> ## Documentation Index
> Fetch the complete documentation index at: https://docs.vlm.run/llms.txt
> Use this file to discover all available pages before exploring further.

# Best Practices

> Best practices for designing schemas for visual inputs.

Defining a clear and effective schema is crucial for getting the most accurate and useful information from visual inputs. A well-designed schema acts as a precise instruction set, guiding the model to extract exactly what you need in a structured format. Following best practices ensures your schemas are robust, maintainable, and yield high-quality results.

This guide outlines key principles and techniques for crafting good, robust and maintainable schemas using [Pydantic](https://docs.pydantic.dev/latest/). If you are interested in contributing to this guide (especially around the usage of [Zod](https://zod.dev/)), please reach out to us on [Discord](https://discord.com/invite/AMApC2UzVY) or [email](mailto:support@vlm.run?subject=Schema%20Request).

## Best Practices

1. **Keep schemas focused**: Define schemas that extract only the information you need.
2. **Use validation rules**: Leverage Pydantic's validation capabilities to ensure data integrity.
3. **Create reusable components**: Break down complex schemas into smaller, reusable models.
4. **Document your fields**: Use the `Field` class with descriptive titles to improve extraction quality.
5. **Test with diverse inputs**: Validate your schemas against a variety of visual inputs to ensure robustness.

## Mapping Schemas to Task Primitives

* **Classification**: Use `Literal` to constrain your field values to a set of possible categories.
* **Captioning**: Use `str` to extract a textual description of the image. Provide some additional details regarding the style, context and also provide a rough estimate of the length of the caption (in number of words).
* **Date Parsing**: Use `datetime.date` to extract a date from the image. Provide some additional details regarding the format of the date (e.g. `YYYY-MM-DD`). One additional caveat is that you can not provide `date` as the field name in your Pydantic BaseModel, as it is a reserved keyword in Pydantic. Use `datetime.datetime` instead if you need to extract additional time information (e.g. `YYYY-MM-DD HH:MM:SS`). Otherwise, always use `datetime.date` for date parsing.