diff --git a/README.md b/README.md index 2695350..1d5620b 100644 --- a/README.md +++ b/README.md @@ -35,7 +35,7 @@ Everything runs locally, every stage survives being killed mid-run, and all arti ## Requirements - Python 3.12+ and [uv](https://docs.astral.sh/uv/), on macOS, Linux, or Windows. (Development happens on macOS; Windows is untested but nothing is platform-specific. One caveat: the owner-only file permissions bggpipe sets on `.env` and browser session state are POSIX-only — on Windows, keep those files in a directory protected by your account.) -- A vision model for extraction — an [Anthropic API key](https://console.anthropic.com/) by default, or any OpenAI-compatible endpoint including a free local [Ollama](https://ollama.com/) model. +- A vision model for extraction — an [Anthropic API key](https://console.anthropic.com/) by default, or any OpenAI-compatible endpoint including a free local [Ollama](https://ollama.com/) model. **Cost expectation:** extracting the author's whole collection — 65 shelf photos, 136 games — cost under a dollar with the default model (Claude Sonnet), one-time. Re-runs are free: every photo's read is cached, and only new or replaced photos go back to the model. - A BoardGameGeek account **and a registered BGG application** — as of BGG's [2025 API policy](https://boardgamegeek.com/using_the_xml_api), the XML API requires a Bearer token from a registered app. Register a free non-commercial application at [boardgamegeek.com/applications](https://boardgamegeek.com/applications) (approval can take a week or more, so **apply on day one**), then create a token. Each user needs their own; tokens must not be shared. ([You can start before it arrives.](docs/guide.md#running-before-your-bgg-token-arrives)) ### Why it asks for your BGG password — and where your credentials go diff --git a/docs/guide.md b/docs/guide.md index ac6664b..2b1cdfa 100644 --- a/docs/guide.md +++ b/docs/guide.md @@ -32,6 +32,8 @@ Your credentials never leave your machine except to sign in to boardgamegeek.com Non-secret knobs live in `config.toml`: `photos_dir`, `data_dir`, the BGG rate limit, and the vision setup — a `[vision.]` block per provider ("anthropic" or any OpenAI-compatible endpoint, including a local [Ollama](https://ollama.com/)), with `vision_provider` picking one. Local models read spines noticeably worse than frontier ones — expect a longer proofread pass on the Titles page, not a broken pipeline. +**What extraction costs:** the vision call is the pipeline's only paid step, and it's small — the author's full collection (65 shelf photos, 136 games) came to under a dollar on the default model (Claude Sonnet). It's also one-time: raw reads are cached per photo, so re-running extract is free, and only new or replaced photos are ever sent again. Everything BGG-side is free (the API token costs nothing). + ## The web app ```sh