菜单
Configure the LLM provider for arktrace (OpenAI, local Ollama, or llama.cpp). Use when setting up a new environment or switching LLM providers.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Deploy arktrace to Cloudflare Pages and configure R2, CI, and environment variables. Use when setting up a new deployment or updating production configuration.
Download the arktrace demo dataset from R2 for local development. Use when you need sample data without running the full pipeline.
Run the arktrace analyst dashboard locally. Use when developing the React frontend or verifying UI changes.
Run the arktrace shadow fleet screening pipeline for a region. Use when scoring vessels, refreshing the watchlist, or running the full pipeline end-to-end.
Run arktrace tests — pipeline unit/integration tests and frontend Vitest tests. Use before committing or when CI fails.
| name | arktrace-llm-setup |
| description | Configure the LLM provider for arktrace (OpenAI, local Ollama, or llama.cpp). Use when setting up a new environment or switching LLM providers. |
| license | Apache-2.0 |
| compatibility | Requires .env file; optional local GPU for self-hosted models |
| metadata | {"repo":"arktrace"} |
Set LLM_PROVIDER in .env to one of:
| Value | Where it runs | Requires |
|---|---|---|
openai | OpenAI API | OPENAI_API_KEY in .env |
ollama | Local (Ollama) | ollama serve running on :11434 |
llama_cpp | Local (llama.cpp) | server running on LLM_BASE_URL |
ollama serve # separate terminal
ollama pull llama3.2
echo 'LLM_PROVIDER=ollama' >> .env
See references/local-llm-setup.md for model selection, GPU config, and performance tuning.