Embedding
Embedding
📖 定义
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.
🔗 在 Higress 中的应用
Higress supports unified proxying of Embedding APIs, can route requests to different embedding service providers, and supports semantic caching to reduce redundant computations.
💡 示例
- 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
🔄 相关术语
❓ 常见问题
Embedding 是什么？
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.
Higress 如何支持 Embedding？
Higress supports unified proxying of Embedding APIs, can route requests to different embedding service providers, and supports semantic caching to reduce redundant computations.
深入了解 Higress
探索更多 Higress 的功能和最佳实践