RAG + multi-agent (retrieval, policy-compliance, drafting) support assistant for a fictional shipping company, built in Rust with Qdrant for vector storage and a hand-rolled Anthropic tool-calling client (no Rust pydantic-ai equivalent exists). A deterministic supervisor orchestrates the agents and runs every response through a rule-based guardrail pipeline with an append-only audit log. Includes a 44-example golden dataset (normal/injection/policy- violation/hallucination-bait/out-of-scope) and a regression harness that scores retrieval, generation, and guardrail correctness separately, plus a write-up of the failure modes and trade-offs. Co-Authored-By: Claude Sonnet 5 <[email protected]>
9 lines
231 B
Rust
9 lines
231 B
Rust
pub mod audit_log;
|
|
pub mod patterns;
|
|
pub mod pipeline;
|
|
pub mod rule_guardrail;
|
|
|
|
pub use audit_log::AuditLogger;
|
|
pub use pipeline::{GuardrailAction, GuardrailDecision, GuardrailPipeline};
|
|
pub use rule_guardrail::RuleBasedGuardrail;
|