rag-embedding-generation

Batch embedding generation with caching, rate limiting, and multiple provider support

509 stars

Best use case

rag-embedding-generation is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Batch embedding generation with caching, rate limiting, and multiple provider support

Teams using rag-embedding-generation should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/rag-embedding-generation/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/specializations/ai-agents-conversational/skills/rag-embedding-generation/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/rag-embedding-generation/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How rag-embedding-generation Compares

Feature / Agentrag-embedding-generationStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Batch embedding generation with caching, rate limiting, and multiple provider support

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# 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)

Related Skills

pdf-generation

509
from a5c-ai/babysitter

Professional PDF documentation generation. Convert Markdown to PDF with custom templates, styling, table of contents, cross-references, and optimized output for print and archival.

diagram-generation

509
from a5c-ai/babysitter

Multi-format diagram generation from text descriptions. Create Mermaid, PlantUML, D2, and Graphviz diagrams including flowcharts, sequence diagrams, architecture diagrams (C4), and data models.

test-data-generation

509
from a5c-ai/babysitter

Synthetic test data generation and management using Faker.js and similar tools. Generate realistic test data, create data factories, implement database seeding, and manage test data anonymization.

procedural-generation

509
from a5c-ai/babysitter

Procedural level generation skill for PCG algorithms.

specification-generation

509
from a5c-ai/babysitter

Convert requirements into structured technical specifications with architecture decisions

Epic Generation

509
from a5c-ai/babysitter

Transform PRD into a technical implementation plan with architecture decisions and dependency mapping.

code-generation

509
from a5c-ai/babysitter

Minimal, pattern-matching code output. Write the least code that satisfies requirements. Match existing project patterns. Use Write/Edit tools only.

process-builder

509
from a5c-ai/babysitter

Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.

Workflow & Productivity

babysitter

509
from a5c-ai/babysitter

Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)

yolo

509
from a5c-ai/babysitter

Run Babysitter autonomously with minimal manual interruption.

user-install

509
from a5c-ai/babysitter

Install the user-level Babysitter Codex setup.

team-install

509
from a5c-ai/babysitter

Install the team-pinned Babysitter Codex workspace setup.