Stats
Actions
Tags
From togetherai-skills
Generates dense vector embeddings, performs semantic search, builds RAG pipelines, and reranks results via Together AI. Use for retrieval plumbing before the generation step.
How this skill is triggered — by the user, by Claude, or both
Slash command
/togetherai-skills:together-embeddingsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill for semantic retrieval components:
Use this skill for semantic retrieval components:
This skill is for retrieval plumbing, not for the final language-model response itself.
together-chat-completions for the final answer-generation steptogether-batch-inference for very large offline embedding backfillstogether-dedicated-endpoints when reranking requires a dedicated deploymentsemantic_search.py). Use a dedicated vector database for production scale.together>=2.0.0). If the user is on an older version, they must upgrade first: uv pip install --upgrade "together>=2.0.0".rag_pipeline.py example demonstrates retrieval plus generation; treat generation as a hand-off to chat completions.npx claudepluginhub togethercomputer/skills --plugin togetherai-skillsGuides selection and optimization of embedding models for vector search and RAG, including model comparisons, chunking strategies, dimension reduction, and Python templates for OpenAI and local models.
Guides selection and optimization of embedding models for vector search, including chunking, dimension reduction, and multilingual support.
Build RAG systems for LLM apps using vector databases, embeddings, and retrieval strategies. Use for document Q&A, grounded chatbots, and semantic search.