Merge pull request yuanzhuangyuanzhuang#2 from wangyuantao/yuantw/oyd8c

Azure OpenAI On Your Data 2024-08-01-preview - Part 2

specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2024-08-01-preview/inference.json

@@ -377,9 +377,6 @@
           "Creates a completion based on Azure Search vector data, previous assistant message and user-assigned managed identity.": {
             "$ref": "./examples/chat_completions_azure_search_advanced.json"
           },
-          "Creates a completion for the provided AML index.": {
-            "$ref": "./examples/chat_completions_aml_index.json"
-          },
           "Creates a completion for the provided Azure Cosmos DB.": {
             "$ref": "./examples/chat_completions_cosmos_db.json"
           },
@@ -4410,7 +4407,6 @@
           "propertyName": "type",
           "mapping": {
             "azure_search": "#/components/schemas/azureSearchChatExtensionConfiguration",
-            "azure_ml_index": "#/components/schemas/azureMachineLearningIndexChatExtensionConfiguration",
             "azure_cosmos_db": "#/components/schemas/azureCosmosDBChatExtensionConfiguration",
             "elasticsearch": "#/components/schemas/elasticsearchChatExtensionConfiguration",
             "pinecone": "#/components/schemas/pineconeChatExtensionConfiguration"
@@ -4422,7 +4418,6 @@
         "description": "  A representation of configuration data for a single Azure OpenAI chat extension. This will be used by a chat\n  completions request that should use Azure OpenAI chat extensions to augment the response behavior.\n  The use of this configuration is compatible only with Azure OpenAI.",
         "enum": [
           "azure_search",
-          "azure_ml_index",
           "azure_cosmos_db",
           "elasticsearch",
           "pinecone"
@@ -4436,11 +4431,6 @@
               "value": "azure_search",
               "description": "Represents the use of Azure Search as an Azure OpenAI chat extension."
             },
-            {
-              "name": "azureMachineLearningIndex",
-              "value": "azure_ml_index",
-              "description": "Represents the use of Azure Machine Learning index as an Azure OpenAI chat extension."
-            },
             {
               "name": "azureCosmosDB",
               "value": "azure_cosmos_db",
@@ -4528,10 +4518,6 @@
             "description": "The configured strictness of the search relevance filtering. The higher of strictness, the higher of the precision but lower recall of the answer.",
             "format": "int32"
           },
-          "role_information": {
-            "type": "string",
-            "description": "Give the model instructions about how it should behave and any context it should reference when generating a response. You can describe the assistant's personality and tell it how to format responses. There's a 100 token limit for it, and it counts against the overall token limit."
-          },
           "endpoint": {
             "type": "string",
             "description": "The absolute endpoint path for the Azure Search resource to use.",
@@ -4562,6 +4548,9 @@
               },
               {
                 "$ref": "#/components/schemas/onYourDataDeploymentNameVectorizationSource"
+              },
+              {
+                "$ref": "#/components/schemas/onYourDataIntegratedVectorizationSource"
               }
             ]
           },
@@ -4660,103 +4649,6 @@
           ]
         }
       },
-      "azureMachineLearningIndexChatExtensionConfiguration": {
-        "required": [
-          "parameters"
-        ],
-        "description": "A specific representation of configurable options for Azure Machine Learning vector index when using it as an Azure\nOpenAI chat extension.",
-        "allOf": [
-          {
-            "$ref": "#/components/schemas/azureChatExtensionConfiguration"
-          },
-          {
-            "properties": {
-              "parameters": {
-                "$ref": "#/components/schemas/azureMachineLearningIndexChatExtensionParameters"
-              }
-            }
-          }
-        ],
-        "x-ms-discriminator-value": "azure_ml_index"
-      },
-      "azureMachineLearningIndexChatExtensionParameters": {
-        "required": [
-          "authentication",
-          "name",
-          "project_resource_id",
-          "version"
-        ],
-        "type": "object",
-        "properties": {
-          "authentication": {
-            "oneOf": [
-              {
-                "$ref": "#/components/schemas/onYourDataAccessTokenAuthenticationOptions"
-              },
-              {
-                "$ref": "#/components/schemas/onYourDataSystemAssignedManagedIdentityAuthenticationOptions"
-              },
-              {
-                "$ref": "#/components/schemas/onYourDataUserAssignedManagedIdentityAuthenticationOptions"
-              }
-            ]
-          },
-          "top_n_documents": {
-            "type": "integer",
-            "description": "The configured top number of documents to feature for the configured query.",
-            "format": "int32"
-          },
-          "max_search_queries": {
-            "type": "integer",
-            "description": "The max number of rewritten queries should be send to search provider for one user message. If not specified, the system will decide the number of queries to send.",
-            "format": "int32"
-          },
-          "allow_partial_result": {
-            "type": "boolean",
-            "default": false,
-            "description": "If specified as true, the system will allow partial search results to be used and the request fails if all the queries fail. If not specified, or specified as false, the request will fail if any search query fails."
-          },
-          "in_scope": {
-            "type": "boolean",
-            "description": "Whether queries should be restricted to use of indexed data."
-          },
-          "strictness": {
-            "maximum": 5,
-            "minimum": 1,
-            "type": "integer",
-            "description": "The configured strictness of the search relevance filtering. The higher of strictness, the higher of the precision but lower recall of the answer.",
-            "format": "int32"
-          },
-          "role_information": {
-            "type": "string",
-            "description": "Give the model instructions about how it should behave and any context it should reference when generating a response. You can describe the assistant's personality and tell it how to format responses. There's a 100 token limit for it, and it counts against the overall token limit."
