Sold by: Upstage
Deployed on AWS
Free Trial
A compact multilingual model optimized for retrieval, delivering strong Korean and English RAG performance with a 32K context window.
Overview
Embedding 2 is a compact yet powerful multilingual embedding model purpose-built for retrieval. Fine-tuned for Retrieval-Augmented Generation (RAG), it delivers strong search accuracy in Korean and English while remaining far smaller than previous-generation embedding models, enabling lower-cost, higher-throughput serving.
Compact and Efficient: At a fraction of the size of prior embedding models, it loads with minimal GPU memory and serves at low latency, making large-scale retrieval more cost-effective without sacrificing quality.
Optimized for Retrieval & RAG: Trained specifically on the retrieval task with dedicated query and passage encoding, it maximizes the precision and recall of the document search at the heart of RAG pipelines.
Long-Context, Multilingual: With a 32K-token context window and robust performance across Korean, English, and beyond, it handles long passages and multiple languages in a single model.
Highlights
- Optimized for Retrieval & RAG: Dedicated query and passage encoding maximizes search precision and recall, directly improving the accuracy of Retrieval-Augmented Generation (RAG) pipelines.
- Multilingual with Long Context: Strong retrieval performance across Korean and English, paired with a 32K-token context window to handle long passages and multiple languages in a single model.
- Key Tasks: Retrieval-Augmented Generation - Semantic Search - Passage Retrieval - Multilingual Search - Text Embeddings
Details
Sold by
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Free trial
Try this product free for 7 days according to the free trial terms set by the vendor.
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.g6.2xlarge Inference (Batch) Recommended | Model inference on the ml.g6.2xlarge instance type, batch mode | $3.00 |
ml.g6e.2xlarge Inference (Real-Time) Recommended | Model inference on the ml.g6e.2xlarge instance type, real-time mode | $3.00 |
ml.g6.12xlarge Inference (Batch) | Model inference on the ml.g6.12xlarge instance type, batch mode | $3.00 |
ml.g6.12xlarge Inference (Real-Time) | Model inference on the ml.g6.12xlarge instance type, real-time mode | $3.00 |
ml.g6.16xlarge Inference (Batch) | Model inference on the ml.g6.16xlarge instance type, batch mode | $3.00 |
ml.g6.16xlarge Inference (Real-Time) | Model inference on the ml.g6.16xlarge instance type, real-time mode | $3.00 |
ml.g6.24xlarge Inference (Batch) | Model inference on the ml.g6.24xlarge instance type, batch mode | $3.00 |
ml.g6.24xlarge Inference (Real-Time) | Model inference on the ml.g6.24xlarge instance type, real-time mode | $3.00 |
ml.g6.2xlarge Inference (Real-Time) | Model inference on the ml.g6.2xlarge instance type, real-time mode | $3.00 |
ml.g6.48xlarge Inference (Batch) | Model inference on the ml.g6.48xlarge instance type, batch mode | $3.00 |
Vendor refund policy
Contact us for refund inquiries. https://www.upstage.ai/contact-us?utm_source=marketplace
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
Initial release of Embedding 2 model
Additional details
Inputs
- Summary
Provide input data in JSON request body. The model field selects one of two specialized aliases:
- embedding-query — for embedding the user's search query
- embedding-passage — for embedding documents to be retrieved
The input field accepts a single string or an array of strings.
Request body format: {"model": "embedding-query" | "embedding-passage", "input": "" | ["", ...]}
- Input MIME type
- application/json, application/jsonlines
"How is the performance of Solar embeddings?"
Please see the batch transform section of the sample notebook.
Resources
Vendor resources
Support
Vendor support
Contact us for model, usage and enterprise integration inquiries.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
A state-of-the-art legal embedding model optimized for semantic search, RAG, and document classification, ranked first on the Massive Legal Embedding Benchmark.
QNX® Hypervisor 2.2 - the industry-leading hypervisor for developing mission-critical embedded systems software, enabling next-generation products in every industry where reliability matters, including automotive, medical devices, robotics, transportation and industrial embedded systems.
Best-in-class legal enrichment, reranking, and embedding models, optimized for legal knowledge graphs and legal RAG.
Embed 4 transforms multiple modalities, such as texts and images, into numerical vectors.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.