Switch OpenViking's embedding model to a local llama-server (or any OpenAI-compatible embedding endpoint) running inside a bwrap sandbox managed by job-env-manager. Handles the full lifecycle: detect current config, validate the target embedding endpoint, modify ov.conf, delete incompatible vectordb index when dimension changes, restart the openviking-server process in the sandbox, and verify…
安装
npx skills add huaweicloud/huaweicloud-skills --skill huawei-cloud-openviking-embedding-switchnpx skills add huaweicloud/huaweicloud-skills --skill huawei-cloud-openviking-embedding-switch -a claude-code -gnpx skills add huaweicloud/huaweicloud-skills --skill huawei-cloud-openviking-embedding-switch -a codex -ggemini skills install https://github.com/huaweicloud/huaweicloud-skills.git --path skills/devtools/extensions/huawei-cloud-openviking-embedding-switchgh skill install huaweicloud/huaweicloud-skills huawei-cloud-openviking-embedding-switchgit clone --depth 1 https://github.com/huaweicloud/huaweicloud-skills /tmp/huaweicloud__huaweicloud-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/huaweicloud__huaweicloud-skills/skills/devtools/extensions/huawei-cloud-openviking-embedding-switch ~/.claude/skills/huawei-cloud-openviking-embedding-switch # Claude Code
cp -R /tmp/huaweicloud__huaweicloud-skills/skills/devtools/extensions/huawei-cloud-openviking-embedding-switch ~/.agents/skills/huawei-cloud-openviking-embedding-switch # Codex, Cursor, Gemini CLI, Copilot, OpenCode