Skip to main content
LightOn gives you an API to search, parse, and ingest documents at scale. Build knowledge-retrieval pipelines without managing vector databases or OCR models.

What you can do

Build a searchable knowledge base

Ingest documents once, then query them. A persistent, indexed corpus you can search or ask questions over.

Ingest

Upload files to a workspace and LightOn turns them into a searchable index automatically, running the whole document-understanding pipeline for you.

Search

Hybrid semantic + lexical search with reranking across your document corpus. Returns ranked chunks with scores, source metadata, and optional page images.

Ask

Retrieval-augmented generation in one call: a grounded LLM answer with the sources it used, returned synchronously or streamed token by token.

Process documents on the fly

Convert or extract from a document in a single call. Nothing is stored, useful for feeding your own pipeline.

Parse

Convert PDFs, Office files, and images to structured Markdown. Sync mode for quick jobs, async for large documents. Nothing stored either way.

Extract

Pull typed fields out of documents using a JSON Schema you provide. Sync mode for small files, async mode for large jobs.

Get started

Quickstart

Get a search result in under 5 minutes.

Authentication

Set up your API key.

API Reference

Full endpoint documentation.
Do you even search?