Fix Azure Search validation errors by removing unsupported fields

Co-authored-by: owndev <69784886+owndev@users.noreply.github.com>

Author: Copilot

docs/azure-ai-integration.md

@@ -55,9 +55,6 @@ AZURE_SEARCH_ENDPOINT="https://your-search-service.search.windows.net"
 # Azure Search index name containing the documents
 AZURE_SEARCH_INDEX_NAME="your-index-name"
 
-# Azure Search project resource ID (optional)
-AZURE_SEARCH_PROJECT_RESOURCE_ID="your-project-resource-id"
-
 # Azure Search API key (if using api_key authentication)
 AZURE_SEARCH_KEY="your-search-api-key"
 
@@ -67,12 +64,6 @@ AZURE_SEARCH_AUTHENTICATION_TYPE="system_assigned_managed_identity"
 # Semantic configuration name for Azure Search
 AZURE_SEARCH_SEMANTIC_CONFIGURATION="azureml-default"
 
-# Azure Search embedding endpoint (optional)
-AZURE_SEARCH_EMBEDDING_ENDPOINT="your-embedding-endpoint"
-
-# Azure Search embedding API key (optional)
-AZURE_SEARCH_EMBEDDING_KEY="your-embedding-key"
-
 # Query type for Azure Search
 AZURE_SEARCH_QUERY_TYPE="vectorSimpleHybrid"
 
@@ -104,15 +95,43 @@ Configure Azure Search by setting the following environment variables:
 
 #### Optional Settings:
 
-- **AZURE_SEARCH_PROJECT_RESOURCE_ID**: Project resource ID
 - **AZURE_SEARCH_SEMANTIC_CONFIGURATION**: Semantic configuration name
-- **AZURE_SEARCH_EMBEDDING_ENDPOINT**: Embedding service endpoint
-- **AZURE_SEARCH_EMBEDDING_KEY**: Embedding service API key
 - **AZURE_SEARCH_QUERY_TYPE**: Query type (`vectorSimpleHybrid`, `vector`, `semantic`)
 - **AZURE_SEARCH_IN_SCOPE**: Limit to indexed documents only
 - **AZURE_SEARCH_ROLE_INFORMATION**: Role information for responses
 - **AZURE_SEARCH_STRICTNESS**: Strictness level (1-5)
-- **AZURE_SEARCH_TOP_N_DOCUMENTS**: Number of documents to retrieve
+- **AZURE_SEARCH_TOP_N_DOCUMENTS**: Number of documents to retrieve
+
+#### Example Generated Data Sources Configuration:
+
+When Azure Search is configured, requests to Azure AI will automatically include:
+
+```json
+{
+  "model": "gpt-4o",
+  "messages": [...],
+  "data_sources": [
+    {
+      "type": "azure_search",
+      "parameters": {
+        "filter": null,
+        "endpoint": "https://your-search-service.search.windows.net",
+        "index_name": "your-index-name",
+        "authentication": {
+          "type": "system_assigned_managed_identity",
+          "key": null
+        },
+        "query_type": "vectorSimpleHybrid",
+        "in_scope": false,
+        "role_information": "You are an AI assistant.",
+        "strictness": 5,
+        "top_n_documents": 20,
+        "semantic_configuration": "azureml-default"
+      }
+    }
+  ]
+}
+```
 
 > [!TIP]  
 > To use **Azure OpenAI** and other **Azure AI** models **simultaneously**, you can use the following URL: `https://<your project>.services.ai.azure.com/models/chat/completions?api-version=2024-05-01-preview`

pipelines/azure/azure_ai_foundry.py

@@ -187,11 +187,6 @@ class Valves(BaseModel):
             description="Azure Search index name for RAG",
         )
 
-        AZURE_SEARCH_PROJECT_RESOURCE_ID: str = Field(
-            default=os.getenv("AZURE_SEARCH_PROJECT_RESOURCE_ID", ""),
-            description="Azure Search project resource ID",
-        )
-
         AZURE_SEARCH_KEY: EncryptedStr = Field(
             default=os.getenv("AZURE_SEARCH_KEY", ""),
             description="Azure Search API key",
@@ -209,16 +204,6 @@ class Valves(BaseModel):
             description="Azure Search semantic configuration name",
         )
 
-        AZURE_SEARCH_EMBEDDING_ENDPOINT: str = Field(
-            default=os.getenv("AZURE_SEARCH_EMBEDDING_ENDPOINT", ""),
-            description="Azure Search embedding endpoint URL",
-        )
-
-        AZURE_SEARCH_EMBEDDING_KEY: EncryptedStr = Field(
-            default=os.getenv("AZURE_SEARCH_EMBEDDING_KEY", ""),
-            description="Azure Search embedding API key",
-        )
-
         AZURE_SEARCH_QUERY_TYPE: str = Field(
             default=os.getenv("AZURE_SEARCH_QUERY_TYPE", "vectorSimpleHybrid"),
             description="Azure Search query type (vectorSimpleHybrid, vector, semantic)",
@@ -339,7 +324,7 @@ def get_azure_search_data_sources(self) -> Optional[List[Dict[str, Any]]]:
         ):
             auth_config["key"] = self.valves.AZURE_SEARCH_KEY.get_decrypted()
 
-        # Build the data source configuration
+        # Build the data source configuration with only officially supported parameters
         data_source = {
             "type": "azure_search",
             "parameters": {
@@ -355,40 +340,12 @@ def get_azure_search_data_sources(self) -> Optional[List[Dict[str, Any]]]:
             },
         }
 
-        # Add optional project resource ID if configured
-        if self.valves.AZURE_SEARCH_PROJECT_RESOURCE_ID:
-            data_source["parameters"]["project_resource_id"] = (
-                self.valves.AZURE_SEARCH_PROJECT_RESOURCE_ID
-            )
-
         # Add semantic configuration if configured
         if self.valves.AZURE_SEARCH_SEMANTIC_CONFIGURATION:
             data_source["parameters"]["semantic_configuration"] = (
                 self.valves.AZURE_SEARCH_SEMANTIC_CONFIGURATION
             )
 
-        # Add embedding configuration if configured
-        if self.valves.AZURE_SEARCH_EMBEDDING_ENDPOINT:
-            data_source["parameters"]["embeddingEndpoint"] = (
-                self.valves.AZURE_SEARCH_EMBEDDING_ENDPOINT
-            )
-            data_source["parameters"]["embedding_dependency"] = None
-
-        if self.valves.AZURE_SEARCH_EMBEDDING_KEY:
-            data_source["parameters"]["embeddingKey"] = (
-                self.valves.AZURE_SEARCH_EMBEDDING_KEY.get_decrypted()
-            )
-
-        # Add additional Azure Search parameters if using API key
-        if (
-            self.valves.AZURE_SEARCH_AUTHENTICATION_TYPE == "api_key"
-            and self.valves.AZURE_SEARCH_KEY
-        ):
-            data_source["parameters"]["key"] = (
-                self.valves.AZURE_SEARCH_KEY.get_decrypted()
-            )
-            data_source["parameters"]["indexName"] = self.valves.AZURE_SEARCH_INDEX_NAME
-
         return [data_source]
 
     def parse_models(self, models_str: str) -> List[str]: