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/search/includes/quickstarts/python-semantic.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -285,7 +285,7 @@ for result in results:
285
285
286
286
In this final query, return semantic answers.
287
287
288
-
Semantic ranking can generate answers to a query string that has the characteristics of a question. The generated answer is extracted verbatim from your content. To get a semantic answer, the question and answer must be closely aligned, and the model must find content that clearly answers the question. If potential answers fail to meet a confidence threshold, the model doesn't return an answer. For demonstration purposes, the question in this example is designed to get a response so that you can see the syntax.
288
+
Semantic ranker can generate answers to a query string that has the characteristics of a question. The generated answer is extracted verbatim from your content. To get a semantic answer, the question and answer must be closely aligned, and the model must find content that clearly answers the question. If potential answers fail to meet a confidence threshold, the model doesn't return an answer. For demonstration purposes, the question in this example is designed to get a response so that you can see the syntax.
289
289
290
290
```python
291
291
# Run a semantic query that returns semantic answers
Copy file name to clipboardExpand all lines: articles/search/search-get-started-rag.md
+3-3Lines changed: 3 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -17,7 +17,7 @@ This quickstart shows you how to send queries to a Large Language Model (LLM) fo
17
17
18
18
- An Azure subscription. [Create one for free](https://azure.microsoft.com/free/).
19
19
20
-
-[Azure AI Search](search-create-service-portal.md), Basic tier or higher so that you can [enable semantic ranking](semantic-how-to-enable-disable.md). Region must be the same one used for Azure OpenAI.
20
+
-[Azure AI Search](search-create-service-portal.md), Basic tier or higher so that you can [enable semantic ranker](semantic-how-to-enable-disable.md). Region must be the same one used for Azure OpenAI.
21
21
22
22
-[Azure OpenAI](https://aka.ms/oai/access) resource with a deployment of `gpt-35-turbo`, `gpt-4`, or equivalent model, in the same region as Azure AI Search.
23
23
@@ -124,7 +124,7 @@ We recommend the hotels-sample-index, which can be created in minutes and runs o
124
124
125
125
1. Run the following query in [Search Explorer](search-explorer.md) to test your index: `hotels near the ocean with beach access and good views`.
126
126
127
-
Output should look similar to the following example. Results that are returned directly from the search engine consist of fields and their verbatim values, along with metadata like a search score and a semantic ranking score and caption if you use semantic ranking.
127
+
Output should look similar to the following example. Results that are returned directly from the search engine consist of fields and their verbatim values, along with metadata like a search score and a semantic ranking score and caption if you use semantic ranker.
128
128
129
129
```
130
130
"@search.score": 5.600783,
@@ -183,7 +183,7 @@ This section uses Visual Studio Code and Python to call the chat completion APIs
183
183
AZURE_DEPLOYMENT_MODEL: str="gpt-35-turbo"
184
184
```
185
185
186
-
1. Run the following code to set query parameters. The query is a keyword search using semantic ranking. In a keyword search, the search engine returns up to 50 matches, but only the top 5 are provided to the model. If you can't [enable semantic ranking](semantic-how-to-enable-disable.md) on your search service, set the value to false.
186
+
1. Run the following code to set query parameters. The query is a keyword search using semantic ranking. In a keyword search, the search engine returns up to 50 matches, but only the top 5 are provided to the model. If you can't [enable semantic rankersemantic-how-to-enable-disable.md) on your search service, set the value to false.
187
187
188
188
```python
189
189
# Set query parameters for grounding the conversation on your search index
Copy file name to clipboardExpand all lines: articles/search/search-get-started-semantic.md
+7-7Lines changed: 7 additions & 7 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,7 +1,7 @@
1
1
---
2
2
title: 'Quickstart: semantic ranking'
3
3
titleSuffix: Azure AI Search
4
-
description: Change an existing index to use semantic ranking.
4
+
description: Change an existing index to use semantic ranker.
5
5
author: HeidiSteen
6
6
manager: nitinme
7
7
ms.author: heidist
@@ -16,9 +16,9 @@ ms.date: 03/11/2024
16
16
17
17
# Quickstart: Semantic ranking with .NET or Python
18
18
19
-
In Azure AI Search, [semantic ranking](semantic-search-overview.md) is query-side functionality that uses machine reading comprehension from Microsoft to rescore search results, promoting the most semantically relevant matches to the top of the list. Depending on the content and the query, semantic ranking can [significantly improve search relevance](https://techcommunity.microsoft.com/t5/azure-ai-services-blog/azure-cognitive-search-outperforming-vector-search-with-hybrid/ba-p/3929167), with minimal work for the developer.
19
+
In Azure AI Search, [semantic ranker](semantic-search-overview.md) is query-side functionality that uses machine reading comprehension from Microsoft to rescore search results, promoting the most semantically relevant matches to the top of the list. Depending on the content and the query, semantic ranking can [significantly improve search relevance](https://techcommunity.microsoft.com/t5/azure-ai-services-blog/azure-cognitive-search-outperforming-vector-search-with-hybrid/ba-p/3929167), with minimal work for the developer.
20
20
21
-
This quickstart walks you through the index and query modifications that invoke semantic ranking.
21
+
This quickstart walks you through the index and query modifications that invoke semantic ranker.
22
22
23
23
> [!NOTE]
24
24
> Looking for an Azure AI Search solution with ChatGPT interaction? See [this demo](https://github.com/Azure-Samples/azure-search-openai-demo/blob/main/README.md) or [this accelerator](https://github.com/Azure-Samples/chat-with-your-data-solution-accelerator) for details.
@@ -27,7 +27,7 @@ This quickstart walks you through the index and query modifications that invoke
27
27
28
28
+ An Azure account with an active subscription. [Create an account for free](https://azure.microsoft.com/free/).
29
29
30
-
+ Azure AI Search, at Basic tier or higher, with [semantic ranking enabled](semantic-how-to-enable-disable.md).
30
+
+ Azure AI Search, at Basic tier or higher, with [semantic ranker enabled](semantic-how-to-enable-disable.md).
31
31
32
32
+ An API key and search service endpoint. Sign in to the [Azure portal](https://portal.azure.com) and [find your search service](https://portal.azure.com/#blade/HubsExtension/BrowseResourceBlade/resourceType/Microsoft.Search%2FsearchServices).
33
33
@@ -39,11 +39,11 @@ This quickstart walks you through the index and query modifications that invoke
39
39
40
40
## Add semantic ranking
41
41
42
-
To use semantic ranking, add a *semantic configuration* to a search index, and add parameters to a query. If you have an existing index, you can make these changes without having to reindex your content because there's no impact on the structure of your searchable content.
42
+
To use semantic ranker, add a *semantic configuration* to a search index, and add parameters to a query. If you have an existing index, you can make these changes without having to reindex your content because there's no impact on the structure of your searchable content.
43
43
44
44
+ A semantic configuration sets a priority order for fields that contribute a title, keywords, and content used in semantic reranking. Field prioritization allows for faster processing.
45
45
46
-
+ Queries that invoke semantic ranking include parameters for query type and whether captions and answers are returned. You can add these parameters to your existing query logic. There's no conflict with other parameters.
46
+
+ Queries that invoke semantic ranker include parameters for query type and whether captions and answers are returned. You can add these parameters to your existing query logic. There's no conflict with other parameters.
47
47
48
48
### [**.NET**](#tab/dotnet)
49
49
@@ -63,7 +63,7 @@ You can find and manage resources in the portal, using the **All resources** or
63
63
64
64
## Next steps
65
65
66
-
In this quickstart, you learned how to invoke semantic ranking on an existing index. We recommend trying semantic ranking on your own indexes as a next step. However, if you want to continue with demos, visit the following link.
66
+
In this quickstart, you learned how to invoke semantic ranker on an existing index. We recommend trying semantic ranker on your own indexes as a next step. However, if you want to continue with demos, visit the following link.
67
67
68
68
> [!div class="nextstepaction"]
69
69
> [Tutorial: Add search to web apps](tutorial-csharp-overview.md)
Copy file name to clipboardExpand all lines: articles/search/search-get-started-vector.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -30,7 +30,7 @@ If you don't have an Azure subscription, create a [free account](https://azure.m
30
30
31
31
Most existing services support vector search. For a small subset of services created prior to January 2019, an index that contains vector fields fails on creation. In this situation, a new service must be created.
