skills.rest
ccf
ccfCOMMUNITY
Explore all skills by this author →
𝕏@cfigueirGitHub

embedding-strategies

Select and optimize embedding models for semantic search and RAG applications.

1|Updated Dec 23, 2025
Search Tags:#semantic search#embeddings#RAG#vector search#chunking#embed
One-click install
npx skills add https://github.com/ccf/claude-code-ccf-marketplace --skill embedding-strategies-ccf
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: embedding-strategies
Source: https://github.com/ccf/claude-code-ccf-marketplace/tree/main/plugins/llm-application-dev/skills/embedding-strategies
Command: npx skills add https://github.com/ccf/claude-code-ccf-marketplace --skill embedding-strategies-ccf

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Embedding strategies optimize semantic search quality and retrieval effectiveness by selecting suitable models, chunking strategies, and preprocessing steps for domain-specific data.

Core Features & Use Cases

  • Model comparison & selection: Compare embedding models by dimensionality, throughput, and accuracy to pick the best fit for your data.
  • Pipeline templates: End-to-end templates for OpenAI embeddings and local SentenceTransformer-based embeddings.
  • Chunking & preprocessing: Guidance on chunk size, overlap, and domain preprocessing to maximize retrieval performance.
  • Use Case: Build a RAG system over a codebase or knowledge corpus across multilingual content.

Quick Start

Start by selecting a target domain and documents, pick an embedding model (e.g., text-embedding-3-small or multilingual E5/BGE variants), configure a chunking strategy, and run embeddings to index your data.

Frequently Asked Questions about embedding-strategies

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I choose the right embedding model for semantic search?▼

To choose an embedding model for semantic search, compare options by dimensionality, throughput, and accuracy. Evaluate OpenAI embeddings or local SentenceTransformer models like multilingual E5 and BGE variants to find the best fit for your domain-specific data.

What is the best way to chunk documents for RAG applications?▼

The best way to chunk documents for RAG applications involves configuring chunk size and overlap based on your content structure. Apply domain-specific preprocessing pipelines to maximize retrieval performance and ensure precise semantic search results.

Can I use local SentenceTransformer models for multilingual semantic search?▼

Yes, you can use local SentenceTransformer models for multilingual semantic search. The pipeline supports multilingual E5 and BGE variants, allowing you to process and embed diverse language content efficiently without relying on external APIs.

How do I configure an embedding pipeline for a codebase?▼

Configuring an embedding pipeline for a codebase requires selecting a target domain, picking an embedding model, defining a chunking strategy, and running batch embeddings. This workflow indexes your code accurately for downstream RAG retrieval.

Does this embedding strategy support batch embedding workflows?▼

Yes, this embedding strategy supports batch embedding workflows. You can process large volumes of documents through configurable preprocessing pipelines, applying consistent chunking and embedding models to efficiently build your search index.

When should I apply domain-specific preprocessing before generating embeddings?▼

You should apply domain-specific preprocessing before generating embeddings when dealing with specialized content like code or multilingual text. Preprocessing optimizes the input data structure, directly maximizing retrieval performance and semantic search accuracy.

Related Skills

Explore More Data & Analytics Skills→
lttrlttr
4

pdf-to-markdown

Extract text from PDFs and save clean Markdown beside the source file.

Community
Intermediate
rukikotoorukikotoo
6

rag

Query the econometrics RAG knowledge base to retrieve relevant document chunks.

Community
Intermediate
patricio0312revpatricio0312rev
5

embedding-pipeline-builder

Automate document embedding pipelines for semantic search.

Community
Advanced
gqf2008gqf2008

qdrant-vector-search

Provides scalable vector similarity search with filtering for RAG applications.

Community
Advanced