Skip to main content
Each cookbook is one working request for a common task. It shows the request and response schemas, a real response from the live API, and code that acts on the result. Copy a cookbook, swap in your own data, and adjust the criteria or labels. The GLiNER cookbooks cover the three most common ways teams use GLiNER 2.5 Multi: entity extraction, classification, and relation extraction.

​
GLiDE

Triage a support ticket

Pick a queue, rate urgency, and decide if a person should reply.

Gate an agent's next move

Check a proposed action against your policy before the agent acts.

Catch a prompt injection

Spot hidden instructions before your agent obeys them.

​
GLiNER 2.5 Multi

Extract entities

Find people, organizations, places, and dates in any supported language.

Classify text

Run several labeling tasks in one call.

Extract relations

Turn sentences into head, relation, and tail facts.
Every cookbook request is checked against the live API, so the responses shown match what the API returns today. Confidence values vary slightly between calls.