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/language-service/personally-identifiable-information/concepts/conversations-entity-categories.md
Use this article to find the entity categories that can be returned by the [conversational PII detection feature](../how-to-call-for-conversations.md). This feature runs a predictive model to identify, categorize, and redact sensitive information from an input conversation.
18
18
19
-
The PII preview feature includes the ability to detect personal (`PII`) information from conversations.
20
-
21
19
## Entity categories
22
20
23
21
The following entity categories are returned when you're sending API requests PII feature.
Copy file name to clipboardExpand all lines: articles/ai-services/language-service/personally-identifiable-information/how-to-call-for-conversations.md
+6-6Lines changed: 6 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -26,11 +26,11 @@ By default, this feature will use the latest available AI model on your input. Y
26
26
27
27
### Language support
28
28
29
-
Currently the conversational PII preview API only supports English language.
29
+
See the [PII Language Support page](language-support.md) for more details. Currently the conversational PII GA model only supports the English language. The preview model and API support the [same list languages](../concepts/language-support.md) as the other Language services.
30
30
31
31
### Region support
32
32
33
-
Currently the conversational PII preview API supports all Azure regions supported by the Language service.
33
+
The conversational PII API supports all Azure regions supported by the Language service.
34
34
35
35
## Submitting data
36
36
@@ -82,7 +82,7 @@ When you get results from PII detection, you can stream the results to an applic
82
82
Use the following example if you have conversations transcribed using the Speech service's [speech to text](../../Speech-Service/speech-to-text.md) feature:
83
83
84
84
```bash
85
-
curl -i -X POST https://your-language-endpoint-here/language/analyze-conversations/jobs?api-version=2022-05-15-preview \
85
+
curl -i -X POST https://your-language-endpoint-here/language/analyze-conversations/jobs?api-version=2024-05-01 \
86
86
-H "Content-Type: application/json" \
87
87
-H "Ocp-Apim-Subscription-Key: your-key-here" \
88
88
-d \
@@ -195,7 +195,7 @@ curl -i -X POST https://your-language-endpoint-here/language/analyze-conversatio
195
195
"taskName": "analyze 1",
196
196
"kind": "ConversationalPIITask",
197
197
"parameters": {
198
-
"modelVersion": "2022-05-15-preview",
198
+
"modelVersion": "2023-04-15-preview",
199
199
"redactionSource": "text",
200
200
"includeAudioRedaction": true,
201
201
"piiCategories": [
@@ -213,7 +213,7 @@ curl -i -X POST https://your-language-endpoint-here/language/analyze-conversatio
213
213
Use the following example if you have conversations that originated in text. For example, conversations through a text-based chat client.
214
214
215
215
```bash
216
-
curl -i -X POST https://your-language-endpoint-here/language/analyze-conversations/jobs?api-version=2022-05-15-preview \
216
+
curl -i -X POST https://your-language-endpoint-here/language/analyze-conversations/jobs?api-version=2024-05-01 \
217
217
-H "Content-Type: application/json" \
218
218
-H "Ocp-Apim-Subscription-Key: your-key-here" \
219
219
-d \
@@ -251,7 +251,7 @@ curl -i -X POST https://your-language-endpoint-here/language/analyze-conversatio
0 commit comments