NEWVectors or files. Pick a path.Start →
    Filter

    Query Expand

    Generate query variations with LLM and fuse search results via RRF

    Note: This playground provides simulated output to showcase functionality. No data is processed on our servers. Use this demo to explore the stage's configuration options before integrating it into your retriever pipeline.

    Configuration

    integer

    Number of query variations to generate (1-10). More = better recall but slower.

    string | null

    Custom prompt for query expansion. Use {{QUERY}} and {{NUM_EXPANSIONS}} placeholders.

    string

    LLM model for generating query expansions.

    object
    Required

    REQUIRED. Full feature_search configuration to execute for each expanded query.

    boolean

    Whether to include the original query in addition to expansions.

    integer

    RRF constant k. Higher values weight lower-ranked results more. Range: 1-1000.

    string

    Result fusion method: 'rrf' (recommended) or 'linear' (score averaging).

    boolean

    Whether to deduplicate results by document_id.

    Output

    No output yet

    Configure the stage parameters and click "Run Stage" to see the simulated output.