skills.rest
kreuzberg-dev
kreuzberg-devOFFICIAL
Explore all skills by this author →
WebsiteGitHub

chunking-embeddings

Create text chunks and FastEmbed vector embeddings for RAG pipelines.

8.9k|539|Updated Jan 31, 2025
Search Tags:#embeddings#rag#nlp#chunking#text-processing#onnx#fastembed
One-click install
npx skills add https://github.com/kreuzberg-dev/kreuzberg --skill chunking-embeddings
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: chunking-embeddings
Source: https://github.com/kreuzberg-dev/kreuzberg/tree/main/.ai-rulez/skills/chunking-embeddings
Command: npx skills add https://github.com/kreuzberg-dev/kreuzberg --skill chunking-embeddings

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Chunking and embeddings automate creating text chunks and vector representations for RAG pipelines.

Core Features & Use Cases

  • Chunking strategies: Fixed-Size, Semantic, Syntax-Aware, Recursive
  • Embedding with FastEmbed (ONNX) and configurable presets
  • RAG pipeline integration for end-to-end document processing and retrieval

Quick Start

Run the chunking-embeddings skill on a document to generate chunked text and embeddings for your RAG index.

Frequently Asked Questions about chunking-embeddings

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

FAQPage Schema
How do I chunk text and generate embeddings for a RAG pipeline?▼

To chunk text and generate embeddings for a RAG pipeline, you can automate creating text chunks and vector representations. This workflow preprocesses diverse document corpora including code, articles, and manuals for semantic search and retrieval.

What chunking strategies work best for preparing documents for semantic search?▼

Chunking strategies for semantic search include Fixed-Size, Semantic, Syntax-Aware, and Recursive options. These methods enable preprocessing diverse document corpora into text chunks optimized for retrieval and knowledge bases.

Can I use FastEmbed with ONNX to generate text embeddings for RAG?▼

Yes, you can use FastEmbed with ONNX to generate text embeddings for RAG. The workflow integrates FastEmbed ONNX-based embeddings and supports configurable presets to produce vector representations for your RAG index.

Does the chunking and embedding workflow support processing code and technical manuals?▼

Yes, the chunking and embedding workflow supports processing code and technical manuals. It applies to diverse document corpora including code, articles, and manuals, enabling preprocessing for semantic search and knowledge bases.

What is the best way to automate creating text chunks and vector embeddings?▼

The best way to automate creating text chunks and vector embeddings is using a chunking and embedding workflow. It implements multiple chunking strategies and integrates with FastEmbed ONNX-based embeddings for end-to-end RAG document processing.

Related Skills

Explore More Software Engineering Skills→
mosheshammoshesham

rag-architect

Design and optimize production-grade RAG pipelines for document-heavy domains.

Community
Advanced
DhumitechDhumitech

rag-engineer

Build retrieval-augmented generation systems with semantic chunking and vector search.

Community
Advanced
qodex-aiqodex-ai
39

rag-agent-builder

Build RAG applications with vector databases, embeddings, and retrieval strategies.

Official
Advanced
ccfccf

embedding-strategies

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

Community
Intermediate