vertex-ai

Introducing Vertex AI's New Text-Multilingual-Embedding-002 Model

Tal Peretz

Jun 27, 2024 — 1 min read

Vertex AI is excited to announce the public preview of its latest text embedding model, the text-multilingual-embedding-002. This model is packed with features designed to enhance text-based applications across a multitude of languages.

Multilingual Support

The text-multilingual-embedding-002 model has been evaluated on a wide array of languages, including Arabic, Bengali, English, Spanish, German, Persian, Finnish, French, Hindi, Indonesian, Japanese, Korean, Russian, Swahili, Telugu, Thai, Yoruba, and Chinese. Additionally, it supports an even broader range of languages, such as Afrikaans, Albanian, Amharic, Armenian, Azerbaijani, Basque, Belarusian, Bulgarian, Burmese, Catalan, Cebuano, Chichewa, Corsican, Czech, Danish, Dutch, Esperanto, Estonian, Filipino, Galician, Georgian, Greek, Gujarati, Haitian Creole, Hausa, Hawaiian, Hebrew, Hmong, Hungarian, Icelandic, Igbo, Irish, Italian, Javanese, Kannada, Kazakh, Khmer, Kurdish, Kyrgyz, Lao, Latin, Latvian, Lithuanian, Luxembourgish, Macedonian, Malagasy, Malay, Malayalam, Maltese, Maori, Marathi, Mongolian, Nepali, Norwegian, Pashto, and many more.

Flexible Dimensionality

This model offers flexible dimensionality, allowing users to select the number of dimensions according to their specific needs. This flexibility can help in optimizing storage and memory usage.

Top-Tier Performance

In terms of performance, the text-multilingual-embedding-002 model ranks among the top models on the Massive Text Embedding Benchmark (MTEB) leaderboard. This ensures that users can rely on its robust and efficient text embedding capabilities.

Easy to Use

Using this model is straightforward with the Vertex AI API or the Vertex AI SDK for Python. It supports up to 250 input texts per request in the us-central1 region and has a token limit of 2048 per input text.

For practical implementation, example code is available in the Vertex AI SDK for Python documentation, offering a step-by-step guide on how to embed texts using this powerful model.

These updates underscore the text-multilingual-embedding-002 model's enhanced capabilities and flexibility, making it an invaluable tool for diverse text-based applications across multiple languages.

Unleashing Creativity with Stability.SD3-Large-V1:0 on Amazon Bedrock

The advent of Stability.SD3-Large-V1:0, a revolutionary text-to-image model, marks a significant milestone in the realm of generative AI. Integrated into Amazon Bedrock, this model is designed to transform how digital assets are created, offering unparalleled performance and quality in image generation. Model Architecture and Performance At the heart

Unlocking the Potential of Bedrock/Meta-Textgeneration-Llama-2-7B with AWS SageMaker

The Bedrock/Meta-Textgeneration-Llama-2-7B is a cutting-edge Large Language Model (LLM) developed by Meta as part of the Llama 2 series. This series ranges from 7 billion to 70 billion parameters, with the 7B model offering a balance of size and capability. Its development involved Supervised Fine-Tuning (SFT) and Reinforcement Learning

Exploring Azure AI's Phi-3-Medium-128K-Instruct: A Revolutionary LLM

Azure AI's Phi-3-Medium-128K-Instruct is a breakthrough in the field of language models, bringing forth a dense decoder-only Transformer model with 14 billion parameters. This model, part of Microsoft's Phi-3 family, stands out for its impressive performance across a wide range of benchmarks, making it a go-to

Unlocking the Potential of Azure AI's Phi-3.5-MoE-Instruct: A New Era in Artificial Intelligence

The Azure AI Phi-3.5-MoE-Instruct model, a groundbreaking addition to Microsoft's Phi-3.5 series, is revolutionizing the landscape of artificial intelligence with its innovative architecture and impressive capabilities. Model Architecture At the heart of the Phi-3.5-MoE-Instruct is the Mixture-of-Experts (MoE) model architecture, which includes 16 experts, each