48 lines
1.3 KiB
Elixir
48 lines
1.3 KiB
Elixir
|
# This file is auto-generated by alef — DO NOT EDIT.
|
||
|
|
# alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
|
||
|
|
# To regenerate: alef generate
|
||
|
|
# To verify freshness: alef verify --exit-code
|
||
|
|
# Issues & docs: https://github.com/kreuzberg-dev/alef
|
||
|
|
defmodule Kreuzberg.StructuredExtractionConfig do
|
||
|
|
@moduledoc """
|
||
|
|
Configuration for LLM-based structured data extraction.
|
||
|
|
|
||
|
|
Sends extracted document content to a VLM with a JSON schema,
|
||
|
|
returning structured data that conforms to the schema.
|
||
|
|
|
||
|
|
# Example
|
||
|
|
|
||
|
|
```toml
|
||
|
|
[structured_extraction]
|
||
|
|
schema_name = "invoice_data"
|
||
|
|
strict = true
|
||
|
|
|
||
|
|
[structured_extraction.schema]
|
||
|
|
type = "object"
|
||
|
|
properties.vendor = { type = "string" }
|
||
|
|
properties.total = { type = "number" }
|
||
|
|
required = ["vendor", "total"]
|
||
|
|
|
||
|
|
[structured_extraction.llm]
|
||
|
|
model = "openai/gpt-4o"
|
||
|
|
```
|
||
|
|
"""
|
||
|
|
|
||
|
|
@typedoc "Configuration for LLM-based structured data extraction."
|
||
|
|
@type t :: %__MODULE__{
|
||
|
|
schema: String.t() | nil,
|
||
|
|
schema_name: String.t() | nil,
|
||
|
|
schema_description: String.t() | nil,
|
||
|
|
strict: boolean(),
|
||
|
|
prompt: String.t() | nil,
|
||
|
|
llm: map()
|
||
|
|
}
|
||
|
|
|
||
|
|
defstruct schema: nil,
|
||
|
|
schema_name: nil,
|
||
|
|
schema_description: nil,
|
||
|
|
strict: false,
|
||
|
|
prompt: nil,
|
||
|
|
llm: nil
|
||
|
|
end
|