semantic-search-setup-1-cpu-vs-gpu
Sub-skill of semantic-search-setup: 1. CPU vs GPU (+3).
Best use case
semantic-search-setup-1-cpu-vs-gpu is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Sub-skill of semantic-search-setup: 1. CPU vs GPU (+3).
Teams using semantic-search-setup-1-cpu-vs-gpu should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/1-cpu-vs-gpu/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How semantic-search-setup-1-cpu-vs-gpu Compares
| Feature / Agent | semantic-search-setup-1-cpu-vs-gpu | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Sub-skill of semantic-search-setup: 1. CPU vs GPU (+3).
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# 1. CPU vs GPU (+3)
## 1. CPU vs GPU
```python
# Force CPU (more stable, sufficient for most cases)
os.environ['CUDA_VISIBLE_DEVICES'] = ''
# Use GPU if available
# Remove the above line and ensure CUDA is installed
```
## 2. Batch Processing
```python
# Larger batches = faster but more memory
batch_size = 100 # Default
batch_size = 500 # If you have 16GB+ RAM
batch_size = 50 # If memory constrained
```
## 3. Progress Tracking
```python
from tqdm import tqdm
for i in tqdm(range(0, total, batch_size)):
# Process batch
pass
```
## 4. Incremental Updates
```python
# Only embed new chunks
cursor.execute('''
SELECT c.id, c.chunk_text
FROM chunks c
LEFT JOIN embeddings e ON c.id = e.chunk_id
WHERE e.id IS NULL
''')
```Related Skills
tax-filing-session-setup-with-github-tracking
Structured workflow for preparing and tracking a tax filing session using prepared documents, task checklist, and GitHub issue cross-referencing
tax-filing-session-setup-with-github-traceability
Structured workflow for setting up a multi-file tax filing session with GitHub issue tracking and prepared-file validation
orcawave-orcaflex-semantic-proof-wave-closeout
Close out an OrcaWave/OrcaFlex semantic-proof wave after a PR merges, split unrelated CI blockers, and seed the next semantic-proof issue wave without duplicating existing issues.
iterative-plan-redraft-semantic-guardrails
Harden a repeatedly re-reviewed documentation/contract plan after adversarial reviewers keep finding semantic gaps despite new test rows.
gif-search
Search and download GIFs from Tenor using curl. No dependencies beyond curl and jq. Useful for finding reaction GIFs, creating visual content, and sending GIFs in chat.
orcaflex-vessel-setup
Configure 6-DOF vessels in OrcaFlex with hydrodynamic properties, RAO import from AQWA, and vessel type creation. Covers initial position, orientation, calculation settings, and motion options.
hermes-windows-setup
Install and configure a repo-centric Hermes agent workspace on Windows. Covers prerequisites, repo cloning, Python/uv environment, skills system, memory bridge, and multi-agent coordination — the Windows equivalent of the Linux workspace-hub pattern.
semantic-taxonomy-reporting-consistency
Keep semantic-diff taxonomy summaries consistent with evidence tables when adding richer categories to legacy comparison/reporting pipelines.
gh-issue-creation-full-repo-and-batch-setup
Create multiple related GitHub issues safely by resolving full OWNER/REPO, checking duplicates and labels first, and verifying each created issue.
research-literature
Systematize research and literature gathering for engineering categories — queries doc index, capability map, and standards ledger to produce structured research briefs for calculation implementation. type: reference
research-and-literature-gathering
Systematic workflow for finding, downloading, and indexing engineering literature by domain. Covers the full lifecycle: discovery via standards ledger and doc index, web search for open-access PDFs, download script generation, PDF validation, catalogue YAML creation, and handoff to the 7-phase document-index-pipeline for indexing. Use when populating a new engineering domain with reference literature or when a WRK item requires domain-specific standards and textbooks.
semantic-search-setup
Setup vector embeddings and semantic search for document collections. Use for AI-powered similarity search, finding related documents, and preparing knowledge bases for RAG systems.