docs(genapi): added ocr models

pages/generative-apis/how-to/query-ocr-models.mdx

@@ -0,0 +1,120 @@
+---
+title: How to query OCR models
+description: Learn how to interact with powerful OCR models using Scaleway's Generative APIs service.
+tags: generative-apis ai-data ocr-models ocr-api
+dates:
+  validation: 2026-04-14
+  posted: 2026-04-14
+---
+import Requirements from '@macros/iam/requirements.mdx'
+
+Scaleway's Generative APIs service allows users to interact with powerful OCR (Optical Character Recognition) models hosted on the platform.
+
+OCR models can extract structured text from documents such as PDFs and images, preserving formatting and layout in the output.
+
+<Message type="note">
+OCR models are currently available via the [OCR API](https://www.scaleway.com/en/developers/api/generative-apis/#path-ocr-beta-create-a-text-extraction) only and are not yet integrated into the Scaleway console playground.
+</Message>
+
+<Requirements />
+
+- A Scaleway account logged in to the [console](https://console.scaleway.com)
+- [Owner](/iam/concepts/#owner) status or [IAM permissions](/iam/concepts/#permission) allowing you to perform actions in the intended Organization
+- A valid [API key](/iam/how-to/create-api-keys/) for API authentication
+- Python 3.7+ installed on your system
+
+## Query OCR models via API
+
+You can query the models programmatically using your favorite tools or languages.
+In the example that follows, we will use the MistralAI Python client.
+
+### Install the MistralAI SDK
+
+Install the MistralAI SDK using pip:
+
+```bash
+pip install mistralai
+```
+
+### Initialize the client
+
+Initialize the MistralAI client with your base URL and API key:
+
+```python
+from mistralai.client import Mistral
+
+# Initialize the client with your server URL and API key
+mistral = Mistral(
+    server_url="https://api.scaleway.ai",  # Scaleway's Generative APIs service URL
+    api_key="<SCW_SECRET_KEY>"  # Your unique API secret key from Scaleway
+)
+```
+
+<Message type="important">
+This code sample requires `mistralai >= 2.0.0`. For `mistralai <= 1.12.4` (also named `v1`), replace `from mistralai.client import Mistral` with `from mistralai import Mistral`.
+</Message>
+
+### Generate an OCR text extraction
+
+You can now generate a text extraction. 
+In the example below, the sample PDF file, [scaleway-impact-report-10-pages.pdf](https://genapi-documentation-assets.s3.fr-par.scw.cloud/scaleway-impact-report-10-pages.pdf), is sent to the OCR model via a public URL. The extracted text from each page is written to a local Markdown file.
+
+```python
+# Generate a text extraction using the 'mistral-ocr-2512' model
+FILE_URL = "https://genapi-documentation-assets.s3.fr-par.scw.cloud/scaleway-impact-report-10-pages.pdf"
+MODEL = "mistral-ocr-2512"
+
+res = mistral.ocr.process(
+    model=MODEL,
+    document={
+        "document_url": FILE_URL,
+        "type": "document_url",
+    }
+)
+
+filename = FILE_URL.split("/")[-1].split(".")[0]
+with open(f"{filename}.md", "w") as f:
+    for page in res.pages:
+        f.write(page.markdown)
+
+# Print the generated response
+print(f"File processed. Result markdown file stored in: {filename}.md")
+```
+
+Once the script completes, a Markdown file named `scaleway-impact-report-10-pages.md` is created in the current directory, containing the extracted and formatted text from each page of the PDF.
+
+<Message type="tip">
+You can replace `FILE_URL` with the URL of any publicly accessible PDF or image file.
+For example, you can provide a file from Object Storage using an [Object Storage pre-signed URL](https://www.scaleway.com/en/docs/object-storage/how-to/access-objects-via-https/).
+</Message>
+
+Alternatively, you can also provide a local PDF file encoded in Base64 format.
+
+```python
+import base64
+
+FILE_PATH = "path/to/your/file.pdf"
+MODEL = "mistral-ocr-2512"
+
+with open(FILE_PATH, "rb") as file:
+    file_content = file.read()
+    encoded_file= base64.b64encode(file_content).decode("utf-8")
+
+res = mistral.ocr.process(
+    model=MODEL,
+    document={
+        "document_url": f"data:application/pdf;base64,{encoded_file}",
+        "type": "document_url",
+    }
+)
+
+filename = FILE_PATH.split("/")[-1].split(".")[0]
+with open(f"{filename}.md", "w") as f:
+    for page in res.pages:
+        f.write(page.markdown)
+
+# Print the generated response
+print(f"File processed. Result markdown file stored in: {filename}.md")
+```
+
+Refer to the dedicated [OCR API documentation](https://www.scaleway.com/en/developers/api/generative-apis/#path-ocr-beta-create-a-text-extraction) for a full list of all available parameters.

pages/generative-apis/menu.ts

@@ -42,7 +42,11 @@ export const generativeApisMenu = {
           label: 'Query audio models',
           slug: 'query-audio-models'
         },
-                {
+        {
+          label: 'Query OCR models',
+          slug: 'query-ocr-models'
+        },
+        {
           label: 'Query reranking models',
           slug: 'query-reranking-models'
         },