Update readme and model

Author: BenConstable9

README.md

@@ -12,7 +12,7 @@ It is intended that the plugins and skills provided in this repository, are adap
 
 - `./text_2_sql` contains an three Multi-Shot implementations for Text2SQL generation and querying which can be used to answer questions backed by a database as a knowledge base. A **prompt based** and **vector based** approach are shown, both of which exhibit great performance in answering sql queries. Additionally, a further iteration on the vector based approach is shown which uses a **query cache** to further speed up generation.  With these plugins, your RAG application can now access and pull data from any SQL table exposed to it to answer questions.
 - `./image_processing` contains code for linking **Azure Document Intelligence** with AI Search to process complex documents with charts and images, and uses **multi-modal models (gpt4o)** to interpret and understand these. With this custom skill, the RAG application can **draw insights from complex charts** and images during the vector search. This function app also contains a **Semantic Text Chunking** method that aims to intelligently group similar sentences, retaining figures and tables together, whilst separating out distinct sentences.
-- `./deploy_ai_search` provides an easy Python based utility for deploying an index, indexer and corresponding skillset for AI Search and for Text2SQL.
+- `./deploy_ai_search_indexes` provides an easy Python based utility for deploying an index, indexer and corresponding skillset for AI Search and for Text2SQL.
 
 The above components have been successfully used on production RAG projects to increase the quality of responses.
 

deploy_ai_search/.env.example deploy_ai_search_indexes/.env.exampledeploy_ai_search/.env.example renamed to deploy_ai_search_indexes/.env.example

@@ -1,11 +1,6 @@
-
+# Environment variables for the deploying AI Search Indexes
 FunctionApp__Endpoint=<FunctionAppEndpoint>
 FunctionApp__Key=<FunctionAppKey>
-FunctionApp__LayoutAnalysis__FunctionName=layout_analysis
-FunctionApp__FigureAnalysis__FunctionName=figure_analysis
-FunctionApp__LayoutAndFigureMerger__FunctionName=layout_and_figure_merger
-FunctionApp__MarkUpCleaner__FunctionName=mark_up_cleaner
-FunctionApp__SemanticTextChunker__FunctionName=semantic_text_chunker
 FunctionApp__AppRegistrationResourceId=<App registration in form api://appRegistrationclientId if using identity based connections>
 IdentityType=key # system_assigned or user_assigned or key
 AIService__AzureSearchOptions__Endpoint=<AzureSearchEndpoint>

deploy_ai_search/README.md deploy_ai_search_indexes/README.mddeploy_ai_search/README.md renamed to deploy_ai_search_indexes/README.md

@@ -205,41 +205,6 @@ def function_app_app_registration_resource_id(self) -> str:
         """
         return os.environ.get("FunctionApp__AppRegistrationResourceId")
 
-    @property
-    def function_app_mark_up_cleaner_route(self) -> str:
-        """
-        This function returns function app data cleanup function name
-        """
-        return os.environ.get("FunctionApp__MarkUpCleaner__FunctionName")
-
-    @property
-    def function_app_semantic_text_chunker_route(self) -> str:
-        """
-        This function returns function app semantic text chunker name
-        """
-        return os.environ.get("FunctionApp__SemanticTextChunker__FunctionName")
-
-    @property
-    def function_app_layout_analysis_route(self) -> str:
-        """
-        This function returns function app adi name
-        """
-        return os.environ.get("FunctionApp__LayoutAnalysis__FunctionName")
-
-    @property
-    def function_app_figure_analysis_route(self) -> str:
-        """
-        This function returns function app figure analysis name
-        """
-        return os.environ.get("FunctionApp__FigureAnalysis__FunctionName")
-
-    @property
-    def function_app_layout_and_figure_merger_route(self) -> str:
-        """
-        This function returns function app layout and figure merger name
-        """
-        return os.environ.get("FunctionApp__LayoutAndFigureMerger__FunctionName")
-
     @property
     def open_ai_embedding_dimensions(self) -> str:
         """
@@ -257,29 +222,18 @@ def use_private_endpoint(self) -> bool:
         This function returns true if private endpoint is used
         """
         return (
-            os.environ.get("AIService__AzureSearchOptions__UsePrivateEndpoint").lower()
+            os.environ.get(
+                "AIService__AzureSearchOptions__UsePrivateEndpoint").lower()
             == "true"
         )
 
     def get_custom_skill_function_url(self, skill_type: str):
         """
         Get the function app url that is hosting the custom skill
         """
-        if skill_type == "mark_up_cleaner":
-            route = self.function_app_mark_up_cleaner_route
-        elif skill_type == "layout_analysis":
-            route = self.function_app_layout_analysis_route
-        elif skill_type == "figure_analysis":
-            route = self.function_app_figure_analysis
-        elif skill_type == "layout_and_figure_merger":
-            route = self.function_app_layout_and_figure_merger
-        elif skill_type == "semantic_text_chunker":
-            route = self.function_app_semantic_text_chunker_route
-        else:
-            raise ValueError(f"Invalid skill type: {skill_type}")
 
         full_url = (
-            f"{self.function_app_end_point}/api/{route}?code={self.function_app_key}"
+            f"{self.function_app_end_point}/api/{skill_type}?code={self.function_app_key}"
         )
 
         return full_url