Struct ContentPrioritizer

pub struct ContentPrioritizer { /* private fields */ }

Content prioritizer that manages sections based on priority and token limits.

The prioritizer sorts content sections by priority and ensures the total content fits within specified token limits by truncating lower priority sections when necessary.

Examples

use ai_context_gen::token_counter::{ContentPrioritizer, ContentSection};

let prioritizer = ContentPrioritizer::new().unwrap();
let sections = vec![
    ContentSection::new("High Priority".to_string(), "Content...".to_string(), 10),
    ContentSection::new("Low Priority".to_string(), "More content...".to_string(), 1),
];
let prioritized = prioritizer.prioritize_content(sections, 1000);

Implementations

impl ContentPrioritizer

pub fn new() -> Result<Self>

Creates a new content prioritizer.

Returns

A new ContentPrioritizer instance with an initialized token counter.

Errors

Returns an error if the underlying token counter cannot be initialized.

pub fn prioritize_content( &self, sections: Vec<ContentSection>, max_tokens: usize, ) -> Vec<ContentSection>

Prioritizes and truncates content sections to fit within token limits.

Sorts sections by priority (highest first) and includes as many complete sections as possible. When a section would exceed the token limit, it attempts to truncate it if there are sufficient remaining tokens.

Arguments

• sections - List of content sections to prioritize
• max_tokens - Maximum total tokens allowed

Returns

A vector of sections that fit within the token limit, sorted by priority.

Examples

use ai_context_gen::token_counter::{ContentPrioritizer, ContentSection};

let prioritizer = ContentPrioritizer::new().unwrap();
let sections = vec![
    ContentSection::new("Important".to_string(), "Critical info".to_string(), 10),
    ContentSection::new("Less Important".to_string(), "Extra details".to_string(), 5),
];
let result = prioritizer.prioritize_content(sections, 100);
// Higher priority sections appear first