Query Expand
Generate query variations with LLM and fuse search results via RRF
Configuration
Number of query variations to generate (1-10). More = better recall but slower.
Custom prompt for query expansion. Use {{QUERY}} and {{NUM_EXPANSIONS}} placeholders.
LLM model for generating query expansions.
REQUIRED. Full feature_search configuration to execute for each expanded query.
Whether to include the original query in addition to expansions.
RRF constant k. Higher values weight lower-ranked results more. Range: 1-1000.
Result fusion method: 'rrf' (recommended) or 'linear' (score averaging).
Whether to deduplicate results by document_id.
Output
No output yet
Configure the stage parameters and click "Run Stage" to see the simulated output.
Related to query_expand
Pages on the same stages, extractors and patterns.
Feature Search
Search and filter documents by vector similarity using feature embeddings
Attribute Filter
Filter documents by metadata attribute values using boolean logic
Llm Filter
Filter documents using LLM-based semantic evaluation
Agent Search
LLM-driven multi-step retrieval with iterative reasoning and tool orchestration
Score Threshold
Drop results below an absolute score and return no results when nothing qualifies