SkillsAdd

zainhas/skills_draft · Archived

together-embeddings

Dense vector embeddings, semantic search, RAG pipelines, and reranking via Together AI.

First seen Feb 27, 2026

Installation

$ npx skills add zainhas/skills_draft --skill together-embeddings
View on skills.sh ↗ GitHub repository ↗

Summary

  • Dense vector embeddings, semantic search, RAG pipelines, and reranking via Together AI.
  • Generate embeddings with open-source models and rerank results behind dedicated endpoints.
  • Reach for it whenever the user needs vector representations or retrieval quality improvements rather than direct text generation.

Stronger alternatives

This repository is archived — consider an actively maintained alternative.

together-code-interpreter Same source · more installs
zainhas/skills_draft

Use this skill for Together AI Code Interpreter workflows: remote Python execution, session reu…

33 installs
together-images Same source · more installs
zainhas/skills_draft

Text-to-image generation and image editing via Together AI, including FLUX and Kontext models, …

15 installs
together-dedicated-endpoints Same source · more installs
zainhas/skills_draft

Single-tenant GPU endpoints on Together AI with autoscaling and no rate limits. Deploy fine-tun…

14 installs
together-audio Same source · more installs
zainhas/skills_draft

Text-to-speech and speech-to-text via Together AI, including REST, streaming, and realtime WebS…

14 installs

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

embeddings Similar name
ruvnet/ruflo

Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster wi…

1.2K installs
grepai-embeddings-ollama Similar name
yoanbernabeu/grepai-skills

Configure Ollama as embedding provider for GrepAI. Use this skill for local, private embedding …

661 installs
grepai-embeddings-lmstudio Similar name
yoanbernabeu/grepai-skills

Configure LM Studio as embedding provider for GrepAI. Use this skill for local embeddings with …

542 installs
grepai-embeddings-openai Similar name
yoanbernabeu/grepai-skills

Configure OpenAI as embedding provider for GrepAI. Use this skill for high-quality cloud embedd…

536 installs
google-gemini-embeddings Similar name
jezweb/claude-skills

Build RAG systems and semantic search with Gemini embeddings (gemini-embedding-001). 768-3072 d…

342 installs
clip-aware-embeddings Similar name
curiositech/some_claude_skills

Semantic image-text matching with CLIP and alternatives. Use for image search, zero-shot classi…

168 installs

Also in this package

Other skills from zainhas/skills_draft · top by installs.

npx skills add zainhas/skills_draft
together-code-interpreter 33 together-images 15 together-dedicated-endpoints 14 together-audio 14 together-chat-completions 13 together-video 12 together-evaluations 11 together-fine-tuning 11 together-batch-inference 10 together-gpu-clusters 10

Browse all from zainhas/skills_draft

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 2
License LICENSE
Default branch main
Open issues 0
Status Archived

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 3,905 B
  • docs SUMMARY.md 335 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 10 installs

SKILL.md

Together Embeddings & Reranking

Overview

Use this skill for semantic retrieval components:

  • create embeddings
  • batch embeddings
  • build retrieval or RAG pipelines
  • rerank retrieved candidates

This skill is for retrieval plumbing, not for the final language-model response itself.

When This Skill Wins

  • Build vector search or semantic similarity features
  • Add embedding generation to a data pipeline
  • Improve retrieval quality with reranking
  • Assemble a retrieval stage before calling a chat model

Hand Off To Another Skill

  • Use together-chat-completions for the final answer-generation step
  • Use together-batch-inference for very large offline embedding backfills
  • Use together-dedicated-endpoints when reranking requires a dedicated deployment

Quick Routing

  • Embeddings API usage

- Read [references/api-reference.md](references/api-reference.md) - Start with [scripts/embedandrerank.py](scripts/embedandrerank.py) or [scripts/embedandrerank.ts](scripts/embedandrerank.ts)

  • Semantic search (embed, store, query)

- Start with [scripts/semanticsearch.py](scripts/semanticsearch.py) -- includes an in-memory vector store, cosine-similarity retrieval, and optional rerank

  • RAG pipeline composition

- Start with [scripts/ragpipeline.py](scripts/ragpipeline.py)

  • Model selection and rerank constraints

- Read [references/models.md](references/models.md)

Workflow

  1. Confirm that the user needs vectors or retrieval, not direct generation.
  2. Choose the embedding model and batch shape.
  3. Generate embeddings for corpus and query paths consistently.
  4. Retrieve candidates. An in-memory cosine-similarity store works for prototyping and small corpora (see semantic_search.py). Use a dedicated vector database for production scale.
  5. Rerank only when the extra latency and endpoint requirement are justified. When no dedicated rerank endpoint is available, cosine-similarity ranking is a reasonable fallback.

High-Signal Rules

  • Python scripts require the Together v2 SDK (together>=2.0.0). If the user is on an older version, they must upgrade first: uv pip install --upgrade "together>=2.0.0".
  • Keep embeddings and reranking conceptually separate; rerank is a second-stage precision step.
  • Reranking in this repo assumes a dedicated endpoint. Do not promise serverless rerank unless the product changes. When no endpoint is available, fall back to cosine-similarity ranking.
  • The embedding model has a 514-token context limit. Chunk longer documents before embedding.
  • The rag_pipeline.py example demonstrates retrieval plus generation; treat generation as a hand-off to chat completions.
  • Preserve model consistency across indexing and querying.

Resource Map

  • API details: [references/api-reference.md](references/api-reference.md)
  • Model guide: [references/models.md](references/models.md)
  • Python embeddings example: [scripts/embedandrerank.py](scripts/embedandrerank.py)
  • TypeScript embeddings example: [scripts/embedandrerank.ts](scripts/embedandrerank.ts)
  • Python semantic search: [scripts/semanticsearch.py](scripts/semanticsearch.py)
  • Python RAG pipeline: [scripts/ragpipeline.py](scripts/ragpipeline.py)

Official Docs