Parseur offers multiple AI parsing engines optimized for different document types and extraction scenarios.
You can choose the AI engine for each mailbox in Mailbox Settings > General > AI engine:
Available AI Engines
Engine | Best For | Key Strengths | Limitations |
AI Text engine v2.5 | Most standard document extraction workflows | Stable, fast, reliable text extraction | Limited layout understanding |
AI Text engine v3 | Advanced text extraction and evolving AI features | Improved reasoning, better long-document understanding | Experimental and may behave differently from v2.5 |
AI Vision engine v3 (Default) | Complex PDFs, scans, images, and visually rich documents | Understands layout, visual structure, handwriting, checkboxes, stamps, and multi-column documents | Can be unnecessary for simple text documents |
Disabled | Template-only workflows | Ensures only templates are used | No AI fallback for unmatched documents |
AI Text engine v2.5
Recommended for most users and production workflows.
AI Text engine v2.5 is Parseur’s current, most stable AI engine. It extracts data primarily from the document’s text content rather than its visual appearance.
Best use cases
Emails
Machine-generated PDFs
Structured documents with predictable text
Invoices, receipts, purchase orders, and bank statements with readable text
High-volume production parsing
Advantages
Stable and predictable extraction behavior
Faster processing than vision-based AI
Lower risk of inconsistent results
Excellent for text-heavy workflows
Works well with native PDFs and digital documents
Limitations
Limited understanding of visual layout
Less effective for:
Multi-column layouts
Handwritten documents
Checkboxes and visual markers
Stamps and signatures
Complex scanned forms
Recommended when
Use AI Text engine v2.5 when:
Your documents already contain selectable text
Layout is relatively simple
Reliability and consistency are more important than advanced layout understanding
You process large document volumes
AI Text engine v3
Recommended for users testing the latest AI parsing improvements.
AI Text engine v3 is Parseur’s newer experimental text AI engine. It includes improvements in reasoning, instruction following, and long-document understanding.
Best use cases
Complex text extraction scenarios
Long documents
Documents requiring detailed instructions
Testing newer AI capabilities
Documents where v2.5 struggles with context
Advantages
Better understanding of long documents
Improved instruction following
More advanced contextual reasoning
Improved extraction flexibility
Limitations
Experimental engine
Results may vary more than v2.5
Some edge cases may behave differently between updates
Not always ideal for highly stable production workflows
Recommended when
Use AI Text engine v3 when:
You want to test the latest parsing improvements
Your extraction logic relies heavily on instructions
Documents contain large amounts of text or complex context
v2.5 is not extracting fields accurately enough
AI Vision engine v3 (Default)
Recommended for visually complex documents and scanned files.
AI Vision engine v3 uses vision-language models (VLMs) to analyze documents visually, similarly to how a human reads a page.
Unlike text-only engines, Vision AI understands:
Layout structure
Visual positioning
Handwriting
Checkboxes
Highlighted fields
Tables with inconsistent formatting
Stamps and signatures
Best use cases
Scanned PDFs
Photos of documents
Multi-column layouts
Forms with checkboxes
Handwritten content
Visually rich documents
Low-quality scans
Documents where layout matters
Advantages
Understands both text and visual structure
Better extraction from difficult layouts
Handles layout interpretation together
Stronger performance on image-based documents
Better handling of messy or inconsistent formatting
Limitations
Can be unnecessary for simple text documents
Recommended when
Use AI Vision engine v3 when:
Documents are scanned or image-based
Visual structure matters
Text extraction alone is insufficient
You need to capture checkboxes, signatures, or handwriting
Documents contain complex layouts
Disabled Mode
When AI is disabled, Parseur will only use template-based parsing.
If no matching template is found, the document will fail processing.
Recommended when
Disable AI when:
You require deterministic extraction
All incoming documents follow known layouts
You only want template-based parsing
Compliance or workflow requirements prohibit AI parsing
Which AI Engine Should You Choose?
Choose AI Text engine v2.5 if:
You want the most stable experience
Your documents are text-heavy
You process standard invoices, receipts, or emails
You need reliable production workflows
Choose AI Text engine v3 if:
You want newer AI capabilities
You process long or context-heavy documents
You rely heavily on AI instructions
You are comfortable testing experimental improvements
Choose AI Vision engine v3 if (recommended default):
Your documents are scanned or image-based
Layout and visual context matter
You need handwriting or checkbox extraction
Documents contain complex formatting
Disable AI if:
You exclusively use templates
Your layouts are fixed and predictable
You require deterministic extraction behavior
Important Notes
Matching templates always take priority over AI engines.
If no template matches, Parseur will use the selected AI engine.
For best results, use clear field names and concise instructions.
AI engines can work alongside template-based workflows in the same mailbox.