Skip to content

solvi guide

The reference behind the documentation's three parts: Using solvi (the ready systems and how you set them up), Building blocks (the low level, solvi.core, they are made of) and Experimental (solvi.experimental). On the site each chapter is a page of its part; here they follow in that order. Where a question needs judgement, a model proposes and solvi's checks decide; the model is whichever you have — an LLM through solvi.models.llm, a decision service through solvi.models.systemone, or a local checkpoint such as solvi-base (solvi.models.decider) for offline or cheap cases (see the model proposes). For a two-minute overview, see the README; for agents and knowledge, Using solvi: agents and knowledge; 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:

Using solvi — the ready systems and what you write to use them: solvi.build, the catalog and its questions, models from solvi.models, System and Response, solvi.Guard, serving, the command line. Agents and knowledge (solvi.Agent, solvi.Knowledge) have a page of their own.

  1. Quick start: solvi.build
  2. Concepts
  3. Installation
  4. The catalog
  5. Questions and answer types
  6. Types, questions and model decisions
  7. Asking: System and Response
  8. Questions without a rule: fit, learn_rule, teach
  9. Guarding an agent's tool calls
  10. Serving: HTTP, MCP and System One
  11. Text in: from a message to a question
  12. Checking a catalog: solvi check
  13. Printing results: solvi.show
  14. Command line
  15. Guarantees and limitations

Building blocks — the low level, solvi.core, that the ready systems are made of — to rebuild a part or write your own. Building blocks has one reference per extension point.

  1. How the strategist plans a flow
  2. Confidence, calibration and abstention
  3. The trace and verification
  4. Grounded decisions: provenance, audit and safeguards
  5. A model that writes: generation, agreement and the re-ask loop
  6. Who answers: System 1, the slow path or a person (solvi.core.dispatch)
  7. Knowledge: what a system learned, and from whom
  8. System 1 and System 2 on a game: the Pokémon world map
  9. Extracting fields from documents
  10. Versions of a document and their impact: solvi.core.versions
  11. Specialists: a model proposes, code checks, the store keeps the run
  12. Explaining a decision: the smallest change that flips it

Experimental — solvi.experimental: works and is tested, no measured gain yet; its API may change, and each piece graduates or is removed by 1.2 (Experimental lists what each one is missing).

  1. solvi behind a coding agent's hooks
  2. A specification compiled into the catalog: solvi.experimental.compile
  3. Verified charts: a specialist that checks every number
  4. The change pipeline: solvi.experimental.changes