Response Times
Response time will vary depending on the source document, the Data Schema, and the options selected.
Unfortunately, there is no free lunch.
Source Document
Properties of the source document which impact response time:
file size, especially for images files
number of pages
density of text
Take a look at the Guidelines For Uploading Files section for ways to improve source files.
Data Schema
Properties of the Data Schema which impact response time:
number of fields
complexity of guidelines
Additionally, lists of nested objects in the Data Schema and many corresponding items in the source document. For example: a multi-page invoice with many products purchased, and each product having multiple fields returned in the response.
Processing Options
Processing options which impact response time:
Continuous Learning (RAG) Before performing the inference, the RAG database must be searched.
Confidence Score and Accuracy Boost Several models are called in parallel, results are then analyzed and combined.
Polygons (Bounding Boxes) Additional information must be extracted from the document, then polygons must be calculated.
Examples
Common combinations of document types and models.
Fastest
Single page documents with few fields.
ID documents: passports, driver licenses, etc.
Healthcare cards
Tickets, boarding passes
Envelopes, packages
Average
Single page documents with nested objects. Multiple page documents with no nested objects.
Most receipts
Single page invoices
Bills of lading
Most business contracts
Slower
Multiple page documents with nested objects and small text.
Very long receipts with many items and small text (i.e. long list of groceries for the week)
Invoices with more than 10 pages, each page having many items
Monthly bank statements, especially when over 10 pages
Whenever possible, remove any unnecessary pages before uploading the document.
Last updated
Was this helpful?