Bring Ocr
to LlamaIndex

The type determines the parsing engine (e.g., "pdf", "email", "attachment"). Once created, you can configure templates and forward documents to the mailbox for automatic extraction. Create a new Parseur mailbox for document parsing

Pass the template name and a JSON config string defining field mappings. Parseur will use this template to extract structured data from matching documents. Create a new extraction template for a Parseur mailbox

Fields depend on the template configuration (e.g., invoice_number, total_amount, line_items). Only works for documents with status "processed". Retrieve the fully extracted JSON data from a parsed document

Does not include the parsed data itself — use get_document_data for that. Get metadata of a single parsed document

Use this to verify mailbox setup before sending documents. Get detailed configuration of a specific Parseur mailbox

Each entry includes document ID, status (processed, failed, pending), and metadata like sender and received date. List all parsed documents inside a Parseur mailbox

Each mailbox represents a parsing pipeline for a specific document type (invoices, receipts, emails). Use the returned mailbox IDs for subsequent operations like listing documents or uploading files. List all Parseur parsing mailboxes

Templates define the extraction rules (field names, locations, regex patterns) used to pull structured data from incoming documents. List available extraction templates for a Parseur mailbox

Useful after fixing template rules or when the original parse failed due to a transient error. The document will be matched against the latest template rules. Retry parsing a failed or errored Parseur document

eml) to the specified mailbox for automatic parsing. The document enters the processing queue and will be parsed according to the mailbox template. Returns the new document ID for tracking. Upload a document URL to a Parseur mailbox for parsing