Vector Search
Hybrid KNN Search
Combines vector similarity with keyword matching for improved retrieval accuracy
Note: This playground provides simulated output to showcase functionality. No input data is processed or stored on our servers. Use this demo to explore the retriever's capabilities before integrating it into your application.
Try Hybrid KNN Search
Experiment with different inputs and parameters to see how this retriever works.
Input
Supported query types: text, embedding vector, number[]
5
70
Minimum confidence threshold for inclusion in results
Whether to include metadata in results
0.7
Weight of vector similarity component (0-1)
0.3
Weight of keyword matching component (0-1)
Results
No results yet
Configure the input parameters and click "Run Retriever" to see the search results.