> ## Documentation Index
> Fetch the complete documentation index at: https://developers.lighton.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Introduction
> Upload a PDF. Search it in milliseconds. Parse any document to clean Markdown.
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.
Upload files to a workspace and LightOn turns them into a searchable index
automatically, running the whole document-understanding pipeline for you.
Hybrid semantic + lexical search with reranking across your document corpus.
Returns ranked chunks with scores, source metadata, and optional page images.
Retrieval-augmented generation in one call: a grounded LLM answer with the
sources it used, returned synchronously or streamed token by token.
### Classify and organise documents
Partition your corpus into isolated containers per team, customer, or tenant.
Group documents into reusable collections that cut across workspaces.
Define classification trees with custom attributes, classify files, and filter search by metadata.
### Process documents on the fly
Convert or extract from a document in a single call. Nothing is stored, useful for feeding your own pipeline.
Convert PDFs, Office files, and images to structured Markdown. Sync mode for
quick jobs, async for large documents. Nothing stored either way.
Pull typed fields out of documents using a JSON Schema you provide. Sync mode
for small files, async mode for large jobs.
## Get started
Get a search result in under 5 minutes.
Set up your API key.
Full endpoint documentation.
