Crate vectorless 

Vectorless

A document engine for AI. It transforms documents into hierarchical semantic trees and uses the LLM itself to navigate and retrieve — purely LLM-guided, from indexing to querying. No vector databases, no embeddings, no similarity search.

Quick Start

use vectorless::{EngineBuilder, IndexContext, QueryContext};

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let client = EngineBuilder::new()
        .with_key("sk-...")
        .with_model("gpt-4o")
        .build()
        .await?;

    let result = client.index(IndexContext::from_path("./document.md")).await?;
    let doc_id = result.doc_id().unwrap();

    let result = client.query(
        QueryContext::new("What is this about?").with_doc_ids(vec![doc_id.to_string()])
    ).await?;
    println!("{}", result.content);

    Ok(())
}

Re-exports

pub use config::Config;

pub use client::BuildError;

pub use client::ClientError;

pub use client::DocumentFormat;

pub use client::DocumentInfo;

pub use client::Engine;

pub use client::EngineBuilder;

pub use client::FailedItem;

pub use client::IndexContext;

pub use client::IndexItem;

pub use client::IndexMode;

pub use client::IndexOptions;

pub use client::IndexResult;

pub use client::QueryContext;

pub use client::QueryResult;

pub use client::QueryResultItem;

pub use error::Error;

pub use error::Result;

pub use document::DocumentStructure;

pub use document::DocumentTree;

pub use document::NodeId;

pub use document::ReasoningIndexConfig;

pub use document::StructureNode;

pub use document::TocConfig;

pub use document::TocEntry;

pub use document::TocNode;

pub use document::TocView;

pub use document::TreeNode;

pub use graph::DocumentGraph;

pub use events::EventEmitter;

pub use events::IndexEvent;

pub use events::QueryEvent;

pub use events::WorkspaceEvent;

pub use metrics::IndexMetrics;

pub use metrics::LlmMetricsReport;

pub use metrics::MetricsReport;

pub use metrics::PilotMetricsReport;

pub use metrics::RetrievalMetricsReport;

Modules

client

High-level client API for document indexing and retrieval.

config

Internal configuration management.

document

Document types - pure data structures for document tree representation.

error

Error types for the vectorless library.

events

Event system for observing and reacting to client operations.

graph

Document graph module — workspace-level cross-document relationship graph.

metrics

Unified metrics collection for Vectorless.