google-gemini-embeddings

Complete production-ready guide for Google Gemini embeddings API This skill provides comprehensive coverage of the gemini-embedding-001 model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. Install the Google Generative AI SDK: For TypeScript projects: Set your Gemini API key as an environment variable: Get your API key from: Result : A 768-dimension embedding vector representing the semantic meaning of the text. Current Model : gemini-embedding-001 (stable, production-ready) The model supports flexible output dimensionality using Matryoshka Representation Learning : Default : 3072 dimensions Recommended : 768, 1536, or 3072 for optimal performance RPM = Requests Per Minute TPM = Tokens Per Minute RPD = Requests Per Day Single text embedding : For Workers/edge environments without SDK support : ⚠️ CRITICAL : When using dimensions other than 3072, you MUST normalize embeddings before computing similarity. Only 3072-dimensional embeddings are pre-normalized by the API. Why This Matters : Non-normalized embeddings have varying magnitudes that distort cosine similarity calculations, leading to incorrect search results. Normalization Helper Function : Source : Official Embeddings Documentation Generate embeddings for multiple...