semantic-search

Perform vector-based semantic search over indexed document collections.

Updated Apr 14, 2026

Search Tags:#semantic search #vector embeddings #information lookup #document retrieval #ai search

Ready to run

npx skills add https://github.com/akselikorhonen-siili/ai_training --skill semantic-search-akselikorhonen-siili

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: semantic-search
Source: https://github.com/akselikorhonen-siili/ai_training/tree/main/.agents/skills/semantic-search
Command: npx skills add https://github.com/akselikorhonen-siili/ai_training --skill semantic-search-akselikorhonen-siili

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires chromadb, google-genai, ollama, python-dotenv, and includes scripts (resource) components.

What problem does it solve?

This Skill enables efficient retrieval of relevant information from large document repositories by performing semantic searches over vector embeddings.

Core Features & Use Cases

Semantic Search: Find documents or information that match a user's query based on meaning rather than exact keywords.
Flexible Filtering: Apply metadata filters to narrow down search results in specific collections or topics.
Use Case: A developer needs to quickly locate relevant tech articles from a repository by describing the topic in natural language.

Quick Start

Use the semantic-search skill to find documents related to "API authentication" in your database.

Frequently Asked Questions about semantic-search

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

FAQPage Schema

How does semantic search retrieve documents based on meaning rather than exact keywords?▼

Semantic search retrieves documents by converting text into vector embeddings and matching query vectors to contextually relevant information in indexed collections, enabling meaning-based information lookup rather than exact keyword matching.

Do I need a running ChromaDB instance to perform vector-based document retrieval?▼

Yes, you need a running ChromaDB instance to perform vector-based document retrieval. This Skill depends on ChromaDB to store and query vector embeddings generated via the gemini-embedding-001 or Ollama models.

Can I apply metadata filters to narrow down semantic search results in specific collections?▼

Yes, you can apply metadata filters to narrow down semantic search results. This allows you to restrict information lookup to specific topics or document collections within your research database.

What is the best way to find relevant tech articles in a repository using natural language queries?▼

The best way to find relevant tech articles is using vector-based semantic search over indexed document repositories. You describe the topic in natural language, and the system retrieves contextually relevant documents.

Does this semantic search approach work with Ollama embeddings and Google Gemini models?▼

Yes, this semantic search approach works with Ollama embeddings and the Google genai gemini-embedding-001 model. It uses these dependencies to generate vector embeddings for retrieving contextually relevant information.