Skip to content

Commit ab12fa5

Browse files
Merge pull request #284116 from ginalee-dotcom/patch-6
Update concept-custom-neural.md & service quota limits page
2 parents fb64e77 + 9c77384 commit ab12fa5

File tree

3 files changed

+106
-6
lines changed

3 files changed

+106
-6
lines changed

articles/ai-services/document-intelligence/concept-custom-neural.md

Lines changed: 27 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -276,8 +276,8 @@ https://{endpoint}/formrecognizer/documentModels/{modelId}:copyTo?api-version=20
276276
:::moniker range="doc-intel-4.0.0"
277277

278278
## Billing
279-
280-
Starting with version `2024-07-31-preview` and later you can receive **10 hours** of free model training. Billing charges are calculated for model trainings that exceed 10 hours. You can choose to spend all of 10 free hours on a single build with a large set of data, or utilize it across multiple builds by adjusting the maximum duration value for the `build` operation by specifying `maxTrainingHours`:
279+
280+
Starting with version `2024-07-31-preview`, you can train your custom neural model for longer durations than 30 minutes. Previous versions have been capped at 30 minutes per training instance, with a total of 20 free training instances per month. Now with `2024-07-31-preview`, you can receive **10 hours** of free model training, and train a model for as long as 10 hours. If you would like to train a model for longer than 10 hours, billing charges are calculated for model trainings that exceed 10 hours. You can choose to spend all of 10 free hours on a single build with a large set of data, or utilize it across multiple builds by adjusting the maximum duration value for the `build` operation by specifying `maxTrainingHours` as below:
281281

282282
```bash
283283

@@ -288,7 +288,10 @@ POST /documentModels:build
288288
}
289289
```
290290

291-
Build time varies. Billing is calculated for the actual time spent (excluding time in queue), with a minimum of 30 minutes per training job. The elapsed time is converted to V100 equivalent training hours and reported as part of the model.
291+
> [!NOTE]
292+
> For Document Intelligence versions `v3.1 (2023-07-31)` and `v3.0 (2022-08-31)`, custom neural model's paid training is not enabled. For the two older versions, you will get a maximum of 30 minutes training duration per model. If you would like to train more than 20 model instances, you can request for increase in the training limit.
293+
294+
Each training hour is the amount of compute a single V100 GPU can perform in an hour. As each build takes different amount of time, billing is calculated for the actual time spent (excluding time in queue), with a minimum of 30 minutes per training job. The elapsed time is converted to V100 equivalent training hours and reported as part of the model.
292295

