Vector Search on Google Cloud
In this chapter, we’ll dive deep into vector search, a very important pattern of modern information retrieval and generative AI applications.
We will explore the architecture of a vector search pipeline and discuss different search techniques, examining their strengths and weaknesses.
Finally, we’ll shift our focus to practical implementation, showcasing how we can harness the combined power of Google Cloud and LangChain to develop retrieval-augmented generation (RAG) applications with vector search tailored for a variety of real-world scenarios and requirements.
In this chapter, we cover the following topics:
- What is vector search?
- LangChain interfaces – embeddings and vector stores
- Vector store with Vertex AI vector search
- Vector store with pgvector on Cloud SQL
- Vector store with BigQuery
