---
title: "PDF Vector integration for LuumenAI"
url: "https://www.luumen.ai/integrations/pdf-vector/"
entity: SoftwareIntegration
category: "AI & automation"
audience: "SRE, DevOps, platform engineering, IT operations"
---

# PDF Vector integration for LuumenAI

Turn PDFs into markdown and structured data, and search the literature

## What LuumenAI can do with PDF Vector

LuumenAI connects to PDF Vector with an API token and exposes 10 tools (10 read-only). Every tool is read-only, so it can answer questions from PDF Vector but cannot change anything in it.

## Key facts

- Authentication: API token
- Tools available: 10 tools (10 read-only)
- Plan: available on all plans
- Category: AI & automation

## About PDF Vector with LuumenAI

Point Luumen at a vendor invoice, a scanned ID, or a bank statement and get markdown back with PDF_VECTOR_PARSE_DOCUMENT, or schema-shaped fields with PDF_VECTOR_EXTRACT_DOCUMENT. Ask one-off questions of a document. Search publications and research grants when the answer lives in the literature. Connected with an API key. Every tool here is read-only, so results come back in the session without an approval step.

## Example tools

Read-only (10 in total):

- `PDF_VECTOR_ASK_DOCUMENT` — Answer one question from a general, identity, invoice, or bank-statement document.
- `PDF_VECTOR_EXTRACT_DOCUMENT` — Extract schema-constrained structured data from a general, identity, invoice, or bank-statement document.
- `PDF_VECTOR_FETCH_PUBLICATIONS` — Resolve up to 100 publication identifiers with provider auto-detection and return both resolved records and per-identifier errors.
- `PDF_VECTOR_FIND_CITATIONS` — Find relevant academic citations for each sentence in a paragraph and preserve provider-specific partial errors.
- `PDF_VECTOR_FIND_SIMILAR_PAPERS` — Find papers related to a seed publication using citation-network similarity, optionally including relationship edges.
- `PDF_VECTOR_GET_PAPER_GRAPH` — Retrieve a publication plus one independently offset-controlled page of citing papers and one page of referenced papers.
- `PDF_VECTOR_PARSE_ACADEMIC_PAPER` — Resolve an academic identifier or provider URL to a public PDF and parse it to markdown.
- `PDF_VECTOR_PARSE_DOCUMENT` — Convert a general, identity, invoice, or bank-statement document to markdown.

## Frequently asked questions

### How does LuumenAI connect to PDF Vector?

Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

### Can LuumenAI change things in PDF Vector on its own?

No. Every one of the 10 tools is read-only, so LuumenAI can answer questions from PDF Vector but cannot change anything in it.

### Is there an audit trail?

Every call to PDF Vector is recorded with the actor, the input, and the result.

Full page: https://www.luumen.ai/integrations/pdf-vector/