Mistral OCR
Mistral OCR reads the text in images and PDF documents with Mistral’s service. It can handle each page of a PDF separately.
When to use it
- Reading scanned invoices or delivery notes to record their data.
- Getting the text from photos of documents that arrive on WhatsApp or by email.
- Extracting specific fields from a form, such as the name and the amount.
Configuration
You need a Mistral AI API credential with your Mistral account key. See Credentials.
| Field | What it does |
|---|---|
| Credential (required) | The Mistral AI API credential. |
| Image/PDF Input | The image or PDF to read, for example the output of Binary or of a component that loads files. |
| Process PDF Pages | Reads each page of a PDF as a separate image. On by default. |
Advanced options
| Field | What it does |
|---|---|
| PDF DPI | Resolution used to convert PDF pages. Higher reads small print better but takes longer. Default: 200. |
Output
The OCR Results output holds the text read from each image or page.
In tool mode, an agent can use the component by itself. See Tool Mode.
Example
A transport company digitises its PDF delivery notes.
- Connect each PDF to Image/PDF Input with Process PDF Pages on.
- Pass OCR Results to a model that extracts the recipient and delivery date.
Related components
- Text Extractor: pulls names, dates or amounts out of the text read.