Tech Blog Build a RAG system with Jina Embeddings and Qdrant Create a RAG system with Jina Embeddings v2, Qdrant vector database, LlamaIndex, and Mistral LLM.
Tech Blog Featured What is ColBERT and Late Interaction and Why They Matter in Search? Jina AI's ColBERT on Hugging Face has set Twitter abuzz, bringing a fresh perspective to search with its 8192-token capability. This article unpacks the nuances of ColBERT and ColBERTv2, showcasing their innovative designs and why their late interaction feature is a game-changer for search.
Tech Blog SceneXplain: Alt Text and Better SEO for Your Ghost Blog With One Command Supercharge your Ghost blog's SEO and accessibility by automatically generating alt texts. All it takes is one command. WordPress/WooCommerce support coming soon!
Tech Blog A Deep Dive into Tokenization Tokenization, in LLMs, means chopping input texts up into smaller parts for processing. So why are embeddings billed by the token?
Tech Blog MyScale & Jina AI: Unleashing Great Potential for Your AI Applications With full integration of Jina Embeddings v2 models, MyScale allows users to harness the capabilities of Jina AI within an SQL database.
Tech Blog Jina Embeddings v2 Bilingual Models Are Now Open-Source On Hugging Face Jina AI's open-source bilingual embedding models for German-English and Chinese-English are now on Hugging Face. We’re going to walk through installation and cross-language retrieval.
Tech Blog Making Accessibility Accessible: Create Alt Text with SceneXplain's API SceneXplain is your accessibility ally, making it easy to generate image alt texts to aid visually-impaired users and improve SEO
Tech Blog Featured Does Subspace Cosine Similarity Imply High-Dimensional Cosine Similarity? Does high similarity in subspace assure a high overall similarity between vectors? This post examines the theory and practical implications of subspace similarity.
Tech Blog Using Jina Embeddings v2 with Haystack Pipelines Access Jina AI's state-of-the-art open-source embedding models in your Haystack application pipeline.
Tech Blog Featured The 1950-2024 Text Embeddings Evolution Poster Take part in celebrating the achievements of text embeddings and carry a piece of its legacy with you.
Tech Blog Words + JSON + Images = SceneXplain's new JSON Schema Builder Effortlessly create JSON Schemas with SceneXplain: Describe your needs in natural language, and get the perfect schema for extracting JSON from your images!
Tech Blog Full-stack RAG with Jina Embeddings v2 and LlamaIndex You can build your own RAG chatbot in a matter of minutes with Jina Embeddings, LlamaIndex and Mixtral Instruct. We'll show you how to get up and running right now.
Tech Blog A Magic Carpet Ride: Building Vivid Product Stories with SceneXplain See how companies are integrating SceneXplain with their existing infrastructure to power their product descriptions and storytelling
Tech Blog Multi-Agent Simulations in PromptPerfect: 𝑛 Heads Are Better Than One Discover the real-world impact of multi-agent simulations and see practical examples of systems uniting individual strengths to tackle complex tasks, offering efficient and tailored solutions across various domains
Tech Blog There's a Time and a Place: Unleashing Dynamic Variables in PromptPerfect Incorporate users' time, date and location into your prompts. Plus contents of other websites, and outputs of other prompts themselves!
Tech Blog Dify.AI integrates Jina Embeddings for RAG Dify.AI, a leading open-source platform specialized in creating generative AI applications, is now leveraging Jina Embeddings v2!
Tech Blog Jina Embeddings v2 and MongoDB Atlas Supercharge MongoDB Atlas multi-cloud vector search solutions with Jina AI’s industry-leading embeddings!
Tech Blog SceneXplain's JSON Schema Store: Automate Your Alt-Text, and More! Take the hassle out of extracting data from images with SceneXplain's new JSON Schema Store. Discover and share reusable JSON schemas. Create, contribute, and access schemas easily through GUI or API
Tech Blog SceneXplain's OCR beats GPT-4V hands down: Chinese, Japanese, Korean, Arabic, Hindi, and more! SceneXplain beats GPT-4V by going beyond English, offering multilingual OCR for Chinese, Japanese, Korean, Arabic, Hindi and more
Tech Blog Embeddings in Depth This second article in our series on embedding technology is much more concrete. It explains where embeddings come from and how they are used.
Tech Blog Look, Up in the Sky! Using SceneXplain To Classify Land Use From Satellite Data Unlock the Secrets of the Satellites: Leverage SceneXplain's powerful 'Extract JSON from Image' feature for land use classification
Tech Blog Jina Embeddings 2: The Best Solution for Embedding Long Documents With Jina Embeddings 2 models you get high-quality embeddings from an open-source, downloadable model with an input size of 8,192 tokens.
Tech Blog How to Caption Image Segments with SceneXplain: Introducing Crop'n Explain SceneXplain: Precise image insights, webcam uploads, multi-API keys, and more user-friendly updates.
Tech Blog Are you ready for this Jelly? SceneXplain’s new algo kills hallucinations dead SceneXplain's state-of-the-art Jelly algorithm is more concise, readable and accurate than ever before, while killing hallucinations.
Tech Blog How Embeddings Drive AI: A Comprehensive Presentation Embeddings are a core concept and technology in AI, present in some form across the spectrum of AI applications. Properly understanding and mastering this technology positions you to leverage AI models to add the most value to your business.