def create_sample_skillset()

in demo-python/code/community-integration/ragas/lib/utils.py [0:0]

• 75 lines of code
• 1 McCabe index (conditional complexity)

def create_sample_skillset(
        search_indexer_client: SearchIndexerClient,
        index_name: str,
        azure_openai_endpoint: str,
        azure_openai_ada002_embedding_deployment: str,
        azure_openai_3_large_embedding_deployment: str,
        azure_openai_key: Optional[str] = None
    ):
    # Create a skillset  
    skillset_name = f"{index_name}-skillset"  
    
    split_skill = SplitSkill(  
        description="Split skill to chunk documents",  
        text_split_mode="pages",  
        context="/document",  
        maximum_page_length=2000,  
        page_overlap_length=500,  
        inputs=[  
            InputFieldMappingEntry(name="text", source="/document/content"),  
        ],  
        outputs=[  
            OutputFieldMappingEntry(name="textItems", target_name="pages")  
        ],  
    )  
    
    embedding_ada_002_skill = AzureOpenAIEmbeddingSkill(  
        description="Skill to generate ada 002 embeddings via Azure OpenAI",  
        context="/document/pages/*",  
        resource_uri=azure_openai_endpoint,  
        deployment_id=azure_openai_ada002_embedding_deployment,  
        api_key=azure_openai_key,
        model_name="text-embedding-ada-002",
        inputs=[  
            InputFieldMappingEntry(name="text", source="/document/pages/*"),  
        ],  
        outputs=[  
            OutputFieldMappingEntry(name="embedding", target_name="vector_ada002")  
        ],  
    )

    embedding_3_large_skill = AzureOpenAIEmbeddingSkill(  
        description="Skill to generate ada 002 embeddings via Azure OpenAI",  
        context="/document/pages/*",  
        resource_uri=azure_openai_endpoint,  
        deployment_id=azure_openai_3_large_embedding_deployment,  
        api_key=azure_openai_key,
        model_name="text-embedding-3-large",
        inputs=[  
            InputFieldMappingEntry(name="text", source="/document/pages/*"),  
        ],  
        outputs=[  
            OutputFieldMappingEntry(name="embedding", target_name="vector_3_large")  
        ],  
    )  
    
    index_projections = SearchIndexerIndexProjections(  
        selectors=[  
            SearchIndexerIndexProjectionSelector(  
                target_index_name=index_name,  
                parent_key_field_name="parent_id",  
                source_context="/document/pages/*",  
                mappings=[  
                    InputFieldMappingEntry(name="chunk", source="/document/pages/*"),  
                    InputFieldMappingEntry(name="vector_ada002", source="/document/pages/*/vector_ada002"),
                    InputFieldMappingEntry(name="vector_3_large", source="/document/pages/*/vector_3_large"),
                    InputFieldMappingEntry(name="title", source="/document/metadata_storage_name"),  
                ],  
            ),  
        ],  
        parameters=SearchIndexerIndexProjectionsParameters(  
            projection_mode=IndexProjectionMode.SKIP_INDEXING_PARENT_DOCUMENTS  
        ),  
    )  
    
    skillset = SearchIndexerSkillset(  
        name=skillset_name,  
        description="Skillset to chunk documents and generating embeddings",  
        skills=[split_skill, embedding_3_large_skill, embedding_ada_002_skill],  
        index_projections=index_projections,  
    )  
    
    return search_indexer_client.create_or_update_skillset(skillset)