The request names sup-simcse-roberta-large, which is a sentence-embedding model rather than a product; the closest matching tooling is Sentence Transformers, which loads and trains embedding models of this kind 1, with Hugging Face hosting the models themselves and offering training and inference paths 2. Hosted embedding alternatives include OpenAI's embedding endpoint 3 and Replicate's hosted sentence-embedding models 4.
- 1
Sentence Transformerssbert.netverified and signed
A Python module (SBERT) for computing embeddings from text and training embedding models, which can load SimCSE-style RoBERTa sentence encoders 1.
official:SDK · sentence-transformers+24 community tools built for it
for agents: embedding · XLNet · deep
- 2
Hugging Facehuggingface.coverified and signed
Hosts the sup-simcse-roberta-large model and offers a train-sentence-transformers action for fine-tuning sentence-transformers models 2.
official:MCP server · @huggingface/mcp-clientSDK · huggingface-hubCLI · text-embeddings-inferencerepository · pwc-cliskill · hf-cli+23 community tools built for it
for agents: train-sentence-transformers · huggingface · models
- 3
OpenAI APIopenai.comverified and signed
Hosted API with a create_embedding action that turns text into vectors for semantic search, as an alternative to running the model yourself 3.
official:MCP server · mcp-extensionsAPI · OpenAI APISDK · openailibrary · OpenAICLI · openai-whisper+177 community tools built for it
for agents: create_embedding · createEmbedding · search_embeddings
- 4
Replicatereplicate.comverified and signed
Runs hosted open-source embedding models such as multilingual-e5-large through a cloud API 4.
+14 community tools built for it
for agents: beautyyuyanli/multilingual-e5-large · adirik/multilingual-e5-large · creatorrr/all-mpnet-base-v2
Sources
- 1SentenceTransformers Documentation — Sentence Transformers documentationsbert.net · read 2026-10-29
- 2Hugging Face – The AI community building the future.huggingface.co · read 2026-10-29
- 3babysit-pr — openai/codexskills.sh · read 2026-10-29
- 4Replicate - Run AI with an APIreplicate.com · read 2026-10-29
For agents: the 10 actions behind this answer
embedding · sentence-transformers verified and signed
train-sentence-transformers · train-sentence-transformers verified and signed
Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for two-stage retrieval / pair classification
create_embedding · OpenAI (Activepieces) verified and signed
Create Embedding — Turn text into a vector for semantic search or clustering.
beautyyuyanli/multilingual-e5-large · beautyyuyanli/multilingual-e5-large verified and signed
multilingual-e5-large: A multi-language text embedding model
model-recommendation · model-recommendation verified and signed
Analyze chatmode or prompt files and recommend optimal AI models based on task complexity, required capabilities, and cost-efficiency
supabase · supabase verified and signed
Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT
language-modeling · Llama-3.3-nemotron-super-49b-v1.5-PB-25h2 verified and signed
Task: Language Modeling
storing-and-querying-vectors · storing-and-querying-vectors verified and signed
Store and query vector embeddings using Amazon S3 Vectors, a cost-effective long-term vector storage service with its own API namespace (s3vectors). Triggers on: create S3 vector bucket, vector index, store embeddings, semantic search, RAG vector storage, similarity search, vector database, migrate
workers-ai-search-model · Cloudflare API verified and signed
Model Search
text · ebcdic verified and signed
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.