qdrant/skills

Qdrant Advisor loads the latest official Qdrant skills to diagnose deployment, search, scaling, memory, and client SDK issues. Use it when a Qdrant cluster, collection, or vector-search question needs current guidance.

Qdrant Clients SDK provides official client libraries for Python, JavaScript, Rust, Go, .NET, and Java. Use it to connect applications to Qdrant through REST or gRPC and to fetch code snippets for common tasks.

Qdrant Deployment Options helps you choose between local mode, Docker, Qdrant Cloud, and Qdrant EDGE. Use it when deciding how to deploy Qdrant for prototyping, production, or lowest-latency search.

Qdrant Edge guides building with Qdrant’s embedded in-process shard. Use it for local sync patterns, BM25 and hybrid search on device, snapshots, and operating Edge correctly in Python or Rust.

Qdrant Indexing Performance Optimization diagnoses slow uploads, long HNSW builds, and stuck optimizers in Qdrant. Use it to tune batching, shards, indexing thresholds, and payload indexes when ingestion or search quality is degraded.

Qdrant Latency Optimization guides how to reduce single-query and tail latency in Qdrant. Use it when search is slow, p99 is high, or you need faster vector search on a Qdrant node.

Qdrant Latency Remote helps diagnose search latency spikes in Qdrant, such as p99 regressions over time. Use it to inspect what changed and narrow down likely causes with skills.qdrant.tech.

Qdrant Memory Optimization diagnoses high RAM use in Qdrant and suggests ways to lower resident memory or page-cache pressure. Use it when memory is growing, nodes crash, or storage and quantization settings do not match expectations.

Qdrant Migration moves collections from one Qdrant instance to another using the Qdrant skills site. Use it when transferring data between clusters with provided URLs and API keys.

Qdrant Model Migration guides changing embedding models in Qdrant without downtime. Use it to re-embed data, add or switch vector fields, or run old and new models side by side.

Qdrant Monitoring routes monitoring and observability questions to the right guidance for Prometheus, Grafana, alerts, logs, and health checks. Use it when tracking metrics or debugging slow requests, memory growth, or optimizer issues.

Qdrant Monitoring Debugging diagnoses production issues with metrics and observability data. Use it when optimizers stall, memory grows, queries slow down, or performance degrades without an obvious config change.

Qdrant Monitoring Setup guides Prometheus scraping, health probes, alerting, and log centralization for Qdrant deployments. Use it when configuring monitoring for self-hosted or Hybrid Cloud clusters.

Qdrant Multitenancy guides how to isolate tenant data in Qdrant for multi-user search and RAG systems. It covers payload partitioning, custom sharding, collection-per-tenant cases, and data residency planning.

Qdrant Performance Optimization routes users to sub-skills for search speed, indexing performance, and memory usage tuning. Use it when planning configuration or capacity changes to improve speed and efficiency.

Qdrant Query Scaling guides how to reduce cross-shard work for large limits and offsets in auto-sharded searches. Use it when queries return too many results, paginate large result sets, or fetch many vectors.

Qdrant Scaling routes scaling questions to the right guidance for capacity, throughput, latency, sharding, and retention needs. Use it when deciding how many nodes, how to shard, or how to reduce query load.

Qdrant Search Quality diagnoses bad search relevance, low recall, and low precision in Qdrant. Use it to identify whether the model, the data, or retrieval settings are causing poor matches and to measure retrieval quality.

Qdrant Search Quality Diagnosis helps isolate why retrieval results are irrelevant, missing, or low-recall. Use it to compare exact vs approximate search, check quantization and filtering, and measure retrieval quality with labeled baselines.

Qdrant Search Speed Optimization diagnoses slow search, high latency, and low QPS in Qdrant. Use it to isolate memory pressure, filter bottlenecks, optimizer lag, or config issues and apply the right fixes.

Qdrant Search Strategies helps choose advanced retrieval methods when basic vector search misses relevant items or ranks them poorly. Use it for hybrid search, reranking, relevance feedback, MMR, recommendations, discovery, and score boosting.

Qdrant Sizing estimates RAM, disk, CPU, GPU, and node count before a deployment is provisioned. Use it for capacity planning, checking whether a vector workload will fit, or choosing an instance type.

Qdrant Throughput Scaling guides how to increase query throughput in Qdrant. Use it when QPS is too low, queries need batching, or read replicas and other tuning options are needed.

Qdrant Version Upgrade explains how to upgrade Qdrant server and SDKs safely, including version matching, stepwise minor upgrades, and rolling upgrades. Use it when planning a version change or troubleshooting behavior after an upgrade.

Scaling Data Volume guides Qdrant capacity decisions when a dataset outgrows one node. Use it for tenant scaling, sliding time windows, vertical scaling, or sharding across nodes.