weaviate-data-ingestion

Community

Streamline data uploads to Weaviate, effortlessly.

Authorsaskinosie
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Ingesting large volumes of diverse data (text, images, files) into a vector database can be time-consuming and complex, especially with requirements for intelligent chunking, multi-modal support, and robust error handling. This Skill automates the entire data upload process, saving you significant time and effort.

Core Features & Use Cases

  • Batch Uploads: Efficiently insert thousands of objects from various sources like JSON, CSV, or Python lists with progress tracking and error handling.
  • Multi-modal Support: Upload images (base64 encoded) into collections configured for visual search, enabling rich content indexing.
  • Intelligent Chunking: Automatically process and chunk large documents (e.g., PDFs, Markdown files) into semantically meaningful units, extracting relevant metadata for better search results.
  • Use Case: Import a folder of PDF technical manuals, have Claude intelligently chunk them by section, extract relevant metadata like page numbers and topics, and upload them to your Weaviate knowledge base for RAG.

Quick Start

Upload the attached 'products.json' file into my 'ProductCatalog' collection.

Dependency Matrix

Required Modules

weaviate-clienttqdmPyPDF2

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: weaviate-data-ingestion
Download link: https://github.com/saskinosie/weaviate-claude-skills/archive/main.zip#weaviate-data-ingestion

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository