Create Vector Index

Currently only SPARSE_HNSW is supported for floating-point sparse vector. Users can check below example:

curl -u shiva:shiva -XPUT 'localhost:8902/hippo/v1/{table}/_create_embedding_index?pretty' -H 'Content-Type: application/json' -d'{  
  "field_name" : "book_intro",  
  "index_name" : "sparse_index",  
  "metric_type" : "ip",  
  "index_type": "SPARSE_HNSW",  
  "params": {  
    "M" : 8,  
    "ef_construction" : 64,  
    "norm_bm25" : false  
  }  
}';

"norm_bm25" represents whether to do BM25 normalization, defaults to true. When sparse vector comes from "splade", "norm_bm25" should be set to false.

Result:

{
  "acknowledged" : true
}