293296
```bash
294297

@@ -305,10 +308,30 @@ This billing structure enables you to train larger data sets for longer duration
305308
306309
:::moniker-end
307310
311+
:::moniker range="doc-intel-3.1.0"
312+
313+
## Billing
314+
315+
For Document Intelligence versions `v3.1 (2023-07-31)` and `v3.0 (2022-08-31)`, you will get a maximum of 30 minutes training duration per model, and a maximum of 20 trainings for free per month. If you would like to train more than 20 model instances, you can request for increase in the training limit.
316+
317+
If you are interested in training models for longer durations than 30 minutes, we support **paid training** for our newest version, `v4.0 (2024-07-31)`. Using the latest version, you can train your model for a longer duration to process larger documents.
318+
319+
:::moniker-end
320+
321+
:::moniker range="doc-intel-3.0.0"
322+
323+
## Billing
324+
325+
For Document Intelligence versions `v3.1 (2023-07-31)` and `v3.0 (2022-08-31)`, you will get a maximum of 30 minutes training duration per model, and a maximum of 20 trainings for free per month. If you would like to train more than 20 model instances, you can request for increase in the training limit.
326+
327+
If you are interested in training models for longer durations than 30 minutes, we support **paid training** for our newest version, `v4.0 (2024-07-31)`. Using the latest version, you can train your model for a longer duration to process larger documents.
328+
329+
:::moniker-end
330+
308331
## Next steps
309332
310333
Learn to create and compose custom models:
311334
312335
> [!div class="nextstepaction"]
313336
> [**Build a custom model**](how-to-guides/build-a-custom-model.md)
314-
> [**Compose custom models**](how-to-guides/compose-custom-models.md)
337+
> [**Compose custom models**](how-to-guides/compose-custom-models.md)

articles/ai-services/document-intelligence/concept-read.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -121,6 +121,7 @@ The searchable PDF capability enables you to convert an analog PDF, such as scan
121121
>
122122
> * Currently, the searchable PDF capability is only supported by Read OCR model `prebuilt-read`. When using this feature, please specify the `modelId` as `prebuilt-read`, as other model types will return error for this preview version.
123123
> * Searchable PDF is included with the 2024-07-31-preview `prebuilt-read` model with no additional cost for generating a searchable PDF output.
124+
> * Searchable PDF currently only supports PDF files as input. Support for other file types, such as image files, will be available later.
124125
125126
### Use searchable PDF
126127

articles/ai-services/document-intelligence/service-limits.md

Lines changed: 78 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -110,7 +110,80 @@ Document Intelligence billing is calculated monthly based on the model type and
110110
| **Max number of Neural models** | 100 | 500 |
111111
| Adjustable | No | No |
112112

113-
::: moniker range=">=doc-intel-3.0.0"
113+
::: moniker range=">=doc-intel-4.0.0"
114+
115+
## Custom model usage
116+
117+
> [!div class="checklist"]
118+
>
119+
> * [**Custom template model**](concept-custom-template.md)
120+
> * [**Custom neural model**](concept-custom-neural.md)
121+
> * [**Custom generative model**](concept-custom-generative.md)
122+
> * [**Composed classification models**](concept-custom-classifier.md)
123+
> * [**Composed custom models**](concept-composed-models.md)
124+
125+
|Quota|Free (F0) <sup>1</sup>|Standard (S0)|
126+
|--|--|--|
127+
| **Compose Model limit** | 5 | 500 (default value) |
128+
| Adjustable | No | No |
129+
| **Training dataset size * Neural and Generative** | 1 GB <sup>3</sup> | 1 GB (default value) |
130+
| Adjustable | No | No |
131+
| **Training dataset size * Template** | 50 MB <sup>4</sup> | 50 MB (default value) |
132+
| Adjustable | No | No |
133+
| **Max number of pages (Training) * Template** | 500 | 500 (default value) |
134+
| Adjustable | No | No |
135+
| **Max number of pages (Training) * Neural and Generative** | 50,000 | 50,000 (default value) |
136+
| Adjustable | No | No |
137+
| **Custom neural model train** | 10 hours per month <sup>5</sup> | no limit (pay by the hour) |
138+
| Adjustable | No |Yes <sup>3</sup>|
139+
| **Max number of pages (Training) * Classifier** | 10,000 | 10,000 (default value) |
140+
| Adjustable | No | No |
141+
| **Max number of document types (classes) * Classifier** | 500 | 500 (default value) |
142+
| Adjustable | No | No |
143+
| **Training dataset size * Classifier** | 1GB | 2GB (default value) |
144+
| Adjustable | No | No |
145+
| **Min number of samples per class * Classifier** | 5 | 5 (default value) |
146+
| Adjustable | No | No |
147+
148+
::: moniker-end
149+
150+
::: moniker range="=doc-intel-3.0.0"
151+
152+
## Custom model usage
153+
154+
> [!div class="checklist"]
155+
>
156+
> * [**Custom template model**](concept-custom-template.md)
157+
> * [**Custom neural model**](concept-custom-neural.md)
158+
> * [**Composed classification models**](concept-custom-classifier.md)
159+
> * [**Composed custom models**](concept-composed-models.md)
160+
161+
|Quota|Free (F0) <sup>1</sup>|Standard (S0)|
162+
|--|--|--|
163+
| **Compose Model limit** | 5 | 200 (default value) |
164+
| Adjustable | No | No |
165+
| **Training dataset size * Neural** | 1 GB <sup>3</sup> | 1 GB (default value) |
166+
| Adjustable | No | No |
167+
| **Training dataset size * Template** | 50 MB <sup>4</sup> | 50 MB (default value) |
168+
| Adjustable | No | No |
169+
| **Max number of pages (Training) * Template** | 500 | 500 (default value) |
170+
| Adjustable | No | No |
171+
| **Max number of pages (Training) * Neural** | 50,000 | 50,000 (default value) |
172+
| Adjustable | No | No |
173+
| **Custom neural model train** | 10 per month | 20 per month |
174+
| Adjustable | No |Yes <sup>3</sup>|
175+
| **Max number of pages (Training) * Classifier** | 10,000 | 10,000 (default value) |
176+
| Adjustable | No | No |
177+
| **Max number of document types (classes) * Classifier** | 500 | 500 (default value) |
178+
| Adjustable | No | No |
179+
| **Training dataset size * Classifier** | 1GB | 1GB (default value) |
180+
| Adjustable | No | No |
181+
| **Min number of samples per class * Classifier** | 5 | 5 (default value) |
182+
| Adjustable | No | No |
183+
184+
::: moniker-end
185+
186+
::: moniker range="=doc-intel-3.1.0"
114187

115188
## Custom model usage
116189

@@ -169,12 +242,15 @@ Document Intelligence billing is calculated monthly based on the model type and
169242
::: moniker range=">=doc-intel-2.1.0"
170243

171244
> <sup>1</sup> For **Free (F0)** pricing tier see also monthly allowances at the [pricing page](https://azure.microsoft.com/pricing/details/form-recognizer/).</br>
172-
> <sup>2</sup> See [best practices](#example-of-a-workload-pattern-best-practice), and [adjustment instructions(#create-and-submit-support-request).</br>
245+
> <sup>2</sup> See [best practices](#example-of-a-workload-pattern-best-practice), and [adjustment instructions](#create-and-submit-support-request).</br>
173246
> <sup>3</sup> Neural models training count is reset every calendar month. Open a support request to increase the monthly training limit.
174247
::: moniker-end
175248
::: moniker range=">=doc-intel-3.0.0"
176249
> <sup>4</sup> This limit applies to all documents found in your training dataset folder prior to any labeling-related updates.
177250
::: moniker-end
251+
::: moniker range=">=doc-intel-4.0.0"
252+
> <sup>5</sup> This limit applies for `v 4.0 (2024-07-31)` custom neural models only. Starting from `v 4.0`, we support training larger documents for longer durations (up to 10 hours for free, and incurring charges after). For more information, please refer to [custom nerual model page](concept-custom-neural.md).
253+
::: moniker-end
178254

179255
## Detailed description, Quota adjustment, and best practices
180256

0 commit comments

Comments
 (0)