docs(genapi): update content and fix typos

Author: bene2k1

pages/generative-apis/how-to/use-batch-processing.mdx

@@ -11,13 +11,6 @@ import Requirements from '@macros/iam/requirements.mdx'
 Batch processing allows you to submit large volumes of requests to Generative APIs asynchronously, at a discounted price.
 Instead of sending requests one by one, you upload an input file to Object Storage and create a batch job. The service processes the requests in the background and writes the results to an output file.
 
-Batch processing is designed for:
-
-* Large-scale content generation
-* Dataset enrichment
-* Offline inference workloads
-* Cost-optimized asynchronous Processing
-
 <Requirements />
 
 - A Scaleway account logged into the [console](https://console.scaleway.com)
@@ -38,6 +31,13 @@ Each line of the input file must be a valid JSON object representing a request t
 
 Example `input.jsonl`:
 
+<Message type="note">
+  The JSONL file must adhere to the following requirements:
+  * The `custom_id` field must be unique for each request.
+  * The `method`, `url`, and `model` fields must remain consistent across all requests.
+  * The `body` object must comply with the [Generative API documentation](https://www.scaleway.com/en/developers/api/generative-apis/).
+</Message>
+
 ```json
 {"custom_id": "request-1", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "mistral-small-3.2-24b-instruct-2506", "messages": [{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": "Translate this into French: Hello world!"}],"max_completion_tokens": 500}}
 {"custom_id": "request-2", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "mistral-small-3.2-24b-instruct-2506", "messages": [{"role": "system", "content": "You are an unhelpful assistant."},{"role": "user", "content": "Write a poem about the ocean."}],"max_completion_tokens": 500}}
@@ -109,21 +109,23 @@ Note that to configure this bucket policy, you need to replace:
 
 ### Creating the batch job
 
-1. 1. Click **Generative APIs* in the **AI** section of the side menu. The Generative APIs overview displays.
-
+1. In the side menu, navigate to the **AI** section and click **Generative APIs**. The Generative APIs overview page appears.
 2. Click the **Batches** tab.
+3. Click **Create batch**. The batch creation wizard opens.
 
-3. Click **Create batch**. The batch creation wizard displays.
+    <Message type="important">
+      The Object Storage bucket and the batch job must belong to the same project.
+    </Message>
 
-4. Provide:
+4. Provide the following:
+   * Input file path (e.g., `s3://scw-managed-genapi-batch/input.jsonl`)
+     <Message type="tip">
+       You can upload your `input.jsonl` file directly by clicking **+ Add file**.
+     </Message>
 
-   * The input file path (for example: `s3://scw-managed-genapi-batch/input.jsonl`)
-        <Message type="tip">
-          You can also upload your `input.jsonl` file during this step, by clicking **+ Add file**.
-        </Message>
-   * The output prefix (optional)
+   * Output prefix (optional)
 
-5. Click **Create batch**. The batch enters the `Validating` state.
+5. Click **Create batch**. The batch job enters the `Validating` state.
 
 
 ### Monitoring the job