Qdrant Sliding Time Window
by qdrant6a03d0ce8f55No licenseListed Oct 8, 2026Updated Oct 8, 2026
Guides sliding time window scaling in Qdrant. Use when someone asks 'only recent data matters', 'how to expire old vectors', 'time-based data rotation', 'delete old data efficiently', 'social media feed search', 'news search', 'log search with retention', or 'how to keep only last N months of data'.
Add to a SourceWeft workspace
- Open the skill in your dashboard and add it to a workspace.
- Enable it for the chats that should use it.
This skill is instructions only: it ships no scripts to execute.
Add to SourceWeftYou will be asked to sign in first, then taken straight to this skill.
Ask your agent to install it
Paste this prompt into Claude Code, Codex, Cursor or another agent that can run commands — or into SourceWeft chat. The agent reads this skill's install guide, shows you its source, license and scripts, and installs it with the SourceWeft CLI once you agree.
Read https://sourceweft.com/skills/gh-qdrant-skills-qdrant-sliding-time-window/install.md and install the skill it describes. Before installing, show me its source, license and whether it ships scripts, and wait for my OK. Ask me before changing anything else on my machine.Install it yourself from a terminal
For Claude Code, Codex, Cursor and other local agents. The SourceWeft CLI fetches the skill from its source repository at the commit scanned here, and verifies every file against the hashes recorded when the skill was scanned. If anything differs, nothing is written.
npx @sourceweft/cli skills install gh-qdrant-skills-qdrant-sliding-time-windowAdd --agent claude-code, codex, cursor or universal to choose which agent gets it (Claude Code by default).
Upstream installer — not verified by SourceWeft
The open-source skills installer fetches the same pinned commit, but does not check the files against the hashes SourceWeft recorded.
npx skills add https://github.com/qdrant/skills/tree/6a03d0ce8f554a579c2e14a81fb7e2245a708db0/skills/qdrant-scaling/scaling-data-volume/sliding-time-windowSource and attribution
Source:qdrant/skillsinskills/qdrant-scaling/scaling-data-volume/sliding-time-windowat commit6a03d0c
License: No license
Content belongs to its original authors. SourceWeft indexes it from a public repository.
More from qdrant/skills
Qdrant Version Upgrade
qdrant
Guides Qdrant server and SDK version upgrades, covering compatibility rules, pre-upgrade checks, and post-upgrade troubleshooting.
Qdrant Sizing
qdrant
Guides capacity planning for Qdrant vector database deployments, estimating RAM, disk, CPU, GPU and node count.
Qdrant Relevance Feedback
qdrant
Guides use of Qdrant's Relevance Feedback query API to improve dense vector search, including weight calibration and usage patterns.
Qdrant Hybrid Search Combining
qdrant
Guides choosing and configuring Qdrant fusion methods (RRF, DBSF, formula, multivector reranking) to combine prefetch results.
Qdrant Hybrid Search
qdrant
Explains Qdrant hybrid search: prefetch building blocks, result combination, and IDF isolation across tenants.
Qdrant Search Strategies
qdrant
Guides selection of Qdrant search strategies such as hybrid search, reranking, MMR, and relevance feedback.
More in Data & Analytics
Spanner Basics
Guides Google Cloud Spanner administration, schema design, querying and performance diagnosis.
Gke Cost Analysis
Answers natural-language questions about GKE cluster and workload costs using BigQuery billing exports and live cluster metrics.
Datalineage Bigquery Asset Impact Analysis
Guides an agent through downstream impact (blast radius) analysis for a BigQuery table or view using Data Lineage.
Bigquery Troubleshooting
Diagnoses failing, slow, or unexpectedly expensive BigQuery jobs through structured root-cause workflows.
Bigquery Optimization
Guides BigQuery cost and performance optimization across capacity editions, storage layout, and SQL queries.
Bigquery Bigframes
Guides writing Python code with BigQuery DataFrames (BigFrames) for data processing, analysis, and machine learning.