Leina 
Wanta 
Read a document
Parse a URL document into Markdown for analysis.
/oo PDF Vector: Parse document [public URL] into Markdown, then summarize its sections and notable tables.
Connect PDF Vector to Your AI Agent
Ask your AI assistant to work with PDF Vector: read Documents and Extract Structured Fields.
3 tools API key
Try a PDF Vector Task
Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.
oo Skill PDF Vector
Extract a structured record
Use a prompt and JSON schema to guide field extraction.
/oo PDF Vector: Extract fields from [public document URL] using prompt [instructions] and schema [JSON schema]. Report missing fields rather than inventing values.
Start Working with PDF Vector
-
Install OOMOL
Set up oo CLI and the oo Skill in your agent.
Install OOMOL → -
Connect PDF Vector
Connect using your PDF Vector API Key.
Connect PDF Vector → -
Give Your Agent a Task
Use /oo with the pages to read, the changes to make, and where to save the result.
Connection Guide →
Choose Your Agent
- An account with access to the PDF Vector resources used in your task.
PDF Vector Tools
PDF Vector processes publicly reachable document URLs into Markdown, document answers, or schema-shaped JSON.
Read a document
Parse a URL document into Markdown for analysis.
Extract a structured record
Use a prompt and JSON schema to guide field extraction.
3 tools
Parse Document
Parse a document from a public URL into Markdown with PDF Vector.
pdf_vector.parse_document Ask Document
Ask a question about a document available at a public URL with PDF Vector.
pdf_vector.ask_document Extract Document
Extract structured JSON matching a supplied schema from a document at a public URL with PDF Vector.
pdf_vector.extract_document No matching tools.
Frequently Asked Questions
Do I upload a local file directly?
These actions take a public documentUrl. Make the file accessible by URL first.
Can I ask a single question without parsing first?
ask_document accepts documentUrl and question directly.
Does extraction infer absent facts?
Specify how missing values should be handled and review the returned JSON against the source document.