Updated AR code samples to use GPT-5-mini

Author: haileytap

articles/search/includes/quickstarts/agentic-retrieval-csharp.md

@@ -113,8 +113,8 @@ To create and run the agentic retrieval pipeline:
     
                 string aoaiEmbeddingModel = "text-embedding-3-large";
                 string aoaiEmbeddingDeployment = "text-embedding-3-large";
-                string aoaiGptModel = "gpt-4.1-mini";
-                string aoaiGptDeployment = "gpt-4.1-mini";
+                string aoaiGptModel = "gpt-5-mini";
+                string aoaiGptDeployment = "gpt-5-mini";
     
                 string indexName = "earth-at-night";
                 string knowledgeSourceName = "earth-knowledge-source";
@@ -723,7 +723,7 @@ Console.WriteLine($"Knowledge source '{knowledgeSourceName}' created or updated
 
 ### Create a knowledge agent
 
-To target `earth-knowledge-source` and your `gpt-4.1-mini` deployment at query time, you need a knowledge agent. Add and run a code cell with the following code to define a knowledge agent named `earth-knowledge-agent`, which you previously specified using the `knowledgeAgentName` variable.
+To target `earth-knowledge-source` and your `gpt-5-mini` deployment at query time, you need a knowledge agent. Add and run a code cell with the following code to define a knowledge agent named `earth-knowledge-agent`, which you previously specified using the `knowledgeAgentName` variable.
 
 `RerankerThreshold` ensures semantic relevance by excluding responses with a reranker score of `2.5` or lower. Meanwhile, `Modality` is set to `AnswerSynthesis`, enabling natural-language answers that cite the retrieved documents.
 
@@ -832,7 +832,7 @@ The following code displays the response, activity, and results of the retrieval
 
 + `Response` provides a synthesized, LLM-generated answer to the query that cites the retrieved documents. When answer synthesis isn't enabled, this section contains content extracted directly from the documents.
 
-+ `Activity` tracks the steps that were taken during the retrieval process, including the subqueries generated by your `gpt-4.1-mini` deployment and the tokens used for semantic ranking, query planning, and answer synthesis.
++ `Activity` tracks the steps that were taken during the retrieval process, including the subqueries generated by your `gpt-5-mini` deployment and the tokens used for semantic ranking, query planning, and answer synthesis.
 
 + `Results` lists the documents that contributed to the response, each one identified by their `DocKey`.
 

articles/search/includes/quickstarts/agentic-retrieval-java.md

@@ -117,7 +117,7 @@ The sample in this quickstart works with the Java Runtime. Install a Java Develo
 
     ```plaintext
     AZURE_OPENAI_ENDPOINT=https://<your-ai-foundry-resource-name>.openai.azure.com/
-    AZURE_OPENAI_GPT_DEPLOYMENT=gpt-4.1-mini
+    AZURE_OPENAI_GPT_DEPLOYMENT=gpt-5-mini
     AZURE_OPENAI_EMBEDDING_DEPLOYMENT=text-embedding-3-large
     AZURE_SEARCH_ENDPOINT=https://<your-search-service-name>.search.windows.net
     AZURE_SEARCH_INDEX_NAME=agentic-retrieval-sample
@@ -167,7 +167,7 @@ The sample in this quickstart works with the Java Runtime. Install a Java Develo
         private static final String SEARCH_ENDPOINT;
         private static final String AZURE_OPENAI_ENDPOINT;
         private static final String AZURE_OPENAI_GPT_DEPLOYMENT;
-        private static final String AZURE_OPENAI_GPT_MODEL = "gpt-4.1-mini";
+        private static final String AZURE_OPENAI_GPT_MODEL = "gpt-5-mini";
         private static final String AZURE_OPENAI_EMBEDDING_DEPLOYMENT;
         private static final String AZURE_OPENAI_EMBEDDING_MODEL = "text-embedding-3-large";
         private static final String INDEX_NAME = "earth_at_night";
@@ -182,7 +182,7 @@ The sample in this quickstart works with the Java Runtime. Install a Java Develo
                 "https://contoso-agentic-search-service.search.windows.net");
             AZURE_OPENAI_ENDPOINT = getEnvVar(dotenv, "AZURE_OPENAI_ENDPOINT",
                 "https://contoso-proj-agentic-foundry-res.openai.azure.com/");
-            AZURE_OPENAI_GPT_DEPLOYMENT = getEnvVar(dotenv, "AZURE_OPENAI_GPT_DEPLOYMENT", "gpt-4.1-mini");
+            AZURE_OPENAI_GPT_DEPLOYMENT = getEnvVar(dotenv, "AZURE_OPENAI_GPT_DEPLOYMENT", "gpt-5-mini");
             AZURE_OPENAI_EMBEDDING_DEPLOYMENT = getEnvVar(dotenv, "AZURE_OPENAI_EMBEDDING_DEPLOYMENT", "text-embedding-3-large");
         }
         
@@ -1150,7 +1150,7 @@ try {
 
 ### Create a knowledge agent
 
-To connect Azure AI Search to your `gpt-4.1-mini` deployment and target the `earth_at_night` index at query time, you need a knowledge agent. The following code defines a knowledge agent named `earth-search-agent` that uses the agent definition to process queries and retrieve relevant documents from the `earth_at_night` index.
+To connect Azure AI Search to your `gpt-5-mini` deployment and target the `earth_at_night` index at query time, you need a knowledge agent. The following code defines a knowledge agent named `earth-search-agent` that uses the agent definition to process queries and retrieve relevant documents from the `earth_at_night` index.
 
 To ensure relevant and semantically meaningful responses, `defaultRerankerThreshold` is set to exclude responses with a reranker score of `2.5` or lower.
 
@@ -1324,13 +1324,13 @@ The output should include:
 
 + `Response` provides a text string of the most relevant documents (or chunks) in the search index based on the user query. As shown later in this quickstart, you can pass this string to an LLM for answer generation.
 
-+ `Activity` tracks the steps that were taken during the retrieval process, including the subqueries generated by your `gpt-4.1-mini` deployment and the tokens used for query planning and execution.
++ `Activity` tracks the steps that were taken during the retrieval process, including the subqueries generated by your `gpt-5-mini` deployment and the tokens used for query planning and execution.
 
 + `Results` lists the documents that contributed to the response, each one identified by their `DocKey`.
 
