Implements Google Gemini embeddings API for high-performance RAG and semantic search applications.
This skill streamlines the integration of Google's gemini-embedding-001 model into your development workflow, providing standardized patterns for generating high-quality vector embeddings. It covers essential production requirements including Matryoshka representation learning for flexible dimensions (768 to 3072), task-specific optimization for queries versus documents, and robust error handling for rate limits and text truncation. Ideal for developers building RAG systems, semantic search engines, or document clustering tools, it ensures implementation consistency across different environments like Node.js and Cloudflare Workers.
Key Features
01Cloudflare Workers and Vectorize integration patterns
02Automatic handling of the 2,048 token input limit via chunking
0321 GitHub stars
04Specialized task types for optimized search and classification results
05Flexible dimensionality (768, 1536, 3072) using Matryoshka learning
06Production-ready batch processing with exponential backoff
Use Cases
01Automating document clustering and topic modeling
