Quantlix Documentation

Workflows, evals, retrieval, observability, and governance for production AI.

Core Sections

Getting Started

Deploy in under 10 minutes. Onboarding flow, first deployment, and runtime activation.

Workflows

Build multi-step flows with tools, retrieval, retries, fallbacks, and human approvals.

Observability

Traces, spans, latency, cost, errors. Inspect every run and grounding.

Evals

Golden datasets, regression testing, version comparisons. Score groundedness and citation correctness.

Contracts

Schema and feature contracts. Versioned, strict by default.

Creating Policies

Violation actions, budget policies, preprocess integrity. Enforcement packs, CLI, API.

Policy Engine

Retry limits, rate control, validation rules, behavioral constraints.

Budget Controls

Real-time compute enforcement, request ceilings, budget tiers.

Audit & Exports

Structured violations, decision logs, exportable enforcement events.

CLI

quantlix deploy, run, status. Full command reference with options and examples.

API Reference

REST API documentation. OpenAPI spec. Deploy, run, status, usage.

Open API docs →

Platform

Student Privacy

Block or flag when student PII (name+ID, personnummer, email) is detected. Education and privacy compliance.

Teams

Org → Team → Project → Deployment. Create teams, add members, assign roles (team_admin, developer, viewer).

Provider Integrations

OpenAI, Anthropic, Voyage AI, Azure. Add providers, set credentials, bind deployments to models.

Retrieval Integrations

Vector backends (pgvector, Pinecone, Weaviate, Qdrant). RAG API: semantic search, answer generation with citations.

Knowledge Source Configuration

Chunking, embedding, vector index, sources. Ingestion pipeline: upload, S3, web. RAG setup.

Quick Start

Deploy with a contract, run inference, and see the platform in action.

1. Deploy with enforcement

Use the dashboard onboarding or CLI. Contract enforcement is enabled by default.

2. Run inference

Valid requests pass. Invalid requests are blocked at the boundary.

curl -X POST https://api.quantlix.ai//run \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"deployment_id": "YOUR_DEPLOYMENT_ID", "input": {"prompt": "Hello, world!"}}'

3. CLI

Install, authenticate, deploy, and run. Enforcement applies to every request.

pip install quantlix
quantlix login
quantlix deploy qx-example
quantlix run <deployment_id> -i '{"prompt": "Hello!"}'

Workflows, evals, retrieval, and governance in one platform.