32
32
33
-
- Optionally, to run the query example that invokes [semantic reranking](semantic-search-overview.md), your search service must be the Basic tier or higher, with [semantic ranking enabled](semantic-how-to-enable-disable.md).
33
+
- Optionally, to run the query example that invokes [semantic reranking](semantic-search-overview.md), your search service must be the Basic tier or higher, with [semantic ranker enabled](semantic-how-to-enable-disable.md).
34
34
35
35
- Optionally, an [Azure OpenAI](https://aka.ms/oai/access) resource with a deployment of `text-embedding-ada-002`. The source `.rest` file includes an optional step for generating new text embeddings, but we provide pregenerated embeddings so that you can omit this dependency.
Copy file name to clipboardExpand all lines: articles/search/search-region-support.md
+8-23Lines changed: 8 additions & 23 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -27,30 +27,15 @@ This article identifies the cloud regions in which Azure AI Search is available.
27
27
|[Azure OpenAI integration](vector-search-integrated-vectorization.md)| Refers to skills and vectorizers that make internal calls to deployed embedding and chat models on Azure OpenAI. Check [Azure OpenAI model region availability](/azure/ai-services/openai/concepts/models#model-summary-table-and-region-availability) for the most current list of regions for each embedding and chat model. Specific Azure OpenAI models are in fewer regions, so be sure to check for joint regional availability before installing.|
28
28
|[Azure AI Studio integration](vector-search-integrated-vectorization-ai-studio.md)| Refers to skills and vectorizers that make internal calls to the models hosted in the model catalog. Check [Azure AI Studio region availability](/azure/ai-studio/reference/region-support) for the most current list of regions. |
29
29
|[Azure AI Vision 4.0 multimodal APIs for image vectorization](search-get-started-portal-image-search.md)| Refers to skills and vectorizers that call the multimodal embedding API. Check the [Azure AI Vision region list](/azure/ai-services/computer-vision/overview-image-analysis#region-availability) for joint regional availability. |
30
-
|[Semantic ranking](semantic-search-overview.md)| Takes a dependency on Microsoft-hosted models in specific regions. Regional support is noted in this article. |
31
-
32
-
<!-- Each cloud region noted in this article includes a column indicating support for the following features.
33
-
34
-
- [Semantic ranking](semantic-search-overview.md) depends on models hosted in specific regions.
35
-
- [AI enrichment](cognitive-search-concept-intro.md) refers to skills and vectorizers that make internal calls to Azure AI and Azure OpenAI. Integration requires that Azure AI Search coexist with an [Azure AI multi-service account](/azure/ai-services/multi-service-resource) in the same physical region.
36
-
- [Availability zones](search-reliability.md#availability-zone-support) are an Azure platform capability that divides a region's data centers into distinct physical location groups to provide high-availability, within the same region.
37
-
38
-
We recommend that you check [Azure AI Studio region availability](/azure/ai-studio/reference/region-support) and [Azure OpenAI model region availability](/azure/reliability/availability-zones-service-support#azure-regions-with-availability-zone-support) for the most current list of regions for those features.
39
-
40
-
Also, if you plan to use Azure AI Vision 4.0 multimodal APIs for image vectorization, it's available in a reduced list of regions. [Check the Azure AI Vision region list for multimodal embeddings](/azure/ai-services/computer-vision/overview-image-analysis#region-availability) and be sure to create both your Azure AI multi-service account and Azure AI Search service in one of those supported regions.
41
-
42
-
> [!NOTE]
43
-
> Higher capacity partitions became available in selected regions starting in April 2024. A second wave of higher capacity partitions released in May 2024. Currently, there are just a few regions that *don't* offer higher capacity patitions, and those are indicated in footnotes.
44
-
>
45
-
> If you're using an older search service, consider creating a new search service in a supported region to benefit from more capacity at the same billing rate as before. For more information, see [Service limits](search-limits-quotas-capacity.md#service-limits) and [How to check service creation date](vector-search-index-size.md#how-to-check-service-creation-date). -->
30
+
|[Semantic ranker](semantic-search-overview.md)| Takes a dependency on Microsoft-hosted models in specific regions. Regional support is noted in this article. |
46
31
47
32
## Azure Public regions
48
33
49
34
You can create an Azure AI Search resource in any of the following Azure public regions. Almost all of these regions support [higher capacity tiers](search-limits-quotas-capacity.md#service-limits). Exceptions are noted where they apply.
