Packages
nous
0.12.6
0.17.0
0.16.6
0.16.5
0.16.4
0.16.3
0.16.2
0.16.1
0.16.0
0.15.8
0.15.7
0.15.6
0.15.5
0.15.4
0.15.3
0.15.2
0.15.1
0.15.0
0.14.3
0.14.2
0.14.1
0.14.0
0.13.3
0.13.2
0.13.1
0.13.0
0.12.17
0.12.16
0.12.15
0.12.14
0.12.13
0.12.12
0.12.11
0.12.9
0.12.7
0.12.6
0.12.5
0.12.3
0.12.2
0.12.0
0.11.3
0.11.0
0.10.1
0.10.0
0.9.0
0.8.1
0.8.0
0.7.2
0.7.1
0.7.0
0.5.0
AI agent framework for Elixir with multi-provider LLM support
Current section
Files
Jump to
Current section
Files
lib/nous/output_schema/validator.ex
defmodule Nous.OutputSchema.Validator do
@moduledoc """
Behaviour for structured output validation.
Implement `validate_changeset/1` in your Ecto schema modules to add
custom validation rules that the LLM must satisfy. Failed validations
are sent back to the LLM as retry messages when `max_retries` > 0.
## Example
defmodule SpamPrediction do
use Ecto.Schema
use Nous.OutputSchema
@llm_doc \"""
## Field Descriptions:
- class: Whether or not the email is spam.
- reason: A short, less than 10 word rationalization.
- score: A confidence score between 0.0 and 1.0.
\"""
@primary_key false
embedded_schema do
field :class, Ecto.Enum, values: [:spam, :not_spam]
field :reason, :string
field :score, :float
end
@impl true
def validate_changeset(changeset) do
changeset
|> Ecto.Changeset.validate_number(:score,
greater_than_or_equal_to: 0.0,
less_than_or_equal_to: 1.0
)
end
end
"""
@doc """
Apply custom validation rules to the changeset after Ecto casting.
Return the changeset with any additional validations applied.
Errors on the changeset will be formatted and sent back to the LLM
for retry when `max_retries` > 0.
"""
@callback validate_changeset(Ecto.Changeset.t()) :: Ecto.Changeset.t()
@optional_callbacks [validate_changeset: 1]
end