Wauldo Rust SDK
Verified AI answers from your documents. Every response includes source citations, confidence scores, and an audit trail — or we don't answer at all.
Official Rust SDK for the Wauldo API — the AI inference layer with smart model routing and zero hallucinations.
Why Wauldo?
- Zero hallucinations — every answer is verified against source documents
- Smart model routing — auto-selects the cheapest model that meets quality (save 40-80% on AI costs)
- One API, 7+ providers — OpenAI, Anthropic, Google, Qwen, Meta, Mistral, DeepSeek with automatic fallback
- OpenAI-compatible — swap your
base_url, keep your existing code - Full audit trail — confidence score, grounded status, model used, latency on every response
Quick Start
use ;
async
Installation
[]
= "0.1"
= { = "1", = ["rt-multi-thread", "macros"] }
Requirements: Rust 1.70+
Features
Chat Completions
let req = new;
let resp = client.chat.await?;
println!;
RAG — Upload & Query
// Upload a document
let upload = client.rag_upload.await?;
println!;
// Query with verified answer
let result = client.rag_query.await?;
println!;
println!;
println!;
for source in &result.sources
Streaming (SSE)
let req = new;
let mut rx = client.chat_stream.await?;
while let Some = rx.recv.await
Conversation Helper
let mut conv = client.conversation
.with_system
.with_model;
let reply = conv.say.await?;
let follow_up = conv.say.await?;
Error Handling
use Error;
match client.chat.await
RapidAPI
let config = new
.with_header
.with_header;
let client = new?;
Get your free API key (300 req/month): RapidAPI
Links
Contributing
Found a bug? Have a feature request? Open an issue.
License
MIT — see LICENSE