Tackle complex research questions with AI-guided iterative searching
How Agentic Search Works
Use Cases for Agentic Search
seed_strategy
parameter determines how initial search queries are generated:
Combines vector and keyword search approaches for balanced results. Best for general-purpose searching across diverse document collections.
Uses top-K retrieval, focusing on the most similar documents by vector similarity. Better for specialized document collections with consistent terminology.
alpha
parameter (0.0-1.0) balances vector search vs. keyword search weights:
Enable Presence/Frequency Penalty Tuning
Enable Temperature/Top-P Tuning
Ask Specific Queries
Provide Context When Relevant
Monitor and Adjust Iterations
initial_seed_multiplier
max_iterations
alpha
for more semantic search weightThe Agentic Search tool shines for complex, multi-faceted queries requiring deep exploration, while File Search is better for direct, factual queries when you know exactly what you’re looking for.