 ### Create the Azure OpenAI client
 
-To extend the retrieval pipeline from answer *extraction* to answer *generation*, set up the Azure OpenAI client to interact with your `gpt-4.1-mini` deployment.
+To extend the retrieval pipeline from answer *extraction* to answer *generation*, set up the Azure OpenAI client to interact with your `gpt-5-mini` deployment.
 
 ```java
 OpenAIAsyncClient openAIClient = new OpenAIClientBuilder()

articles/search/includes/quickstarts/agentic-retrieval-javascript.md

@@ -71,7 +71,7 @@ Although you can provide your own data, this quickstart uses [sample JSON docume
 
     ```plaintext
     AZURE_OPENAI_ENDPOINT=https://<your-ai-foundry-resource-name>.openai.azure.com/
-    AZURE_OPENAI_GPT_DEPLOYMENT=gpt-4.1-mini
+    AZURE_OPENAI_GPT_DEPLOYMENT=gpt-5-mini
     AZURE_OPENAI_EMBEDDING_DEPLOYMENT=text-embedding-3-large
     AZURE_SEARCH_ENDPOINT=https://<your-search-service-name>.search.windows.net
     AZURE_SEARCH_INDEX_NAME=agentic-retrieval-sample
@@ -92,8 +92,8 @@ Although you can provide your own data, this quickstart uses [sample JSON docume
     const config = {
         searchEndpoint: process.env.AZURE_SEARCH_ENDPOINT || "https://your-search-service.search.windows.net",
         azureOpenAIEndpoint: process.env.AZURE_OPENAI_ENDPOINT || "https://your-ai-foundry-resource.openai.azure.com/",
-        azureOpenAIGptDeployment: process.env.AZURE_OPENAI_GPT_DEPLOYMENT || "gpt-4.1-mini",
-        azureOpenAIGptModel: "gpt-4.1-mini",
+        azureOpenAIGptDeployment: process.env.AZURE_OPENAI_GPT_DEPLOYMENT || "gpt-5-mini",
+        azureOpenAIGptModel: "gpt-5-mini",
         azureOpenAIApiVersion: process.env.OPENAI_API_VERSION || "2025-03-01-preview",
         azureOpenAIEmbeddingDeployment: process.env.AZURE_OPENAI_EMBEDDING_DEPLOYMENT || "text-embedding-3-large",
         azureOpenAIEmbeddingModel: "text-embedding-3-large",
@@ -878,7 +878,7 @@ try {
 
 ### Create a knowledge agent
 
-To connect Azure AI Search to your `gpt-4.1-mini` deployment and target the `earth_at_night` index at query time, you need a knowledge agent. The following code defines a knowledge agent named `earth-search-agent` that uses the agent definition to process queries and retrieve relevant documents from the `earth_at_night` index.
+To connect Azure AI Search to your `gpt-5-mini` deployment and target the `earth_at_night` index at query time, you need a knowledge agent. The following code defines a knowledge agent named `earth-search-agent` that uses the agent definition to process queries and retrieve relevant documents from the `earth_at_night` index.
 
 To ensure relevant and semantically meaningful responses, `defaultRerankerThreshold` is set to exclude responses with a reranker score of `2.5` or lower.
 
@@ -1011,13 +1011,13 @@ The output should include:
 
 + `Response` provides a text string of the most relevant documents (or chunks) in the search index based on the user query. As shown later in this quickstart, you can pass this string to an LLM for answer generation.
 
-+ `Activity` tracks the steps that were taken during the retrieval process, including the subqueries generated by your `gpt-4.1-mini` deployment and the tokens used for query planning and execution.
++ `Activity` tracks the steps that were taken during the retrieval process, including the subqueries generated by your `gpt-5-mini` deployment and the tokens used for query planning and execution.
 
 + `Results` lists the documents that contributed to the response, each one identified by their `DocKey`.
 
 ### Create the Azure OpenAI client
 
-To extend the retrieval pipeline from answer *extraction* to answer *generation*, set up the Azure OpenAI client to interact with your `gpt-4.1-mini` deployment.
+To extend the retrieval pipeline from answer *extraction* to answer *generation*, set up the Azure OpenAI client to interact with your `gpt-5-mini` deployment.
 
 ```javascript
 const scope = "https://cognitiveservices.azure.com/.default";

articles/search/includes/quickstarts/agentic-retrieval-python.md

@@ -81,8 +81,8 @@ To install the packages and load the connections:
     aoai_endpoint = "PUT-YOUR-AOAI-FOUNDRY-URL-HERE"
     aoai_embedding_model = "text-embedding-3-large"
     aoai_embedding_deployment = "text-embedding-3-large"
-    aoai_gpt_model = "gpt-4.1-mini"
-    aoai_gpt_deployment = "gpt-4.1-mini"
+    aoai_gpt_model = "gpt-5-mini"
+    aoai_gpt_deployment = "gpt-5-mini"
     index_name = "earth-at-night"
     knowledge_source_name = "earth-knowledge-source"
     knowledge_agent_name = "earth-knowledge-agent"
@@ -191,7 +191,7 @@ print(f"Knowledge source '{knowledge_source_name}' created or updated successful
 
 ## Create a knowledge agent
 
-To target `earth-knowledge-source` and your `gpt-4.1-mini` deployment at query time, you need a knowledge agent. Add and run a code cell with the following code to define a knowledge agent named `earth-knowledge-agent`, which you previously specified using the `knowledge_agent_name` variable.
+To target `earth-knowledge-source` and your `gpt-5-mini` deployment at query time, you need a knowledge agent. Add and run a code cell with the following code to define a knowledge agent named `earth-knowledge-agent`, which you previously specified using the `knowledge_agent_name` variable.
 
 `reranker_threshold` ensures semantic relevance by excluding responses with a reranker score of `2.5` or lower. Meanwhile, `modality` is set to `ANSWER_SYNTHESIS`, enabling natural-language answers that cite the retrieved documents.
 
@@ -315,7 +315,7 @@ The output should be similar to the following example, where:
 
 + `Response` provides a synthesized, LLM-generated answer to the query that cites the retrieved documents. When answer synthesis isn't enabled, this section contains content extracted directly from the documents.
 
