feed.rss

<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:media="http://search.yahoo.com/mrss/"><channel><title><![CDATA[Jina AI]]></title><description><![CDATA[Please visit https://jina.ai]]></description><link>https://jina.ai/news</link><image><url>https://jina.ai/favicon.ico</url><title>Jina AI</title><link>https://jina.ai/news</link></image><generator>Ghost 5.118</generator><lastBuildDate>Tue, 22 Apr 2025 14:32:59 GMT</lastBuildDate><atom:link href="https://jina-ai-gmbh.ghost.io/326d1d7035ea75a576ec026540f88b/rss/" rel="self" type="application/rss+xml"/><ttl>60</ttl><item><title><![CDATA[On the Size Bias of Text Embeddings and Its Impact in Search]]></title><description><![CDATA[Size bias refers to how the length of text inputs affects similarity, regardless of semantic relevance. It explains why search systems sometimes return long, barely-relevant documents instead of shorter, more precise matches to your query.]]></description><link>https://jina.ai/news/on-the-size-bias-of-text-embeddings-and-its-impact-in-search/</link><guid isPermaLink="false">67e52df15dcba60001c30ebe</guid><category><![CDATA[Tech Blog]]></category><dc:creator><![CDATA[Scott Martens]]></dc:creator><pubDate>Wed, 16 Apr 2025 01:40:03 GMT</pubDate><media:content url="https://jina-ai-gmbh.ghost.io/content/images/2025/04/Heading---2025-04-16T094756.687.png" medium="image"/></item><item><title><![CDATA[jina-reranker-m0: Multilingual Multimodal Document Reranker]]></title><description><![CDATA[Introducing jina-reranker-m0, our new multilingual multimodal reranker for retrieving visual documents, with SOTA performance on multilingual long documents and code searching tasks.]]></description><link>https://jina.ai/news/jina-reranker-m0-multilingual-multimodal-document-reranker/</link><guid isPermaLink="false">67ea5eb45dcba60001c30f0a</guid><category><![CDATA[Press]]></category><dc:creator><![CDATA[Jina AI]]></dc:creator><pubDate>Tue, 08 Apr 2025 11:10:38 GMT</pubDate><media:content url="https://jina-ai-gmbh.ghost.io/content/images/2025/04/Banner-Reranker-m0--2--1.png" medium="image"/></item><item><title><![CDATA[Using DeepSeek R1 Reasoning Model in DeepSearch]]></title><description><![CDATA[Standard LLM or reasoning model, which is better for DeepSearch? In this post, we explored using DeepSeek-R1 in the DeepSearch implementation for choosing the next action.]]></description><link>https://jina.ai/news/using-deepseek-r1-reasoning-model-in-deepsearch/</link><guid isPermaLink="false">67dd5037143bda0001036423</guid><category><![CDATA[Tech Blog]]></category><dc:creator><![CDATA[Andrei Ungureanu]]></dc:creator><pubDate>Tue, 01 Apr 2025 07:38:45 GMT</pubDate><media:content url="https://jina-ai-gmbh.ghost.io/content/images/2025/04/Heading--92-.png" medium="image"/></item><item><title><![CDATA[DeepSearch on Private Visual Documents: An Enterprise Case Study]]></title><description><![CDATA[Our DeepSearch works with private PDFs and visual documents right out of the box. Discover how DeepSearch can unlock valuable insights from your enterprise data.]]></description><link>https://jina.ai/news/deepsearch-on-private-visual-documents-an-enterprise-case-study/</link><guid isPermaLink="false">67ea631b5dcba60001c30f16</guid><category><![CDATA[Tech Blog]]></category><dc:creator><![CDATA[Maximilian Werk]]></dc:creator><pubDate>Mon, 31 Mar 2025 11:36:51 GMT</pubDate><media:content url="https://jina-ai-gmbh.ghost.io/content/images/2025/03/Heading--5-.jpg" medium="image"/></item><item><title><![CDATA[Snippet Selection and URL Ranking in DeepSearch/DeepResearch]]></title><description><![CDATA[Nailing these two details takes your DeepSearch from mid to GOAT: selecting the best snippets from lengthy webpages and ranking URLs before crawling.]]