skills.rest
xberg-io
xberg-ioOFFICIAL
Explore all skills by this author →
Website𝕏@kreuzberg_devGitHub

embeddings-and-search

Generate embeddings, search the web, and process OCR via liter-llm's API.

26|2|Updated Jun 8, 2026
Search Tags:#embeddings#web search#OCR#text analysis#liter-llm
One-click install
npx skills add https://github.com/xberg-io/plugins --skill embeddings-and-search
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: embeddings-and-search
Source: https://github.com/xberg-io/plugins/tree/main/plugins/liter-llm/.cursor-plugin/skills/embeddings-and-search
Command: npx skills add https://github.com/xberg-io/plugins --skill embeddings-and-search

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires liter_llm, and includes scripts (resource) components.

What problem does it solve?

This Skill simplifies the process of generating embeddings, performing web searches, and conducting OCR on documents, streamlining tasks that require AI-powered text analysis.

Core Features & Use Cases

  • Embeddings Generation: Create embeddings for text data with support for various models.
  • Web Search: Access 12 web search providers for comprehensive search capabilities.
  • OCR Processing: Utilize 4 OCR providers to extract text from images and documents.
  • Reranking: Improve search results and document processing through reranking capabilities.
  • Use Case: If you need to analyze a large dataset of documents and want to quickly extract insights, this Skill can help you generate embeddings, perform searches, and process OCR text efficiently.

Quick Start

Generate embeddings for a text document using the embeddings-and-search skill with the command: embeddings-and-search generate-embeddings --text "Your text here" --model "model_name" --encoding "encoding_format" --dimensions "dimensions" --api_key "YOUR_API_KEY".

Frequently Asked Questions about embeddings-and-search

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

FAQPage Schema
How do I generate text embeddings for information retrieval?▼

To generate text embeddings, run the command with your text, desired model, encoding format, dimensions, and API key. It leverages liter-llm to create embeddings for information retrieval and content analysis.

Can I extract text from images using OCR processing?▼

Yes, you can extract text from images and documents using OCR processing. The skill utilizes 4 OCR providers to accurately process and extract text for your document analysis workflows.

Does this tool support multiple web search providers?▼

Yes, the web search functionality supports 12 different web search providers. This ensures comprehensive search capabilities for gathering information and analyzing text data across various sources.

Do I need API keys to use the embeddings and OCR features?▼

Yes, you must provide specific API keys to use the embeddings, web search, and OCR processing features. The tool requires these keys to authenticate with the respective service providers via liter-llm.

What is the best way to improve search results from document processing?▼

To improve search results from document processing, use the built-in reranking capabilities. Reranking enhances the accuracy of information retrieval and content analysis after generating embeddings or extracting OCR text.

Related Skills

Explore More Software Engineering Skills→
ricablericable
1

Claude Flow Embeddings

Generate vector embeddings from text using ONNX, OpenAI, and Transformers.js providers.

Community
Advanced
Kingly-AgencyKingly-Agency

rag-implementation

Build RAG pipelines that ground LLM responses with retrieved external knowledge.

Official
Advanced
ZardLi1115ZardLi1115
4

ocr-and-documents

Extract text from PDFs and scanned documents via OCR pipelines.

Community
Intermediate
walterrawalterra
58

searxng-search

Search and aggregate web results locally via SearXNG without external API keys.

Community
Intermediate