-+ `Activity` tracks the steps that were taken during the retrieval process, including the subqueries generated by your `gpt-4.1-mini` deployment and the tokens used for semantic ranking, query planning, and answer synthesis.
++ `Activity` tracks the steps that were taken during the retrieval process, including the subqueries generated by your `gpt-5-mini` deployment and the tokens used for semantic ranking, query planning, and answer synthesis.
 
 + `Results` lists the documents that contributed to the response, each one identified by their `doc_key`.
 

articles/search/includes/quickstarts/agentic-retrieval-rest.md

@@ -70,8 +70,8 @@ To load the connections:
     @aoai-url = PUT-YOUR-AOAI-FOUNDRY-URL-HERE
     @aoai-embedding-model = text-embedding-3-large
     @aoai-embedding-deployment = text-embedding-3-large
-    @aoai-gpt-model = gpt-4.1-mini
-    @aoai-gpt-deployment = gpt-4.1-mini
+    @aoai-gpt-model = gpt-5-mini
+    @aoai-gpt-deployment = gpt-5-mini
     @index-name = earth-at-night
     @knowledge-source-name = earth-knowledge-source
     @knowledge-agent-name = earth-knowledge-agent
@@ -232,7 +232,7 @@ POST {{search-url}}/knowledgesources?api-version={{api-version}}  HTTP/1.1
 
 ## Create a knowledge agent
 
-To target your `earth-knowledge-source` and `gpt-4.1-mini` deployment at query time, you need a knowledge agent. Use [Knowledge Agents - Create (REST API)](/rest/api/searchservice/knowledge-agents/create?view=rest-searchservice-2025-08-01-preview&preserve-view=true) to define an agent named `earth-knowledge-agent`, which you previously specified using the `@knowledge-agent-name` variable.
+To target your `earth-knowledge-source` and `gpt-5-mini` deployment at query time, you need a knowledge agent. Use [Knowledge Agents - Create (REST API)](/rest/api/searchservice/knowledge-agents/create?view=rest-searchservice-2025-08-01-preview&preserve-view=true) to define an agent named `earth-knowledge-agent`, which you previously specified using the `@knowledge-agent-name` variable.
 
 `knowledgeSources.rerankerThreshold` ensures semantic relevance by excluding responses with a reranker score of `2.5` or lower. Meanwhile, `outputConfiguration.modality` is set to `answerSynthesis`, enabling natural-language answers that cite the retrieved documents.
 
@@ -301,7 +301,7 @@ The output should be similar to the following JSON, where:
 
 + `response` provides a synthesized, LLM-generated answer to the query that cites the retrieved documents. When answer synthesis isn't enabled, this section contains content extracted directly from the documents.
 
-+ `activity` tracks the steps that were taken during the retrieval process, including the subqueries generated by your `gpt-4.1-mini` deployment and the tokens used for semantic ranking, query planning, and answer synthesis.
++ `activity` tracks the steps that were taken during the retrieval process, including the subqueries generated by your `gpt-5-mini` deployment and the tokens used for semantic ranking, query planning, and answer synthesis.
 
 + `references` lists the documents that contributed to the response, each one identified by their `docKey`.
 

articles/search/includes/quickstarts/agentic-retrieval-setup.md

@@ -85,7 +85,7 @@ To use agentic retrieval, you must deploy two Azure OpenAI models to your Azure
 
 + An embedding model for text-to-vector conversion. This quickstart uses `text-embedding-3-large`, but you can use any embedding model that supports the `text-embedding` task.
 
-+ A [supported chat completion model](../../search-agentic-retrieval-how-to-create.md#supported-models) for query planning and answer generation. This quickstart uses `gpt-4.1-mini`. Optionally, you can use one model for query planning and another model for answer generation, but this quickstart uses the same model for simplicity.
++ A [supported chat completion model](../../search-agentic-retrieval-how-to-create.md#supported-models) for query planning and answer generation. This quickstart uses `gpt-5-mini`. Optionally, you can use one model for query planning and another model for answer generation, but this quickstart uses the same model for simplicity.
 
