You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/ai-services/document-intelligence/faq.yml
+41-49Lines changed: 41 additions & 49 deletions
Original file line number
Diff line number
Diff line change
@@ -22,7 +22,7 @@ sections:
22
22
- question: |
23
23
Are Azure AI Document Intelligence and Azure AI Form Recognizer the same service?
24
24
answer: |
25
-
Yes.
25
+
**Yes.**
26
26
27
27
Azure AI Document Intelligence and Azure AI Form Recognizer are the same service. The service was renamed from Azure AI Form Recognizer to Azure AI Document Intelligence in July 2023. The service provides the same capabilities and features as before the renaming.
28
28
@@ -33,26 +33,24 @@ sections:
33
33
- question: |
34
34
Does Document Intelligence integrate with other Microsoft services?
35
35
answer: |
36
+
**Yes.**
36
37
37
-
Yes.
38
+
Document Intelligence integrates with the following services:
38
39
39
-
"Document Intelligence integrates with the following services:"
- [Azure AI Search](../../search/cognitive-search-custom-skill-form.md)
42
43
43
-
- [Azure AI Search](../../search/cognitive-search-custom-skill-form.md)
44
+
- [Azure Functions](tutorial-azure-function.md)
44
45
45
-
- [Azure Functions](tutorial-azure-function.md)
46
-
47
-
- [Azure Logic Apps](tutorial-logic-apps.md)
46
+
- [Azure Logic Apps](tutorial-logic-apps.md)
48
47
49
48
- name: AI capabilities
50
49
questions:
51
50
- question: |
52
51
Can I use Document Intelligence with generative AI for document processing?
53
52
answer: |
54
-
55
-
Yes.
53
+
**Yes.**
56
54
57
55
You can use a document generative AI solution to chat with your documents, generate captivating content from those documents, and access Azure OpenAI Service models on your data.
58
56
@@ -63,8 +61,7 @@ sections:
63
61
- question: |
64
62
Does Document Intelligence offer a semantic chunking solution for retrieval-augmented generation?
65
63
answer: |
66
-
67
-
Yes.
64
+
**Yes.**
68
65
69
66
Semantic chunking is a key step in retrieval-augmented generation (RAG) to ensure its efficient storage and retrieval.
70
67
@@ -79,8 +76,8 @@ sections:
79
76
- question: |
80
77
Do I need specific permissions to access Document Intelligence Studio?
81
78
answer: |
79
+
**Yes.**
82
80
83
-
Yes.
84
81
You need an active [Azure account](https://azure.microsoft.com/free/cognitive-services/) and subscription with at least a Reader role to access Document Intelligence Studio.
85
82
86
83
For document analysis and prebuilt models, here are the role requirements for user scenarios:
@@ -112,7 +109,7 @@ sections:
112
109
- question: |
113
110
Can I process documents with more than two pages in Document Intelligence Studio?
114
111
answer: |
115
-
Yesfor paid-tier resources; no for free-tier resources.
112
+
**Yes,**for paid-tier resources. **No**, for free-tier resources.
116
113
117
114
- For free-tier (F0) resources, **only the first two pages** are analyzed whether you're using Document Intelligence Studio, the REST API, or client libraries.
118
115
@@ -122,8 +119,7 @@ sections:
122
119
- question: |
123
120
Can I change directories or subscriptions in Document Intelligence Studio?
124
121
answer: |
125
-
126
-
Yes.
122
+
**Yes.**
127
123
128
124
- To change a directory in Document Intelligence Studio, select the **Settings** (gear) button. Under **Directory**, select the directory from the list, and then select **Switch Directory**. You're prompted to sign in again after you switch the directory.
129
125
@@ -133,25 +129,22 @@ sections:
133
129
Can I use Document Intelligence Studio with a resource that is configured with a firewall or virtual network?
134
130
135
131
answer: |
136
-
137
-
Yes.
132
+
**Yes.**
138
133
139
134
If your Document Intelligence resource is configured with a firewall or virtual network,you need to add the dedicated IP address 20.3.165.95 to the firewall allowlist for your Document Intelligence resource.
140
135
141
136
- question: |
142
137
Can I reuse or customize the labeling experience from Document Intelligence Studio and build it into my own application?
143
138
answer: |
144
-
145
-
Yes.
139
+
**Yes.**
146
140
147
141
The labeling experience from Document Intelligence Studio is open sourced in the [Toolkit repo](https://github.com/microsoft/Form-Recognizer-Toolkit).
148
142
149
143
- question: |
150
144
Are there separate URL endpoints for Document Intelligence sovereign cloud regions?
