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/search-get-started-rag.md
+30-4Lines changed: 30 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -47,16 +47,16 @@ Requests to the search endpoint must be authenticated and authorized. You can us
47
47
48
48
1. On the left menu, select **Settings** > **Keys**, and then select either **Role-based access control** or **Both**.
49
49
50
-
1. On the left menu, select **Access control (IAM)**.
51
-
52
50
1. Assign roles:
53
51
52
+
1. On the left menu, select **Access control (IAM)**.
53
+
54
54
1. On Azure AI Search, add two role assignments for the Azure OpenAI managed identity:
55
55
56
56
-**Search Index Data Reader**
57
57
-**Search Service Contributor**
58
58
59
-
1. On Azure OpenAI, assign yourself to a role. The code for this quickstart runs locally. Requests to Azure OpenAI originate from your system:
59
+
1. On Azure OpenAI, select **Access control (IAM)** to assign yourself to a role. The code for this quickstart runs locally. Requests to Azure OpenAI originate from your system:
60
60
61
61
-**Cognitive Services OpenAI User**
62
62
@@ -115,8 +115,32 @@ We recommend the hotels-sample-index, which can be created in minutes and runs o
115
115
116
116
1. Run the following query to test your index: `hotels near the ocean with beach access and good views`.
117
117
118
+
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.
119
+
120
+
```
121
+
"@search.score": 5.600783,
122
+
"@search.rerankerScore": 2.4191176891326904,
123
+
"@search.captions": [
124
+
{
125
+
"text": "Ocean Breeze Motel. Budget. pool\r\nair conditioning\r\nbar. Oceanfront hotel overlooking the beach features rooms with a private balcony and 2 indoor and outdoor pools. Various shops and art entertainment are on the boardwalk, just steps away..",
126
+
"highlights": "Ocean Breeze Motel. Budget.<em> pool\r\nair conditioning\r\nbar. O</em>ceanfront hotel overlooking the beach features rooms with a private balcony and 2 indoor and outdoor pools. Various shops and art entertainment are on the boardwalk, just steps away."
127
+
}
128
+
],
129
+
"HotelId": "41",
130
+
"HotelName": "Ocean Breeze Motel",
131
+
"Description": "Oceanfront hotel overlooking the beach features rooms with a private balcony and 2 indoor and outdoor pools. Various shops and art entertainment are on the boardwalk, just steps away.",
132
+
"Category": "Budget",
133
+
"Tags": [
134
+
"pool",
135
+
"air conditioning",
136
+
"bar"
137
+
],
138
+
```
139
+
118
140
## Get service endpoints
119
141
142
+
In the remaining sections, you set up API calls to Azure OpenAI and Azure AI Search. Get the service endpoints so that you can provide them as variables in your code.
143
+
120
144
1. Sign in to the [Azure portal](https://portal.azure.com).
121
145
122
146
1. [Find your search service](https://portal.azure.com/#blade/HubsExtension/BrowseResourceBlade/resourceType/Microsoft.Search%2FsearchServices).
@@ -129,7 +153,9 @@ We recommend the hotels-sample-index, which can be created in minutes and runs o
129
153
130
154
## Set up the query and chat thread
131
155
132
-
This section uses Visual Studio Code and Python to call the chat APIs on Azure OpenAI.
156
+
This section uses Visual Studio Code and Python to call the chat completion APIs on Azure OpenAI.
157
+
158
+
1. Start Visual Studio Code and [open the .ipynb file](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-RAG) or create a new Python file.
0 commit comments