Sold by: Instituto Ingenieria Conocimiento
Deployed on AWS
Free Trial
Rigoembeddings is a text embedding model that excels in Spanish. It ensures that similar sentences are close in vector space
Overview
With extensive experience in developing natural language processing (NLP) products and services in Spanish, from the Instituto de Ingeniería del Conocimiento (IIC), we want to share our knowledge with the rest of the world by making available the best NLP assets in our language. The Rigo family is a set of specialized NLP services in Spanish that have been packaged and tested with the IIC quality seal.
Rigoembeddings is a text embedding model in Spanish that excels in its accuracy and ability to capture the semantic meaning of words in various contexts. It can be used as a building block for advanced NLP applications and benefits across a wide range of fields. The main applications of this model include NLP, where it enhances text comprehension and generation, facilitating the creation of chatbots, Retrieval-Augmented Generation (RAG), virtual assistants, and recommendation systems among others.
Highlights
- Despite the existence of numerous multilingual embedding models, the vast majority are primarily focused on English, leaving a significant gap in quality and accuracy for other languages. In response to this need, **we have developed a specialized embedding model for Spanish**, designed to capture the nuances and particularities of our language. This specialization allows us to offer a significant advantage over other embedding models, **providing a more precise and efficient understanding and representation of Spanish** in various linguistic and technological applications.
- Rigoembeddings has been specifically specialized for the Spanish language. We conducted an extensive evaluation using a curated Spanish version of the MTEB (Massive Embedding Text Benchmark). The **results of this evaluation underscore Rigoembeddings' superior performance**, particularly on the Spanish version of the MASSIVE dataset. This demonstrates Rigoembeddings' robustness and effectiveness in handling Spanish textual data, making it a valuable tool for applications requiring high-quality Spanish language embeddings.
- Text Classification, Sentiment Analysis, Topic Detection, Spam Detection, Machine Translation, Information Retrieval, Search Engines, Question Answering Systems, Named Entity Recognition (NER), Text Summarization, Automated Writing Assistance, Chatbots and Conversational Agents, Text Similarity and Clustering, Document Similarity, Paraphrase Detection, Language Modeling, Predictive Text, Autocomplete Systems, Recommendation Systems, Speech Recognition, Plagiarism Detection, Ad Placement and Targeting, Content Moderation, Document Tagging and Categorization, Social Media Monitoring
Details
Delivery method
Latest version
Deployed on AWS
Unlock automation with AI agent solutions
Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.
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 5 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.g4dn.2xlarge Inference (Real-Time) Recommended | Model inference on the ml.g4dn.2xlarge instance type, real-time mode | $0.523 |
ml.g5.2xlarge Inference (Batch) Recommended | Model inference on the ml.g5.2xlarge instance type, batch mode | $0.842 |
ml.g4dn.4xlarge Inference (Batch) | Model inference on the ml.g4dn.4xlarge instance type, batch mode | $0.835 |
ml.g4dn.8xlarge Inference (Batch) | Model inference on the ml.g4dn.8xlarge instance type, batch mode | $1.511 |
ml.g4dn.12xlarge Inference (Batch) | Model inference on the ml.g4dn.12xlarge instance type, batch mode | $2.717 |
ml.g5.8xlarge Inference (Batch) | Model inference on the ml.g5.8xlarge instance type, batch mode | $1.222 |
ml.g5.12xlarge Inference (Batch) | Model inference on the ml.g5.12xlarge instance type, batch mode | $1.472 |
ml.g4dn.xlarge Inference (Batch) | Model inference on the ml.g4dn.xlarge instance type, batch mode | $0.366 |
ml.g4dn.2xlarge Inference (Batch) | Model inference on the ml.g4dn.2xlarge instance type, batch mode | $0.523 |
ml.g5.4xlarge Inference (Batch) | Model inference on the ml.g5.4xlarge instance type, batch mode | $1.014 |
Vendor refund policy
No refunds
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
We have updated the model inference endpoint with several security and performance patches.
Additional details
Inputs
- Summary
The embeddings model accepts as input a JSON object containing a list of texts.
{"inputs": ["Esta es una frase de ejemplo", "Cada frase tiene su vector", "El modelo se encarga de todo"]}
- Input MIME type
- application/json
https://github.com/iiconocimiento/iic-aws/blob/main/notebooks/rigoembeddings/data/input/embeddings_input.json
https://github.com/iiconocimiento/iic-aws/blob/main/notebooks/rigoembeddings/data/input/embeddings_input.json
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
inputs | A list of strings to be embedded by the model. | Each text must be under 512 tokens. | Yes |
Resources
Vendor resources
Support
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.
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.