---
title: "requests"
canonical_url: "https://www.nutrient.io/api/python/requests/"
md_url: "https://www.nutrient.io/api/python/requests.md"
last_updated: "2026-08-12T09:03:58.381Z"
description: "API reference for the requests module"
---

API reference for the `requests` module.

```python

# All public classes import directly from the top-level package:

from nutrient_sdk import ClassificationRequest

```

## Classes

| Class                                                             | Description                                                                                                                                                                                                                                                                                                                                                                                                                     |
| ----------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [`ClassificationRequest`](./classification-request/)              | Describes a zero-shot classification request for `Classify`: the candidate labels the document is scored against. Each label optionally carries a longer description that gives the matcher more context; the description never appears in the result. At least two labels are required — classification is zero-shot, so the labels define the entire output space, and a single label would trivially win with probability 1. |
| [`SchemaGenerationRequest`](./schema-generation-request/)         | Describes a schema generation request for `GenerateSchema`. Carries the document type the schema must represent, an optional free-form requirement, and up to five example documents that ground the schema in real layouts.                                                                                                                                                                                                    |
| [`StructuredExtractionRequest`](./structured-extraction-request/) | Describes a structured data extraction request for `ExtractStructured`. Carries a schema envelope — `{"schema": <JSON Schema>}` — describing the fields the extracted data must conform to, and optional free-form instructions that steer the extraction.                                                                                                                                                                      |

---

## Related pages

- [Classification Request](/api/python/requests/classification-request.md)
- [Schema Generation Request](/api/python/requests/schema-generation-request.md)
- [Structured Extraction Request](/api/python/requests/structured-extraction-request.md)