Milvus EnsembleQuery pipeline stage configuration specifications
|
|
The Milvus Ensemble stage is deprecated in Managed Fusion 5.9.5. Use Seldon or Lucidworks AI vector query stages instead.
|
The Milvus Ensemble Query stage performs ensemble of different search results to retrieve metadata from Solr (see Milvus documentation).
|
|
When entering configuration values in the UI, use unescaped characters, such as \t for the tab character. When entering configuration values in the API, use escaped characters, such as \\t for the tab character.
|
Performs ensemble of different search results to retrieve metadata from Solr. This stage is deprecated and will be removed in a future release. Please use the Solr dense vectors and associated Vectorize and Hybrid Query stages instead.
skip - boolean
Set to true to skip this stage.
Default: false
label - string
A unique label for this stage.
<= 255 characters
condition - string
Define a conditional script that must result in true or false. This can be used to determine if the stage should process or not.
ensembleExpression - stringrequired
Can reference results (numeric_id, score) map objects by key in the context, as well as max_[context key], min_[context key], count_[context key] etc.
>= 1 characters
Default: 1.0 * milvus_results
resultFieldName - stringrequired
Field name to store result ensemble score
>= 1 characters
Default: ensemble_score
threshold - number
Only documents with scores greater than or equal to the threshold will be returned
failOnError - boolean
Flag to indicate if this stage should throw an exception if an error occurs.
Default: false