agentsclimarketplace
Sign in

Rag embedding generation

Skill a5c-ai/babysitter/library/specializations/ai-agents-conversational/skills/rag-embedding-generation

Batch embedding generation with caching, rate limiting, and multiple provider supportFrom its SKILL.md

Install
npx -y skills add a5c-ai/babysitter --skill rag-embedding-generation

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

1.6 KB, 244 tokens by cl100k_base, as published. Nobody here has run it

RAG Embedding Generation Skill

Capabilities

  • Generate embeddings with multiple providers
  • Implement batch processing for large datasets
  • Configure caching for embedding reuse
  • Handle rate limiting and retries
  • Support various embedding models
  • Implement embedding quality validation

Target Processes

  • rag-pipeline-implementation
  • vector-database-setup

Implementation Details

Embedding Providers

  1. OpenAI Embeddings: text-embedding-ada-002, text-embedding-3-*
  2. HuggingFace: sentence-transformers models
  3. Cohere: embed-v3 models
  4. Voyage AI: voyage-2 models
  5. Local Models: GGUF/ONNX embedding models

Configuration Options

  • Model selection and parameters
  • Batch size optimization
  • Cache backend configuration
  • Rate limit settings
  • Retry policies
  • Dimensionality settings

Best Practices

  • Use appropriate model for domain
  • Implement caching for cost reduction
  • Monitor embedding quality
  • Handle API errors gracefully

Dependencies

  • langchain-openai / langchain-huggingface
  • numpy
  • Caching backend (Redis, SQLite)

What ships with it: 1 file

582 B alongside SKILL.md

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.