Quantlix Documentation

Ship AI with safety rules, document lookup, run visibility, and quality checks—without stitching four tools together.

New here?

Start in the product first; deep references stay linked below.

Onboarding

Pick Quick Start, a one-click fast path, or the pre-provisioned demo.

Open →

Fast first run

Skip to “run a test question” with demo model + balanced safety defaults.

Open →

Without an ML background

Short explainers for quality checks, knowledge lookup, templates, and fit.

Open →

Product & integrations

Templates

Start from concrete outcomes—safer chat, document Q&A, approvals—not blank graphs.

Read more →

Workflows

Multi-step flows with tools, knowledge lookup (retrieval), retries, and human approvals.

Read more →

Run visibility

Execution timelines (traces), latency, cost, and errors for every request.

Read more →

Quality checks

Golden datasets and comparisons—think tests for AI output quality (evals).

Read more →

Knowledge & docs

Answers from your own documents—chunking, embeddings, and sources (document lookup; also called RAG).

Read more →

Provider integrations

OpenAI, Anthropic, Azure, Bedrock, Groq, Together, Voyage AI, plus built-in demo model.

Read more →

CLI

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

Read more →

API Reference

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

Open API docs →

Advanced governance & contracts

For teams tightening enforcement, budgets, and schema contracts after the basics feel familiar.

Contracts

Schema and feature contracts. Versioned, strict by default.

Read more →

Creating policies

Violation actions, budget policies, preprocess integrity. Curated policy bundles (packs in the UI), CLI, API.

Read more →

Policy engine & budgets

Retry limits, rate control, validation rules, compute ceilings, audit exports.

Read more →

Platform

Student privacy

Block or flag when student PII patterns are detected. Education and privacy contexts.

Read more →

Teams

Org → Team → Project → Deployment. Roles: team_admin, developer, viewer.

Read more →

Retrieval integrations

Vector backends (pgvector, Pinecone, Weaviate, Qdrant) and semantic search APIs.

Read more →

Knowledge source configuration

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

Read more →

Quick start (API)

Deploy with a contract, run inference, and see enforcement at the boundary.

1. Deploy with enforcement

Use 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!"}'

Markdown mirror for editors: docs/START_HERE.md in the repo (linked from /docs/start above).