Skip to main content

Welcome to Vectorless

Vectorless is a document understanding engine for AI. It compiles documents into structured trees of meaning, then dispatches multiple agents to reason through headings, sections, and paragraphs — evaluating how each part relates to the whole. The problem it solves is not "where to look", but "what does this mean in context". Every answer is a reasoning act, not a retrieval result.

How It Works​

  1. Parse — Documents (Markdown, PDF) are parsed into hierarchical semantic trees, preserving structure and relationships between sections.
  2. Compile — Trees are stored with metadata, keywords, and summaries. The pipeline resolves cross-references ("see Section 2.1") and expands keywords with LLM-generated synonyms for improved recall. Incremental compiling skips unchanged files via content fingerprinting.
  3. Ask — An LLM-powered agent navigates the tree to find the most relevant sections. The Orchestrator coordinates multi-document queries, dispatching Workers that use ls, cd, cat, find, and grep commands to explore the tree and collect evidence.

Quick Start​

import asyncio
from vectorless import Engine

async def main():
    engine = Engine(
        api_key="sk-...",
        model="gpt-4o",
    )

    # Compile a document
    result = await engine.compile(path="./report.pdf")
    doc_id = result.doc_id

    # Ask a question
    response = await engine.ask("What is the total revenue?", doc_ids=[doc_id])
    print(response.single().content)

asyncio.run(main())

Using a Custom Endpoint​

engine = Engine(
    api_key="sk-...",
    model="gpt-4o",
    endpoint="https://api.your-provider.com/v1",
)

From Environment Variables​

engine = Engine.from_env()

From Config File​

engine = Engine.from_config_file("./config.toml")