rag-reranking

Cross-encoder reranking and MMR diversity filtering for improved retrieval quality

509 stars

bya5c-ai

View on GitHub Installation ↓

Best use case

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

Cross-encoder reranking and MMR diversity filtering for improved retrieval quality

Teams using rag-reranking 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-reranking/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/specializations/ai-agents-conversational/skills/rag-reranking/SKILL.md"

Manual Installation

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

How rag-reranking Compares

Feature / Agent	rag-reranking	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Cross-encoder reranking and MMR diversity filtering for improved retrieval quality

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 Reranking Skill

## Capabilities

- Implement cross-encoder reranking models
- Configure Maximal Marginal Relevance (MMR) filtering
- Set up Cohere Rerank integration
- Design multi-stage retrieval pipelines
- Implement diversity-aware reranking
- Configure score normalization and thresholds

## Target Processes

- advanced-rag-patterns
- rag-pipeline-implementation

## Implementation Details

### Reranking Methods

1. **Cross-Encoder Reranking**: Sentence-transformer cross-encoders
2. **Cohere Rerank**: Cohere rerank-v3 API
3. **MMR Reranking**: Diversity-aware result filtering
4. **LLM Reranking**: Using LLM for relevance scoring
5. **Reciprocal Rank Fusion**: Combining multiple retrievers

### Configuration Options

- Reranking model selection
- Top-k after reranking
- MMR lambda (relevance vs diversity)
- Score threshold filtering
- Batch size for reranking

### Best Practices

- Use cross-encoders for quality
- Balance relevance and diversity
- Set appropriate thresholds
- Monitor reranking latency

### Dependencies

- sentence-transformers
- cohere (optional)

Related Skills

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.)