62 lines
2.5 KiB
Markdown
62 lines
2.5 KiB
Markdown
Installed https://github.com/santifer/career-ops
|
|
|
|
Good — since career-ops explicitly supports Ollama as a free local engine, let's wire this to what you already built. Quick check first: which AI CLI do you want to drive it — Claude Code (uses your Claude subscription/API), or OpenCode (lets you point directly at your local Ollama for $0 cost)? Given the whole point of setting up Ollama was to avoid API costs, I'll assume **OpenCode + Ollama**, but flag if you'd rather use Claude Code.
|
|
|
|
**1. Check prerequisites**
|
|
|
|
```bash
|
|
node -v # need Node.js — if missing: brew install node
|
|
git --version
|
|
```
|
|
|
|
**2. Install career-ops**
|
|
|
|
```bash
|
|
npx @santifer/career-ops init
|
|
cd career-ops
|
|
```
|
|
|
|
This clones the latest release and installs dependencies for you.
|
|
|
|
**3. Install the browser engine for PDF generation**
|
|
|
|
```bash
|
|
npx playwright install chromium
|
|
```
|
|
|
|
career-ops uses Playwright (headless Chrome) to render your friend's CV/cover letter to PDF and to scan some job portals — this is a one-time download (~150-300MB).
|
|
|
|
**4. Get OpenCode (if you don't already have an AI CLI)**
|
|
|
|
```bash
|
|
npm i -g opencode-ai
|
|
```
|
|
|
|
**5. Point OpenCode at your local Ollama**
|
|
|
|
career-ops is CLI-agnostic — it just needs an AI CLI wired to a model. Configure OpenCode to talk to Ollama's OpenAI-compatible endpoint. In OpenCode's config (`~/.config/opencode/opencode.json` or via `opencode auth login` flow depending on version), set the local provider to:
|
|
|
|
```
|
|
base URL: http://localhost:11434/v1
|
|
model: qwen2.5-coder:14b (or whichever you pulled)
|
|
```
|
|
|
|
**6. Run the doctor check**
|
|
|
|
```bash
|
|
npm run doctor
|
|
```
|
|
|
|
This validates your setup (Node, Playwright, CLI config) and tells you specifically what's missing — much better than guessing.
|
|
|
|
**7. Launch and onboard**
|
|
|
|
```bash
|
|
opencode
|
|
```
|
|
|
|
Then inside the session, just start chatting — on first launch career-ops walks you through CV/profile setup conversationally rather than making you hand-edit YAML.
|
|
|
|
One honest caveat before you commit to the local-model path: career-ops's evaluation quality (fit scoring, CV tailoring, company research) leans on the model actually being good at instruction-following and reasoning across a long agentic session. A 14B local model will be noticeably weaker at this than Claude — worth testing on one real job posting before running your friend's whole batch through it, so you're not silently getting worse evaluations to save money.
|
|
|
|
Want me to walk through step 5's exact config file syntax once you've got OpenCode installed and can share what version/config format it's using? |