solvi guide¶

This guide walks through the whole API. Where a question needs judgement, a model proposes and solvi's checks decide; the model is whichever you have — an LLM through solvi.llm, a decision service, or a local checkpoint such as solvi-base for offline or cheap cases (see the model proposes). For a two-minute overview, see the README; for advice drawn from building on solvi, see best practices. Every measured number in this guide names its source: a script in benchmarks/ or an example, which you can re-run from this repository, or the model card of a published model (solvi-base, solvi-large, solvi-large-long, extract-base, extract-receipts).

Contents: