MedCPT Query Encoder
MedCPT-Query-Encoder is a biomedical text embedding model hosted on Hugging Face. It belongs to the MedCPT suite released by the NLM/DIR BioNLP Group at NCBI and converts queries into vector representations for semantic retrieval applications.
The model is provided as a BERT-based transformer for feature extraction. It is distributed in PyTorch and Safetensors formats and supports text-embeddings-inference. Users load it through the Transformers library with either a high-level pipeline for feature extraction or direct instantiation of the AutoTokenizer and AutoModel classes. The repository includes example code for both approaches and references a Google Colab notebook for demonstration.
It carries a public-domain license. The underlying research appears in arXiv preprint 2307.00589. The page lists an introduction to MedCPT along with usage cases for the query encoder and semantic search over PubMed, though implementation details for those cases reside in linked notebooks rather than the model card itself.
The model targets developers and researchers integrating embedding-based search into biomedical systems. It is delivered exclusively as a downloadable model artifact on the Hugging Face platform.
Overview
3 featuresMedCPT Query Encoder is an Embeddings & retrieval project. It focuses on finding relevant biomedical literature by encoding queries into dense vector representations. MedCPT Query Encoder is an open-source project aimed at researchers. MedCPT Query Encoder is open source under the Open Source license. It runs on the web and API.
NCBI builds and maintains MedCPT Query Encoder. Among its 3 catalogued features are Text Embeddings, Semantic Search, and Biomedical Domain. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
- Text Embeddings
- Semantic Search
- Biomedical Domain
Built with & integrations
- AWS
- x-amz-cf-id header · x-amz-cf-pop header · via header
- meta_llama
- llama- in the HTML
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
- Indexed21 Jul · 16:32 UTCncbi/MedCPT-Query-Encoder verified against its public sourceSource: PulseGate · Open
Frequently asked questions about MedCPT Query Encoder
- What does MedCPT Query Encoder do?
- MedCPT Query Encoder focuses on finding relevant biomedical literature by encoding queries into dense vector representations. It is catalogued under Embeddings & retrieval on PulseGate.
- Who is MedCPT Query Encoder for?
- MedCPT Query Encoder is an open-source project built for researchers.
- Is MedCPT Query Encoder free?
- Yes — MedCPT Query Encoder is open source under the Open Source license and free to use.
- What platforms does MedCPT Query Encoder run on?
- MedCPT Query Encoder runs on the web and API.
- Is MedCPT Query Encoder still maintained?
- Unverified. MedCPT Query Encoder has not been re-checked since it entered the index, so there is no finding either way — and only a positive finding would say otherwise.
- Who makes MedCPT Query Encoder?
- MedCPT Query Encoder is developed by NCBI, based in the United States.
- Is MedCPT Query Encoder open source?
- Yes — MedCPT Query Encoder is open source under the Open Source license.
- Does MedCPT Query Encoder have an API or integrations?
- Yes — MedCPT Query Encoder exposes a public API.
Similar projects
Closest matches by what these projects do