Executes a semantic search on the specified table, allowing users to find the most relevant records based on a natural language query. This endpoint leverages vector-based retrieval to find similar results, making it ideal for question-answering and information discovery use cases. Provide your search phrase and other options (such as top_k and projection) in the request body to customize your search.
Bearer token authentication. Include the token in the Authorization header as 'Bearer
Semantic search request. It includes top_k, query, ef_search, projection.
The name of the vector column to search.
"embedding"
Query to run on Semantic Search
Number of top results to return from the semantic search. Must be greater than 0.
"5"
Size of the dynamic candidate list during search. A larger value will result in more accurate but slower searches.
x >= 0"1000"
SQL WHERE clause to filter the results. If not specified, no filtering will be applied. The filter condition must be a valid SQL expression that evaluates to a boolean value. For example: "text like '%hello%'" or "metadata like '%world%'"
"text like '%hello%'"
Columns to include in the result set. Uses SQL projection syntax (e.g. "col1, col2"). If not specified, all columns will be returned.
"text,metadata,distance"