 To deploy the Azure OpenAI models:
 
@@ -101,4 +101,4 @@ To deploy the Azure OpenAI models:
 
 1. Select **Deploy**.
 
-1. Repeat the previous steps, but this time, deploy **gpt-4.1-mini** from the model catalog.
+1. Repeat the previous steps, but this time, deploy **gpt-5-mini** from the model catalog.

articles/search/includes/quickstarts/agentic-retrieval-typescript.md

@@ -77,7 +77,7 @@ Although you can provide your own data, this quickstart uses [sample JSON docume
 
     ```plaintext
     AZURE_OPENAI_ENDPOINT=https://<your-ai-foundry-resource-name>.openai.azure.com/
-    AZURE_OPENAI_GPT_DEPLOYMENT=gpt-4.1-mini
+    AZURE_OPENAI_GPT_DEPLOYMENT=gpt-5-mini
     AZURE_OPENAI_EMBEDDING_DEPLOYMENT=text-embedding-3-large
     AZURE_SEARCH_ENDPOINT=https://<your-search-service-name>.search.windows.net
     AZURE_SEARCH_INDEX_NAME=agentic-retrieval-sample
@@ -114,8 +114,8 @@ Although you can provide your own data, this quickstart uses [sample JSON docume
     const config = {
         searchEndpoint: process.env.AZURE_SEARCH_ENDPOINT || "https://your-search-service.search.windows.net",
         azureOpenAIEndpoint: process.env.AZURE_OPENAI_ENDPOINT || "https://your-ai-foundry-resource.openai.azure.com/",
-        azureOpenAIGptDeployment: process.env.AZURE_OPENAI_GPT_DEPLOYMENT || "gpt-4.1-mini",
-        azureOpenAIGptModel: "gpt-4.1-mini",
+        azureOpenAIGptDeployment: process.env.AZURE_OPENAI_GPT_DEPLOYMENT || "gpt-5-mini",
+        azureOpenAIGptModel: "gpt-5-mini",
         azureOpenAIApiVersion: process.env.OPENAI_API_VERSION || "2025-03-01-preview",
         azureOpenAIEmbeddingDeployment: process.env.AZURE_OPENAI_EMBEDDING_DEPLOYMENT || "text-embedding-3-large",
         azureOpenAIEmbeddingModel: "text-embedding-3-large",
@@ -1079,7 +1079,7 @@ try {
 
 ### Create a knowledge agent
 
-To connect Azure AI Search to your `gpt-4.1-mini` deployment and target the `earth_at_night` index at query time, you need a knowledge agent. The following code defines a knowledge agent named `earth-search-agent` that uses the agent definition to process queries and retrieve relevant documents from the `earth_at_night` index.
+To connect Azure AI Search to your `gpt-5-mini` deployment and target the `earth_at_night` index at query time, you need a knowledge agent. The following code defines a knowledge agent named `earth-search-agent` that uses the agent definition to process queries and retrieve relevant documents from the `earth_at_night` index.
 
 To ensure relevant and semantically meaningful responses, `defaultRerankerThreshold` is set to exclude responses with a reranker score of `2.5` or lower.
 
@@ -1220,13 +1220,13 @@ The output should include:
 
 + `Response` provides a text string of the most relevant documents (or chunks) in the search index based on the user query. As shown later in this quickstart, you can pass this string to an LLM for answer generation.
 
-+ `Activity` tracks the steps that were taken during the retrieval process, including the subqueries generated by your `gpt-4.1-mini` deployment and the tokens used for query planning and execution.
++ `Activity` tracks the steps that were taken during the retrieval process, including the subqueries generated by your `gpt-5-mini` deployment and the tokens used for query planning and execution.
 
 + `Results` lists the documents that contributed to the response, each one identified by their `DocKey`.
 
 ### Create the Azure OpenAI client
 
-To extend the retrieval pipeline from answer *extraction* to answer *generation*, set up the Azure OpenAI client to interact with your `gpt-4.1-mini` deployment.
+To extend the retrieval pipeline from answer *extraction* to answer *generation*, set up the Azure OpenAI client to interact with your `gpt-5-mini` deployment.
 
 ```typescript
 const scope = "https://cognitiveservices.azure.com/.default";