-          },
-          "project_resource_id": {
-            "type": "string",
-            "description": "The resource ID of the Azure Machine Learning project."
-          },
-          "name": {
-            "type": "string",
-            "description": "The Azure Machine Learning vector index name."
-          },
-          "version": {
-            "type": "string",
-            "description": "The version of the Azure Machine Learning vector index."
-          },
-          "filter": {
-            "type": "string",
-            "description": "Search filter. Only supported if the Azure Machine Learning vector index is of type AzureSearch."
-          },
-          "include_contexts": {
-            "type": "array",
-            "description": "The included properties of the output context. If not specified, the default value is `citations` and `intent`.",
-            "items": {
-              "$ref": "#/components/schemas/onYourDataContextProperty"
-            }
-          }
-        },
-        "description": "Parameters for the Azure Machine Learning vector index chat extension."
-      },
       "azureCosmosDBChatExtensionConfiguration": {
         "required": [
           "parameters"
@@ -4816,10 +4708,6 @@
             "description": "The configured strictness of the search relevance filtering. The higher of strictness, the higher of the precision but lower recall of the answer.",
             "format": "int32"
           },
-          "role_information": {
-            "type": "string",
-            "description": "Give the model instructions about how it should behave and any context it should reference when generating a response. You can describe the assistant's personality and tell it how to format responses. There's a 100 token limit for it, and it counts against the overall token limit."
-          },
           "database_name": {
             "type": "string",
             "description": "The MongoDB vCore database name to use with Azure Cosmos DB."
@@ -4958,10 +4846,6 @@
             "description": "The configured strictness of the search relevance filtering. The higher of strictness, the higher of the precision but lower recall of the answer.",
             "format": "int32"
           },
-          "role_information": {
-            "type": "string",
-            "description": "Give the model instructions about how it should behave and any context it should reference when generating a response. You can describe the assistant's personality and tell it how to format responses. There's a 100 token limit for it, and it counts against the overall token limit."
-          },
           "endpoint": {
             "type": "string",
             "description": "The endpoint of Elasticsearch®.",
@@ -5118,10 +5002,6 @@
             "description": "The configured strictness of the search relevance filtering. The higher of strictness, the higher of the precision but lower recall of the answer.",
             "format": "int32"
           },
-          "role_information": {
-            "type": "string",
-            "description": "Give the model instructions about how it should behave and any context it should reference when generating a response. You can describe the assistant's personality and tell it how to format responses. There's a 100 token limit for it, and it counts against the overall token limit."
-          },
           "environment": {
             "type": "string",
             "description": "The environment name of Pinecone."
@@ -5436,6 +5316,7 @@
           "mapping": {
             "endpoint": "#/components/schemas/onYourDataEndpointVectorizationSource",
             "deployment_name": "#/components/schemas/onYourDataDeploymentNameVectorizationSource",
+            "integrated": "#/components/schemas/onYourDataIntegratedVectorizationSource",
             "model_id": "#/components/schemas/onYourDataModelIdVectorizationSource"
           }
         }
@@ -5446,6 +5327,7 @@
         "enum": [
           "endpoint",
           "deployment_name",
+          "integrated",
           "model_id"
         ],
         "x-ms-enum": {
@@ -5462,6 +5344,11 @@
               "value": "deployment_name",
               "description": "Represents an Ada model deployment name to use. This model deployment must be in the same Azure OpenAI resource, but\nOn Your Data will use this model deployment via an internal call rather than a public one, which enables vector\nsearch even in private networks."
             },
+            {
+              "name": "integrated",
+              "value": "integrated",
+              "description": "Represents the integrated vectorizer defined within the search resource."
+            },
             {
               "name": "modelId",
               "value": "model_id",
@@ -5532,6 +5419,15 @@
         ],
         "x-ms-discriminator-value": "deployment_name"
       },
+      "onYourDataIntegratedVectorizationSource": {
+        "description": "Represents the integrated vectorizer defined within the search resource.",
+        "allOf": [
+          {
+            "$ref": "#/components/schemas/onYourDataVectorizationSource"
+          }
+        ],
+        "x-ms-discriminator-value": "integrated"
+      },
       "onYourDataModelIdVectorizationSource": {
         "required": [
           "model_id"
@@ -5602,6 +5498,11 @@
           "chunk_id": {
             "type": "string",
             "description": "The chunk ID of the citation."
+          },
+          "rerank_score": {
+            "type": "number",
+            "description": "The rerank score of the retrieved document.",
+            "format": "double"
           }
         },
         "description": "citation information for a chat completions response message."
@@ -5637,11 +5538,6 @@
                 "description": "The original search score of the retrieved document.",
                 "format": "double"
               },
-              "rerank_score": {
-                "type": "number",
-                "description": "The rerank score of the retrieved document.",
-                "format": "double"
-              },
               "filter_reason": {
                 "$ref": "#/components/schemas/filterReason",
                 "description": "Represents the rationale for filtering the document. If the document does not undergo filtering, this field will remain unset."
@@ -12082,4 +11978,4 @@
       }
     }
   }
-}
+}