Embedding
Embedding
📖 Definition
Embedding is a technique for converting data such as text and images into high-dimensional vectors. These vectors can capture semantic information of the data, making semantically similar content close in vector space, which is the foundation for semantic search and RAG.
🔗 How Higress Uses This
Higress supports unified proxying of Embedding APIs, can route requests to different embedding service providers, and supports semantic caching to reduce redundant computations.
💡 Examples
- 1 OpenAI text-embedding-ada-002 is a commonly used text embedding model
- 2 Vector databases use Embeddings to implement similarity search
- 3 Semantic caching determines cache hits through embedding similarity
🔄 Related Terms
❓ FAQ
What is Embedding?
Embedding is a technique for converting data such as text and images into high-dimensional vectors. These vectors can capture semantic information of the data, making semantically similar content close in vector space, which is the foundation for semantic search and RAG.
How does Higress support Embedding?
Higress supports unified proxying of Embedding APIs, can route requests to different embedding service providers, and supports semantic caching to reduce redundant computations.
Learn More About Higress
Explore more Higress features and best practices