Semantic Filtering
Filter results
Filter & optionally observe top 100-200 results from your existing pipeline
POST
If you want to observe your pipeline wihtout changing behavior, check out the /observe endpoint
Authorizations
Body
application/json
Name of the object key to be used as the ID field for each document passed into the scoring system. Default is "id"
Total number of results returned by the filter
Wether or not to run the observability pipeline on this query
Number of plain text results to be passed to the last step of our at the end of our scoring system
Name of the object key to the metadata field of each document being passed in. Default is "metadata"
Query that was initally passed into your pipeline
Field to be filtered on, default is "text"
Number of vector results to be passed to the last step of our scoring system