Fix and do not deploy embeddings model if it is not needed.

Author: nick863

README.md

@@ -61,7 +61,7 @@ azd env set AZURE_AI_AGENT_MODEL_VERSION <MODEL_VERSION>
 ```
 
 #### How to configure Agent knowledge retrieval
-By default, the template deploys OpenAI's file search for agent's knowledge retrieval. An agent also can perform search using the search index, deployed in Azure AI Search resource. The semantic index search represents so-called hybrid search i.e. it uses LLM to search for the relevant context in the provided index as well as embedding similarity search. This index is built from the `embeddings.csv` file, containing the embeddings vectors, followed by the contexts.
+By default, the template deploys OpenAI's [file search](https://learn.microsoft.com/azure/ai-services/agents/how-to/tools/file-search?tabs=python&pivots=overview) for agent's knowledge retrieval. An agent also can perform search using the search index, deployed in Azure AI Search resource. The semantic index search represents so-called hybrid search i.e. it uses LLM to search for the relevant context in the provided index as well as embedding similarity search. This index is built from the `embeddings.csv` file, containing the embeddings vectors, followed by the contexts.
 To use index search, please set the local environment variable `USE_AZURE_AI_SEARCH_SERVICE` to `true` during the `azd up` command. In this case the Azure AI Search resource will be deployed and used.
 
 #### Logging

infra/main.bicep

@@ -138,7 +138,7 @@ var tags = { 'azd-env-name': environmentName }
 
 var agentID = !empty(aiAgentID) ? aiAgentID : ''
 
-var aiDeployments = [
+var aiChatModel = [
   {
     name: agentDeploymentName
     model: {
@@ -151,6 +151,8 @@ var aiDeployments = [
       capacity: agentDeploymentCapacity
     }
   }
+]
+var aiEmbeddingModel = [ 
   {
     name: embeddingDeploymentName
     model: {
@@ -165,6 +167,10 @@ var aiDeployments = [
   }
 ]
 
+var aiDeployments = concat(
+  aiChatModel,
+  useSearchService ? aiEmbeddingModel : [])
+
 //for container and app api
 param apiAppExists bool = false