Sold by: NYSgpt
Deployed on AWS
Biomedical text embeddings for semantic search and RAG. Fine-tuned from bge-m3 on bioRxiv and medRxiv; outperforms NLM MedCPT on retrieval.
Overview
A dense retrieval encoder for biomedical text, fine-tuned from BAAI/bge-m3 on bioRxiv and medRxiv preprints. It maps queries, abstracts and passages to 1,024-dimension normalized embeddings for semantic search, retrieval-augmented generation and similarity analysis over life-sciences literature.
Performance
On a frozen, leakage-audited benchmark (MeSH concept queries searched against 433,449 preprints), it outperforms the US National Library of Medicine's MedCPT encoder: Recall@10 0.524 vs 0.457 (+15%, paired p = 1e-6), trained on roughly 2,500x less data. It also scores +83% over its base model and +49% over allenai/specter2_base on the same queries.
Input and output
Input: application/json {"inputs": ["text", ...]} or text/plain, one text per line. Output: {"embeddings": [[...1024 floats...]], "dimensions": 1024}.
Runs entirely in your account
CPU inference on ml.m5 and ml.c5 instances; no data leaves your AWS account. Model card: https://huggingface.co/NYSgpt/biomed-encoder
Highlights
- Outperforms NLM MedCPT on biomedical concept search (Recall@10 0.524 vs 0.457, +15%)
- 1,024-dimension normalized embeddings, JSON or plain-text input
- CPU inference; your data never leaves your AWS account
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
This product is available free of charge. Free 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.
Vendor refund policy
This product is free; there are no software charges to refund. AWS infrastructure charges are billed by AWS. Contact Brendan@nysgpt.com with any issue.
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 the NYSgpt Biomedical Encoder.
Additional details
Inputs
- Summary
Biomedical text to embed: queries, abstracts or passages. JSON {"inputs": ["text", ...], "normalize": true} or text/plain with one text per line.
- Limitations for input type
- Inputs longer than 8,192 tokens are truncated.
- Input MIME type
- application/json, text/plain
{"inputs": ["CRISPR knockout screen identifies regulators of T cell exhaustion"]}
https://github.com/nyd-user-1/biomed-encoder-sagemaker/blob/main/data/sample-input.json
Support
Vendor support
Support by email from the publisher (Brendan@nysgpt.com ); typical response within one business day. Usage notebook:
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
This listing consists of a dataset containing the complete Electronic Medical Records related to sore throat related disease conditions over 1000 patients within the United States. The data is simulated based on clinical knowledge and census demographics.
Rapidly validate Claude or other LLM workflows in GxP/HIPAA environments. Includes SOP templates, prompt-safety guidelines, and AWS audit logging recipes.
Machine Learning model to predict the Adverse Drug Reactions.
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.