Vector Search Python SDK example usage
This notebook shows how to use the Vector Search Python SDK, which provides a VectorSearchClient as a primary API for working with Vector Search.
Alternatively, you can call the REST API directly.
Requirements
This notebook assumes that a Model Serving endpoint named databricks-bge-large-en exists. To create that endpoint, see the "Vector Search foundational embedding model (BGE) Example" notebook (AWS|Azure).
Load toy dataset into source Delta table
The following creates the source Delta table.
Create vector search endpoint
Create vector index
Get a vector index
Use get_index() to retrieve the vector index object using the vector index name. You can also use describe() on the index object to see a summary of the index's configuration information.
Similarity search
Query the Vector Index to find similar documents.
Convert results to LangChain documents
The first column retrieved is loaded into page_content, and the rest into metadata.