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/cognitive-services/language-service/language-studio.md
+25Lines changed: 25 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -57,6 +57,31 @@ When you're ready to use Language Studio features on your own text data, you wil
57
57
58
58
4. Select **Done**. Your resource will be created, and you will be able to use the different features offered by the Language service with your own text.
59
59
60
+
61
+
### Valid text formats for conversation features
62
+
63
+
> [!NOTE]
64
+
> This section applies to the following features:
65
+
> *[PII detection for conversation](./personally-identifiable-information/overview.md)
If you're sending conversational text to supported features in Language Studio, be aware of the following input requirements:
69
+
* The text you send must be a conversational dialog between two or more participants.
70
+
* Each line must start with the name of the participant, followed by a `:`, and followed by what they say.
71
+
* Each participant must be on a new line. If multiple participants' utterances are on the same line, it will be processed as one line of the conversation.
72
+
73
+
See the following example for how you should structure conversational text you want to send.
74
+
75
+
*Agent: Hello, you're chatting with Rene. How may I help you?*
76
+
77
+
*Customer: Hi, I tried to set up wifi connection for Smart Brew 300 espresso machine, but it didn't work.*
78
+
79
+
*Agent: I’m sorry to hear that. Let’s see what we can do to fix this issue.*
80
+
81
+
Note that the names of the two participants in the conversation (*Agent* and *Customer*) begin each line, and that there is only one participant per line of dialog.
82
+
83
+
:::image type="content" source="./media/language-studio-conversation-example.png" alt-text="A screenshot showing an example conversation input in Language Studio." lightbox="./media/language-studio-conversation-example.png":::
84
+
60
85
## Clean up resources
61
86
62
87
If you want to clean up and remove a Cognitive Services subscription, you can delete the resource or resource group. Deleting the resource group also deletes any other resources associated with it.
Copy file name to clipboardExpand all lines: articles/cognitive-services/language-service/personally-identifiable-information/how-to-call-for-conversations.md
+5-2Lines changed: 5 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -8,7 +8,7 @@ manager: nitinme
8
8
ms.service: cognitive-services
9
9
ms.subservice: language-service
10
10
ms.topic: how-to
11
-
ms.date: 05/10/2022
11
+
ms.date: 01/31/2023
12
12
ms.author: jboback
13
13
ms.reviewer: bidishac
14
14
---
@@ -35,6 +35,9 @@ Currently the conversational PII preview API supports all Azure regions supporte
35
35
36
36
## Submitting data
37
37
38
+
> [!NOTE]
39
+
> See the [Language Studio](../language-studio.md#valid-text-formats-for-conversation-features) article for information on formatting conversational text to submit using Language Studio.
40
+
38
41
You can submit the input to the API as list of conversation items. Analysis is performed upon receipt of the request. Because the API is asynchronous, there may be a delay between sending an API request, and receiving the results. For information on the size and number of requests you can send per minute and second, see the data limits below.
39
42
40
43
When using the async feature, the API results are available for 24 hours from the time the request was ingested, and is indicated in the response. After this time period, the results are purged and are no longer available for retrieval.
@@ -59,7 +62,7 @@ When you get results from PII detection, you can stream the results to an applic
59
62
60
63
1. Go to your resource overview page in the [Azure portal](https://portal.azure.com/#home)
61
64
62
-
2. From the menu on the left side, select **Keys and Endpoint**. You will need one of the keys and the endpoint to authenticate your API requests.
65
+
2. From the menu on the left side, select **Keys and Endpoint**. You'll need one of the keys and the endpoint to authenticate your API requests.
63
66
64
67
3. Download and install the client library package for your language of choice:
@@ -40,6 +40,9 @@ There's another feature in Azure Cognitive Service for Language named [document
40
40
41
41
## Submitting data
42
42
43
+
> [!NOTE]
44
+
> See the [Language Studio](../../language-studio.md#valid-text-formats-for-conversation-features) article for information on formatting conversational text to submit using Language Studio.
45
+
43
46
You submit documents to the API as strings of text. Analysis is performed upon receipt of the request. Because the API is [asynchronous](../../concepts/use-asynchronously.md), there may be a delay between sending an API request and receiving the results. For information on the size and number of requests you can send per minute and second, see the data limits below.
44
47
45
48
When you use this feature, the API results are available for 24 hours from the time the request was ingested, and is indicated in the response. After this time period, the results are purged and are no longer available for retrieval.
0 commit comments