></description><link>https://jina.ai/news/snippet-selection-and-url-ranking-in-deepsearch-deepresearch/</link><guid isPermaLink="false">67d13ae9099ee70001bed48b</guid><category><![CDATA[Tech Blog]]></category><dc:creator><![CDATA[Han Xiao]]></dc:creator><pubDate>Wed, 12 Mar 2025 13:20:43 GMT</pubDate><media:content url="https://jina-ai-gmbh.ghost.io/content/images/2025/03/Heading--89-.png" medium="image"/></item><item><title><![CDATA[Long-Context Embedding Models are Blind Beyond 4K Tokens]]></title><description><![CDATA[We investigate embedding models on new "needle-in-haystack" tasks and find that beyond 4K tokens, they're just rolling dice - even with exact lexical matches or query expansion, they can't tell signal from noise in long context.]]></description><link>https://jina.ai/news/long-context-embedding-models-are-blind-beyond-4k-tokens/</link><guid isPermaLink="false">67c868baf1c5780001164330</guid><category><![CDATA[Tech Blog]]></category><dc:creator><![CDATA[Saahil Ognawala]]></dc:creator><pubDate>Fri, 07 Mar 2025 02:56:34 GMT</pubDate><media:content url="https://jina-ai-gmbh.ghost.io/content/images/2025/03/haystack.png" medium="image"/></item><item><title><![CDATA[LLM-as-SERP: Search Engine Result Pages from Large Language Models]]></title><description><![CDATA[This idea either extremely smart or extremely stupid—no in-between. Read till the end and find out why this could be useful.]]></description><link>https://jina.ai/news/llm-as-serp-search-engine-result-pages-from-large-language-models/</link><guid isPermaLink="false">67c02c3b343c560001efca6e</guid><category><![CDATA[Tech Blog]]></category><dc:creator><![CDATA[Han Xiao]]></dc:creator><pubDate>Thu, 27 Feb 2025 12:36:57 GMT</pubDate><media:content url="https://jina-ai-gmbh.ghost.io/content/images/2025/02/llmserp-banner.png" medium="image"/></item><item><title><![CDATA[A Practical Guide to Implementing DeepSearch/DeepResearch]]></title><description><![CDATA[QPS out, depth in. DeepSearch is the new norm. Find answers through read-search-reason loops. Learn what it is and how to build it.]]></description><link>https://jina.ai/news/a-practical-guide-to-implementing-deepsearch-deepresearch/</link><guid isPermaLink="false">67bc50b0b1b8af00014db4c9</guid><category><![CDATA[Tech Blog]]></category><dc:creator><![CDATA[Han Xiao]]></dc:creator><pubDate>Tue, 25 Feb 2025 13:36:17 GMT</pubDate><media:content url="https://jina-ai-gmbh.ghost.io/content/images/2025/02/deepsearch-banner.png" medium="image"/></item><item><title><![CDATA[Query Expansion with LLMs: Searching Better by Saying More]]></title><description><![CDATA[Search has changed a lot since embedding models were introduced. Is there still a role for lexical techniques like query expansion in AI? We think so.]]></description><link>https://jina.ai/news/query-expansion-with-llms-searching-better-by-saying-more/</link><guid isPermaLink="false">67af53142962d20001d63c71</guid><category><![CDATA[Tech Blog]]></category><dc:creator><![CDATA[Michael Günther]]></dc:creator><pubDate>Tue, 18 Feb 2025 02:24:20 GMT</pubDate><media:content url="https://jina-ai-gmbh.ghost.io/content/images/2025/02/query-banner.png" medium="image"/></item><item><title><![CDATA[A Practical Guide to Deploying Search Foundation Models in Production]]></title><description><![CDATA[We offer detailed cost and performance breakdowns for three deployment strategies: Jina API, self-hosted K8s, and AWS SageMaker, to help you make the right decision.]]></description><link>https://jina.ai/news/a-practical-guide-to-deploying-search-foundation-models-in-production/</link><guid isPermaLink="false">679b56ba42b46600019a86e3</guid><category><![CDATA[Tech Blog]]></category><dc:creator><![CDATA[Saahil Ognawala]]></dc:creator><pubDate>Fri, 31 Jan 2025 04:32:29 GMT</pubDate><media:content url="https://jina-ai-gmbh.ghost.io/content/images/2025/01/guide-banner.jpg" medium="image"/></item><item><title><![CDATA[What Should We Learn From ModernBERT?]]