https://r....
From github.com
Jina AI
@JinaAI_
Oct 21, 2022
Make sure to follow us for the latest in #multimodal AI research! We were just at the #COLING2022 conference in Gyeongju, Korea - the premier conference in computational linguistics & NLP. Check out our review of the research presented there. jina.ai/news/coling202… #emnlp2022
Jina AI
@JinaAI_
Apr 12, 2024
Feeding webpages to LLMs is crucial for grounding, but it's hard to do right. Scraping webpages is complex and unreliable, especially with dynamic pages. 🥁Introduce Jina Reader: simply prefix any URL with 𝗵𝘁𝘁𝗽𝘀://𝗿.𝗷𝗶𝗻𝗮.𝗮𝗶 and get an LLM-friendly input! Our Reader
Jina AI
@JinaAI_
Aug 21, 2025
Got a Mac with an M-chip? You can now train Gemma3 270m locally as a multilingual embedding or reranker model using our mlx-retrieval project. It lets you train Gemma3 270m locally at 4000 tokens/s on M3 Ultra - that's actually usable speed. We've implemented some standard
Jina AI
@JinaAI_
Mar 12, 2025
Doing these 2 things right takes your DeepSearch/DeepResearch impl from mid to GOAT: (1) selecting the best snippets from lengthy webpages and (2) ranking URLs before crawling. After some iterations, we've discovered uncommon yet effective uses for classic retriever models in
Jina AI
@JinaAI_
May 27, 2025
One interesting question people ask us is: "How do you guys vibe-check your embeddings?" Sure, there's MTEB for more serious quantitative evaluation on public benchmarks, but what do you do for open-domain or new problem? Today we want to share a small internal tool we use for
00:00
Jina AI
@JinaAI_
Nov 21, 2024
Jina-CLIP-v2: a 0.9B multilingual multimodal embedding model that supports 89 languages, 512x512 image resolution, 8192 token-length, and Matryoshka representations down to 64-dim for both images and text. jina.ai/news/jina-clip… With of course strong performance on retrieval &
Jina CLIP v2: Multilingual Multimodal Embeddings for Text and Images
From jina.ai