151
145
answer: |
146
+
**Yes.**
152
147
153
-
Yes.
154
-
155
148
"Document Intelligence Studio has separate URL endpoints for sovereign cloud regions:"
156
149
157
150
- "URL for the Azure US Government cloud (Azure Fairfax): [Document Intelligence Studio US Government](https://formrecognizer.appliedai.azure.us/studio)."
@@ -164,8 +157,7 @@ sections:
164
157
- question: |
165
158
Can I develop applications using Azure AI Document Intelligence using the latest development options?
166
159
answer: |
167
-
168
-
Yes.
160
+
**Yes.**
169
161
170
162
"Document Intelligence offers the latest development options within the following platforms:"
171
163
@@ -184,8 +176,7 @@ sections:
184
176
- question: |
185
177
Can I migrate my application to the latest version of Document Intelligence?
186
178
answer: |
187
-
188
-
Yes.
179
+
**Yes.**
189
180
190
181
"The following table provides links to detailed instructions for migrating to the newest version of Document Intelligence:"
191
182
@@ -200,8 +191,7 @@ sections:
200
191
- question: |
201
192
Can I specify a range of pages to be analyzed in a document?
202
193
answer: |
203
-
204
-
Yes.
194
+
**Yes.**
205
195
206
196
"Use the `pages` parameter (supported in v2.1, v3.0, and later versions of the REST API) and specify pages for multiple-page PDF and TIFF documents. Accepted input includes the following ranges:"
207
197
@@ -218,9 +208,9 @@ sections:
218
208
- question: |
219
209
Do you recommend using Document Intelligence Studio or the FOTT Sample Labeling tool for my project?
220
210
answer: |
221
-
Most of the time, we recommend [Document Intelligence Studio](https://documentintelligence.ai.azure.com/studio) because it can reduce your time for configuring Document Intelligence resources and storage services.
211
+
We recommend [Document Intelligence Studio](https://documentintelligence.ai.azure.com/studio) most of the time because it can reduce your time for configuring Document Intelligence resources and storage services.
222
212
223
-
Consider using the Form OCR Testing Tool (FOTT) for the following scenarios:
213
+
Consider using the Form OCR Testing Tool (FOTT) only for the following scenarios:
224
214
225
215
- Your data must remain within a single machine. Use the [FOTT Sample Labeling tool](/azure/ai-services/document-intelligence/label-tool) and a [Document Intelligence container](/azure/ai-services/document-intelligence/containers/install-run).
226
216
@@ -230,7 +220,7 @@ sections:
230
220
Are there best practices to mitigate throttling?
231
221
232
222
answer: |
233
-
Yes.
223
+
**Yes.**
234
224
235
225
Document Intelligence uses autoscaling to provide the required computational resources on demand, while keeping customer costs low. To mitigate throttling during autoscaling, we recommend the following approach:
236
226
@@ -249,7 +239,7 @@ sections:
249
239
- question: |
250
240
Can I improve an estimated accuracy score for a custom model?
251
241
answer: |
252
-
Yes.
242
+
**Yes.**
253
243
254
244
Variances in the visual structure of your documents can influence the accuracy of a model. Here are some tips:
255
245
@@ -266,7 +256,7 @@ sections:
266
256
- question: |
267
257
Can I retrain a custom model?
268
258
answer: |
269
-
No.
259
+
**No.**
270
260
271
261
* Document Intelligence doesn't have an explicit retrain operation. Each train operation generates a new model.
272
262
@@ -287,7 +277,7 @@ sections:
287
277
- question: |
288
278
Can I move my trained models from one environment (like beta) to another (like production)?
289
279
answer: |
290
-
Yes.
280
+
**Yes.**
291
281
292
282
You can use the [Copy API](disaster-recovery.md#copy-api-overview) to copy custom models from one Document Intelligence account into others that exist in any supported geographical region. For detailed instructions, see [Disaster recovery](disaster-recovery.md).
293
283
@@ -298,8 +288,7 @@ sections:
298
288
- question: |
299
289
Is there an expiry time for the shared access signature (SAS) token that I for my storage account authentication?
300
290
answer: |
301
-
302
-
Yes.
291
+
**Yes.**
303
292
304
293
When you create a shared access signature (SAS), the default duration is 48 hours. After 48 hours, you need to create a new token.
305
294
@@ -308,7 +297,9 @@ sections:
308
297
- question: |
309
298
Can Document Intelligence access data in my storage account if it is behind a virtual network or firewall?