></title><description><![CDATA[Bigger training data, efficient parameter sizing, and a deep-but-thin architecture, ModernBERT sets a direction for future BERT-like models.]]></description><link>https://jina.ai/news/what-should-we-learn-from-modernbert/</link><guid isPermaLink="false">678cc6a18f6bb40001a63537</guid><category><![CDATA[Tech Blog]]></category><dc:creator><![CDATA[Nan Wang]]></dc:creator><pubDate>Wed, 22 Jan 2025 07:31:26 GMT</pubDate><media:content url="https://jina-ai-gmbh.ghost.io/content/images/2025/01/modernbert-banner.png" medium="image"/></item><item><title><![CDATA[ReaderLM v2: Frontier Small Language Model for HTML to Markdown and JSON]]></title><description><![CDATA[ReaderLM-v2 is a 1.5B small language model for HTML-to-Markdown conversion and HTML-to-JSON extraction with exceptional quality.]]></description><link>https://jina.ai/news/readerlm-v2-frontier-small-language-model-for-html-to-markdown-and-json/</link><guid isPermaLink="false">6785bfd62defad0001fb5f22</guid><category><![CDATA[Press]]></category><dc:creator><![CDATA[Jina AI]]></dc:creator><pubDate>Wed, 15 Jan 2025 10:35:18 GMT</pubDate><media:content url="https://jina-ai-gmbh.ghost.io/content/images/2025/01/readerlm-v2.png" medium="image"/></item><item><title><![CDATA[Text-Image Global Contrastive Alignment and Token-Patch Local Alignment]]></title><description><![CDATA[CLIP can visualize token-patch similarities, however, it’s more of a post-hoc interpretability trick than a robust or official "attention" from the model. Here's why.]]></description><link>https://jina.ai/news/text-image-global-contrastive-alignment-and-token-patch-local-alignment/</link><guid isPermaLink="false">677be55d2defad0001fb5e13</guid><category><![CDATA[Tech Blog]]></category><dc:creator><![CDATA[Han Xiao]]></dc:creator><pubDate>Tue, 07 Jan 2025 11:23:50 GMT</pubDate><media:content url="https://jina-ai-gmbh.ghost.io/content/images/2025/01/banner--16-.png" medium="image"/></item><item><title><![CDATA[Text Embeddings Fail to Capture Word Order and How to Fix It]]></title><description><![CDATA[Text embedding models struggle with capturing subtle linguistic nuances like word order, directional relationships, temporal sequences, causal connections, comparisons, and negation. Understanding these challenges is key to improving model performance.]]></description><link>https://jina.ai/news/text-embeddings-fail-to-capture-word-order-and-how-to-fix-it/</link><guid isPermaLink="false">6761676f2defad0001fb5d8a</guid><category><![CDATA[Tech Blog]]></category><dc:creator><![CDATA[Bo Wang]]></dc:creator><pubDate>Tue, 17 Dec 2024 15:30:27 GMT</pubDate><media:content url="https://jina-ai-gmbh.ghost.io/content/images/2024/12/banner-order.png" medium="image"/></item><item><title><![CDATA[Re·Search: Order 2024 Yearbook of Search Foundation Advances]]></title><description><![CDATA[Discover Re·Search, our premium yearbook showcasing our best research articles and search foundation models in 2024. Featuring spot UV-coated hardcover, 160 full-color pages, and meticulous design throughout. Available worldwide at $35, shipping included.]]></description><link>https://jina.ai/news/re-search-order-2024-yearbook-of-search-foundation-advances/</link><guid isPermaLink="false">675f75780ce9930001b870a7</guid><category><![CDATA[Press]]></category><dc:creator><![CDATA[Jina AI]]></dc:creator><pubDate>Mon, 16 Dec 2024 14:35:49 GMT</pubDate><media:content url="https://jina-ai-gmbh.ghost.io/content/images/2024/12/banner-1-1.png" medium="image"/></item></channel></rss>