Google Launches Gemini Embedding Model for Enhanced Text Processing

Google has launched the Gemini Embedding model, now available in the Gemini API, announced on their website. This model is designed to enhance text processing tasks, including Retrieval-Augmented Generation (RAG), classification, and search.

The Gemini Embedding model is noted for its versatility and power, achieving top scores on the Massive Text Embedding Benchmark (MTEB) leaderboard. It supports over 100 languages and offers a controllable embedding size, priced at $0.15 USD per million tokens.

Users can generate text embeddings using the `embed_content` method, which allows for the creation of embeddings for words, phrases, sentences, and code. These embeddings are crucial for tasks such as semantic search, classification, and clustering, providing more accurate and context-aware results than traditional keyword-based approaches.

For enterprise-grade applications, the model is also available on Vertex AI, offering optimized performance for high-volume workloads. The Gemini Embedding model's introduction marks a significant advancement in Google's AI capabilities, providing developers with powerful tools for a wide range of natural language processing tasks.