310
299
answer: |
311
-
No, not directly. Document Intelligence can't access your storage account if it's protected by a virtual network or firewall.
300
+
**No**, not directly.
301
+
302
+
Document Intelligence can't access your storage account if it's protected by a virtual network or firewall.
312
303
313
304
However, private Azure storage account access and authentication support [managed identities for Azure resources](../../active-directory/managed-identities-azure-resources/overview.md). When you use a managed identity, the Document Intelligence service can access your storage account by using an assigned credential.
314
305
@@ -322,18 +313,19 @@ sections:
322
313
- question: |
323
314
Is there a difference between disconnected and connected containers?
324
315
answer: |
325
-
Yes. Although the model capabilities are the same, the billing and connectivity methods differ:
316
+
**Yes.**
317
+
318
+
Although the model capabilities are the same for connected and disconneted containers, the billing and connectivity methods differ:
326
319
327
320
- Connected containers send billing information to Azure by using a Document Intelligence resource on your Azure account. With connected containers, internet connectivity is required to send [billing information](containers/install-run.md?tabs=layout#billing) to Azure. Document Intelligence connected containers send billing information to Azure by using a Document Intelligence resource on your Azure account. Connected containers don't send customer data, such as the image or text that's being analyzed, to Microsoft. For an example of the information that connected containers send to Microsoft for billing, see the [Azure AI container FAQ](../../ai-services/containers/disconnected-container-faq.yml#how-does-billing-work).
328
321
329
322
- [Disconnected containers](../../ai-services/containers/disconnected-containers.md) enable you to use APIs that are disconnected from the internet. [Billing information](../../ai-services/containers/disconnected-container-faq.yml#how-does-billing-work) isn't sent via the internet. Instead, you're charged based on a purchased commitment tier. Currently, disconnected container usage is available for Document Intelligence custom and invoice models.
330
-
323
+
331
324
332
325
- question: |
333
326
Can I use local storage for the Document Intelligence Sample Labeling Tool (FOTT) container?
334
327
answer: |
335
-
336
-
Yes.
328
+
**Yes.**
337
329
338
330
FOTT has a version that uses local storage. The version needs to be installed on a Windows machine. You can install it from [this location](https://github.com/microsoft/OCR-Form-Tools/releases/download/v2.1-ga/oflt-2.1.3-win32.exe).
339
331
@@ -342,8 +334,7 @@ sections:
342
334
- question: |
343
335
Is there a best practice for scaling up?
344
336
answer: |
345
-
346
-
Yes.
337
+
**Yes.**
347
338
348
339
For asynchronous calls, you can run multiple containers with shared storage. The container that's processing the `POST` analyze call stores the output in the storage. Then, any other container can fetch the results from the storage and serve the `GET` calls. The request ID isn't tied to a container.
349
340
@@ -352,17 +343,17 @@ sections:
352
343
- question: |
353
344
Can I set up containers with shared storage?
354
345
answer: |
355
-
Yes.
346
+
**Yes.**
356
347
357
348
The containers use the `Mounts:Shared` property while starting up for specifying the shared storage to store the processing files. To see the use of this property, refer to the [containers documentation](containers/install-run.md?view=doc-intel-3.0.0&tabs=custom#create-a-folder-for-storing-internal-processing-shared-between-the-containers).
358
349
359
350
- name: Security and privacy
360
351
questions:
361
-
352
+
362
353
- question: |
363
354
Does Document Intelligence store my data?
364
355
answer: |
365
-
Yes, briefly.
356
+
**Yes,** briefly.
366
357
367
358
For all features, Document Intelligence temporarily stores data and results in Azure Storage in the same region as the request. Your data is then deleted within 24 hours from the time that you submit an analyze request.
368
359
@@ -375,12 +366,13 @@ sections:
375
366
- question: |
376
367
Are there other resources available to provide solutions to Azure AI Document Intelligence questions?
377
368
answer: |
378
-
Yes.
379
-
369
+
**Yes.**
370
+
380
371
[Microsoft Q & A](/answers/topics/azure-form-recognizer.html) is the home for technical questions and answers at Microsoft. You can filter queries that are specific to Document Intelligence.
381
372
382
373
- question: |
383
374
Can I provide direct feedback if the service doesn't recognize specific text, or recognizes it incorrectly, when I'm labeling documents?
384
375
answer: |
385
-
Yes.
376
+
**Yes.**
377
+
386
378
We continually update and improve the Document Intelligence OCR model. You can [email the Document Intelligence team](mailto:[email protected]). If possible, share a sample document with the issue highlighted.
0 commit comments