Cohere Embed v3 Multilingual
Version: 1
Cohere Embed Multilingual is the market’s leading multimodal (text, image) representation model used for semantic search, retrieval-augmented generation (RAG), classification, and clustering. Embed Multilingual supports 100+ languages and can be used to search within a language (e.g., search with a French query on French documents) and across languages (e.g., search with an English query on Chinese documents). This model was trained on nearly 1B English training pairs and nearly 0.5B Non-English training pairs from 100+ languages.
Content Filtering
Prompts and completions are passed through a default configuration of Azure AI Content Safety classification models to detect and prevent the output of harmful content. Learn more about Azure AI Content Safety . Configuration options for content filtering vary when you deploy a model for production in Azure AI; learn more .Embed multilingual has SOTA performance on multilingual benchmarks such as Miracl and the multilingual evaluation results can be found in the following Embed v3.0 Miracl Evaluation Results and full MTEB results can be found in the following Embed v3.0 MTEB Evaluation Results . Evaluations against multi-modal embedding models can be found in the following Embed v3.0 Multimodal Evaluation Results .
Model Specifications
Context Length512
LicenseCustom
Last UpdatedApril 2024
Input TypeText
Output TypeEmbeddings
PublisherCohere
Languages10 Languages