50
35
51
36
### Americas
52
37
53
-
| Region | AI integration | Semantic ranking| Availability zones |
38
+
| Region | AI integration | Semantic ranker| Availability zones |
54
39
|--|--|--|--|
55
40
| Brazil South | ✅ | ✅ ||
56
41
| Canada Central | ✅ | ✅ | ✅ |
@@ -71,7 +56,7 @@ You can create an Azure AI Search resource in any of the following Azure public
71
56
72
57
### Europe
73
58
74
-
| Region | AI integration | Semantic ranking| Availability zones |
59
+
| Region | AI integration | Semantic ranker| Availability zones |
75
60
|--|--|--|--|
76
61
| North Europe | ✅ | ✅ | ✅ |
77
62
| West Europe <sup>1, 2</sup>| ✅ | ✅ | ✅ |
@@ -93,7 +78,7 @@ You can create an Azure AI Search resource in any of the following Azure public
93
78
94
79
### Middle East
95
80
96
-
| Region | AI integration | Semantic ranking| Availability zones |
81
+
| Region | AI integration | Semantic ranker| Availability zones |
97
82
|--|--|--|--|
98
83
| Israel Central <sup>2</sup> ||| ✅ |
99
84
| Qatar Central <sup>1, 2</sup> ||| ✅ |
@@ -105,13 +90,13 @@ You can create an Azure AI Search resource in any of the following Azure public
105
90
106
91
### Africa
107
92
108
-
| Region | AI integration | Semantic ranking| Availability zones |
93
+
| Region | AI integration | Semantic ranker| Availability zones |
109
94
|--|--|--|--|
110
95
| South Africa North | ✅ || ✅ |
111
96
112
97
### Asia Pacific
113
98
114
-
| Region | AI integration | Semantic ranking| Availability zones |
99
+
| Region | AI integration | Semantic ranker| Availability zones |
115
100
|--|--|--|--|
116
101
| Australia East | ✅ | ✅ | ✅ |
117
102
| Australia Southeast || ✅ ||
@@ -131,7 +116,7 @@ You can create an Azure AI Search resource in any of the following Azure public
131
116
132
117
## Azure Government regions
133
118
134
-
| Region | AI integration | Semantic ranking| Availability zones |
119
+
| Region | AI integration | Semantic ranker| Availability zones |
135
120
|--|--|--|--|
136
121
| Arizona | ✅ | ✅ ||
137
122
| Texas ||||
@@ -141,7 +126,7 @@ You can create an Azure AI Search resource in any of the following Azure public
141
126
142
127
## Azure operated by 21Vianet
143
128
144
-
| Region | AI integration | Semantic ranking| Availability zones |
129
+
| Region | AI integration | Semantic ranker| Availability zones |
Copy file name to clipboardExpand all lines: articles/search/semantic-answers.md
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -128,7 +128,7 @@ Within @search.answers:
128
128
129
129
+**"score"** is a confidence score that reflects the strength of the answer. If there are multiple answers in the response, this score is used to determine the order. Top answers and top captions can be derived from different search documents, where the top answer originates from one document, and the top caption from another, but in general the same documents appear in the top positions within each array.
130
130
131
-
Answers are followed by the **"value"** array, which always includes scores, captions, and any fields that are retrievable by default. If you specified the select parameter, the "value" array is limited to the fields that you specified. See [Configure semantic ranking](semantic-how-to-configure.md) for details.
131
+
Answers are followed by the **"value"** array, which always includes scores, captions, and any fields that are retrievable by default. If you specified the select parameter, the "value" array is limited to the fields that you specified. See [Configure semantic ranker](semantic-how-to-configure.md) for details.
132
132
133
133
## Tips for producing high-quality answers
134
134
@@ -144,4 +144,4 @@ For best results, return semantic answers on a document corpus having the follow
0 commit comments