Infer a schema

The shape tool inspects your markdown content and infers a schema of the data it contains. It returns the classes, properties, and relationships so you know what is available to extract.

Prerequisites

An AiQL API key in the AIQL_API_KEY environment variable
Markdown content from the Convert or Split step

Infer the schema

Send the markdown you want to inspect. Tool requests authenticate with a Bearer token and do not need a workspace.

curl -X POST https://api.aiql.io/shape \
  -H "Authorization: Bearer $AIQL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"markdown": "# Report\n\nThe markdown content..."}'

import os
from aiql import AiQL

client = AiQL(api_key=os.environ["AIQL_API_KEY"])

schema = client.tools.shape(markdown=markdown)
print(schema.classes)

import { AiQL } from "@aiql.io/sdk";

const client = new AiQL({ apiKey: process.env.AIQL_API_KEY });

const schema = await client.tools.shape({ markdown });
console.log(schema.classes);

The response is a schema made of classes, properties, and relationships:

A class has a name and a definition.
A property has a name, a definition, and a domain (the class or classes it applies to).
A relationship has a name, a definition, a domain (the class or classes it starts from), and a range (the class or classes it points to).

Use it to decide what to pull in the next step.

Next step

Pass the schema to Extract to pull its values out of the markdown.

shape is billed at 10 credits per 1,000 words, with a minimum of 1 credit. See Pricing for details.

Tools

Pipeline

Workspace

Embedding

Prerequisites

Infer the schema

Next step

​Prerequisites

​Infer the schema

​Next step

Prerequisites

Infer the schema

Next step