PDF Vector
for LuumenAI
Turn PDFs into markdown and structured data, and search the literature
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.
The PDF Vector toolbox
10 tools, all read-only. They answer instantly, and every call is logged.
- ReadAsk DocumentAnswer one question from a general, identity, invoice, or bank-statement document.
- ReadExtract Document DataExtract schema-constrained structured data from a general, identity, invoice, or bank-statement document.
- ReadFetch PublicationsResolve up to 100 publication identifiers with provider auto-detection and return both resolved records and per-identifier errors.
- ReadFind CitationsFind relevant academic citations for each sentence in a paragraph and preserve provider-specific partial errors.
- ReadFind Similar PapersFind papers related to a seed publication using citation-network similarity, optionally including relationship edges.
- ReadGet Paper GraphRetrieve a publication plus one independently offset-controlled page of citing papers and one page of referenced papers.
- ReadParse Academic PaperResolve an academic identifier or provider URL to a public PDF and parse it to markdown.
- ReadParse DocumentConvert a general, identity, invoice, or bank-statement document to markdown.
- ReadSearch PublicationsSearch academic publications across selected databases and return one offset-controlled page, including any provider-specific partial errors.
- ReadSearch Research GrantsSearch US, EU, and UK research-grant providers and return one explicit offset-controlled page with partial provider errors.
Questions
Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
No. Every one of the 10 tools LuumenAI has for PDF Vector is read-only, so it can answer questions from PDF Vector but cannot change anything in it. Read actions still follow the configured access and approval policy, and are recorded on the audit trail.
You decide. Access is granted per agent, skill, and team, and per environment — production is not staging.
Every call to PDF Vector is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Often connected alongside
All integrations
Adobe Marketing Agent MCPAdobe Experience Platform context, sandbox switches, and async task status
AffindaRead parsed documents, collections, and annotations — change them with approval
Agent MailGive the agent its own mailbox for reading threads and sending updates
AI/ML APIInspect assistants, threads, and runs — and change them as approved stepsPut PDF Vector to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.