Results for “query-tuning”

Diagnoses and improves Qdrant search relevance by isolating embedding model, configuration, or query strategy issues.

Optimize machine learning model hyperparameters using grid search, random search, Bayesian optimization, and Hyperband to maximize model performance within a compute budget. Use when the user requests hyperparameter tuning or provides relevant inputs for this workflow.

Adds autotuning to CuTile kernels using the exhaustive_search API with a tune-once/cache/direct-launch pattern, covering occupancy-only and complex tile-size search spaces.

Guides selection of Qdrant search strategies including hybrid search, reranking, relevance feedback, MMR, and discovery APIs to improve retrieval quality.

Diagnoses Qdrant search quality issues by isolating causes like HNSW approximation, quantization, embedding model, or search pipeline problems.

Optimizes Qdrant query performance for large limits across multiple shards by using Poisson-distributed subsampling to reduce inter-shard data transfer.

Fine-tune open models or Gemini models using Agent Platform infrastructure, from environment setup through data preparation, job configuration, monitoring, and deployment.

`task-agent`/`review-agent`: use when broker delivery, ordering, acknowledgement, DLQ, backpressure, or replay changes; skip synchronous retry without message semantics.

Design or revise a company's commercial policy governing discounts, approver thresholds, exception flows, and deal frameworks using data-backed matrices and linting tools.

Visual Prompt Tuning

Process the Refinery merge queue - collect agent work, detect and resolve conflicts, merge in dependency order, and verify integration.