skills.rest
labrat-0
labrat-0COMMUNITY
Explore all skills by this author →
Website𝕏@shiftmickGitHub

rag-embedding-generator

Generate vector embeddings from text inputs using OpenAI or Cohere.

Updated Feb 14, 2026
Search Tags:#security#validation#rag#apify#vector#dataset#embedding
One-click install
npx skills add https://github.com/labrat-0/rag-embedding-generator --skill rag-embedding-generator
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-embedding-generator
Source: https://github.com/labrat-0/rag-embedding-generator/tree/main
Command: npx skills add https://github.com/labrat-0/rag-embedding-generator --skill rag-embedding-generator

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The RAG Embedding Generator converts raw text and chunked datasets into vector representations, enabling efficient retrieval in vector databases for RAG workflows, while preserving useful metadata for source attribution.

Core Features & Use Cases

  • Embeds a single text, a list of texts, or dataset chunks from RAG Content Chunker or Website Content Crawler.
  • Supports batched API requests to maximize throughput with OpenAI and Cohere, while maintaining controls on input size and errors.
  • Outputs embeddings with pass-through metadata (chunk_id, source_url, page_title, section_heading) ready for storage in Pinecone, Qdrant, Weaviate, Chroma, or similar vectors stores.
  • Quick Use Case: Transform a website's content into a searchable vector store for rapid retrieval in a knowledge base.

Quick Start

Run the actor with an API key and input (text, texts, or dataset_id) to generate embeddings and metadata for downstream storage.

Frequently Asked Questions about rag-embedding-generator

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

FAQPage Schema
How do I generate vector embeddings from text for a RAG pipeline?▼

To generate vector embeddings for a RAG pipeline, you can process a single text, a list of texts, or a dataset stream using OpenAI or Cohere. The output includes vectors and pass-through metadata like source URLs and page titles for downstream storage.

Does this embedding generator work with Website Content Crawler datasets?▼

Yes, the embedding generator works with Website Content Crawler datasets. It directly accepts dataset streams from the Website Content Crawler or RAG Content Chunker, embedding the chunked text while preserving metadata like chunk IDs and section headings.

Can I store the generated embeddings directly into vector databases like Pinecone or Qdrant?▼

Yes, you can store the generated embeddings in vector databases like Pinecone, Qdrant, Weaviate, or Chroma. The output is formatted with pass-through metadata including chunk IDs and source URLs, making it ready for immediate vector database ingestion.

How are API keys handled when generating embeddings with OpenAI or Cohere?▼

API keys are handled with strict security and validation to ensure they are not logged. Outbound requests are restricted exclusively to trusted OpenAI or Cohere provider endpoints, and all text inputs are sanitized before processing.

What is the best way to embed a large dataset of chunked website content into vectors?▼

The best way to embed large datasets is by using batched API requests to maximize throughput. The generator supports batched requests to OpenAI and Cohere while maintaining controls on input size and processing errors.

What metadata is preserved when converting text chunks into vector representations?▼

When converting text chunks into vector representations, the generator preserves pass-through metadata such as chunk IDs, source URLs, page titles, and section headings. This metadata enables efficient source attribution during retrieval.

Related Skills

Explore More Data & Analytics Skills→
kivo360kivo360
1

moai-essentials-refactor

Transform domain knowledge into vector embeddings for semantic retrieval.

Community
Intermediate
eyadsibaieyadsibai
7

vector-databases

Compare Chroma, FAISS, Qdrant, Pinecone, and Weaviate for vector database selection.

Community
Intermediate
mjunaidcamjunaidca
9

rag-ingestion-pipeline

Ingest MD, HTML, and PDF documents into RAG pipelines with hashing and chunking.

Community
Advanced
zepdbzepdb
43

zeppelin

Index and search text with Zeppelin vector store and BM25 full-text indexing.

Official
Advanced