documentmetadata

Documentation

Overview

Copyright 2025 National Technology and Engineering Solutions of Sandia SPDX-License-Identifier: BSD-3-Clause

Index

• Constants
• func PrepareHTML(raw []byte, config Config) (prepared string)
• type Config
  • func DefaultConfig() Config

Constants

const HTMLPrompt = `` /* 896-byte string literal not displayed */

HTMLPrompt instructs the LLM how to interpret the selected HTML evidence.

Functions

func PrepareHTML

func PrepareHTML(raw []byte, config Config) (prepared string)

PrepareHTML tries to extract only HTML relevant to determining website metadata. If no useful regions are found, it returns raw HTML

Types

type Config

type Config struct {
	StartBytes int
	EndBytes   int
}

Config controls how much HTML evidence PrepareHTML returns from each end.

func DefaultConfig

func DefaultConfig() Config

DefaultConfig returns the payload limits used by the metadata extraction clients.