def create_or_update_skillset()

in demo-python/code/custom-vectorizer/scripts/setup_search_service.py [0:0]

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

def create_or_update_skillset(search_indexer_client: SearchIndexerClient, custom_vectorizer_url: str):
    split_skill = SplitSkill(  
        description="Split skill to chunk documents",  
        text_split_mode="pages",  
        context="/document",  
        maximum_page_length=300,  
        page_overlap_length=20,  
        inputs=[  
            InputFieldMappingEntry(name="text", source="/document/content"),  
        ],  
        outputs=[  
            OutputFieldMappingEntry(name="textItems", target_name="pages")  
        ],  
    )  
    
    embedding_skill = WebApiSkill(  
        description="Skill to generate embeddings via a custom endpoint",  
        context="/document/pages/*",
        uri=custom_vectorizer_url, 
        inputs=[
            InputFieldMappingEntry(name="text", source="/document/pages/*"),  
        ],  
        outputs=[  
            OutputFieldMappingEntry(name="vector", target_name="vector")  
        ],
    )  
    
    index_projections = SearchIndexerIndexProjections(  
        selectors=[  
            SearchIndexerIndexProjectionSelector(  
                target_index_name=sample_index_name,  
                parent_key_field_name="parent_id",  
                source_context="/document/pages/*",  
                mappings=[  
                    InputFieldMappingEntry(name="chunk", source="/document/pages/*"),  
                    InputFieldMappingEntry(name="vector", source="/document/pages/*/vector"),  
                    InputFieldMappingEntry(name="title", source="/document/metadata_storage_name"),  
                ],  
            ),  
        ],  
        parameters=SearchIndexerIndexProjectionsParameters(  
            projection_mode=IndexProjectionMode.SKIP_INDEXING_PARENT_DOCUMENTS  
        ),  
    )  
    
    skillset = SearchIndexerSkillset(  
        name=sample_skillset_name,  
        description="Skillset to chunk documents and generating embeddings",  
        skills=[split_skill, embedding_skill],  
        index_projections=index_projections,  
    )
    result = search_indexer_client.create_or_update_skillset(skillset)