skills.rest
akselikorhonen-siili
akselikorhonen-siiliCOMMUNITY
Explore all skills by this author →
GitHub

data-indexing

Index web pages and local files into ChromaDB using Gemini models.

Updated Apr 14, 2026
Search Tags:#indexing#knowledge management#semantic search#gemini#content processing#chromadb
One-click install
npx skills add https://github.com/akselikorhonen-siili/ai_training --skill data-indexing
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: data-indexing
Source: https://github.com/akselikorhonen-siili/ai_training/tree/main/.agents/skills/data-indexing
Command: npx skills add https://github.com/akselikorhonen-siili/ai_training --skill data-indexing

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires chromadb, google-genai, html2text, requests, python-dotenv, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables efficient indexing of web pages and local files into ChromaDB, facilitating fast and accurate semantic search capabilities.

Core Features & Use Cases

  • Content Processing: Uses Gemini models to process and embed document content for meaningful indexing.
  • Versatile Indexing: Supports URLs and local files, making it suitable for both web crawling and local data management.
  • Use Case: Upload a collection of research papers or web articles and perform semantic search queries to retrieve relevant information rapidly.

Quick Start

Use the data-indexing skill to index your local document file and prepare it for semantic search queries.

Frequently Asked Questions about data-indexing

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

FAQPage Schema
How do I index local files and web pages into ChromaDB for semantic search?▼

To index local files and web pages into ChromaDB for semantic search, this Skill processes document content and generates embeddings via Gemini models. It handles both URLs and local files for scalable document indexing.

Do I need a Gemini API key to generate embeddings for document indexing?▼

Yes, you need a Gemini API key to generate embeddings for document indexing. This Skill relies on Google GenAI models to process and embed your content, requiring valid API access configured in your environment.

Can I use this for indexing research papers and web articles for knowledge management?▼

Yes, you can use this for indexing research papers and web articles for knowledge management. It supports content organization and research workflows, enabling you to upload document collections and perform fast semantic search queries.

Does semantic search indexing with ChromaDB require a local database running?▼

Yes, semantic search indexing with ChromaDB requires a local database instance running. This Skill indexes documents into a ChromaDB instance hosted on localhost to store and retrieve your generated embeddings.

What is the best way to process HTML web pages for semantic search?▼

The best way to process HTML web pages for semantic search is to convert the HTML content to text using html2text, then generate embeddings with Gemini models before storing the vectors in ChromaDB. This Skill automates that extraction and indexing pipeline.

Related Skills

Explore More Data & Analytics Skills→
0xHoneyJar0xHoneyJar
1

loa-credentials

Manage API credentials across environment variables, encrypted stores, and dotenv files.

Official
Intermediate
akselikorhonen-siiliakselikorhonen-siili

semantic-search

Perform vector-based semantic search over indexed document collections.

Community
Intermediate
zeronx798zeronx798

chroma

Manage vector collections and perform similarity searches with metadata filtering.

Community
Intermediate
markus41markus41
1

vectordb

Manage vector embeddings for semantic search across Pinecone, Weaviate, Chroma, and pgvector.

Community
Intermediate