{"id":19394,"date":"2026-09-23T05:41:10","date_gmt":"2026-09-23T05:41:10","guid":{"rendered":"https:\/\/www.examlabs.com\/certification\/?p=19394"},"modified":"2026-09-23T05:41:10","modified_gmt":"2026-09-23T05:41:10","slug":"snowflake-snowpro-specialty-gen-ai-ges-c01-practice-test-questions-and-exam-dumps-part-6-q101-120","status":"publish","type":"post","link":"https:\/\/www.examlabs.com\/certification\/snowflake-snowpro-specialty-gen-ai-ges-c01-practice-test-questions-and-exam-dumps-part-6-q101-120\/","title":{"rendered":"Snowflake SnowPro Specialty Gen AI GES-C01 Practice Test Questions and Exam Dumps Part 6 Q101-120"},"content":{"rendered":"

View Full <\/b>Snowflake SnowPro Specialty Gen AI GES-C01<\/b> Exam Dumps<\/b><\/a> and Practice Test Dumps<\/b><\/p>\n

 <\/p>\n

Question 101: Which Snowflake Cortex capability is designed to help search and retrieve relevant information from enterprise content?<\/b><\/p>\n

    \n
  1. <\/b> Cortex Analyst<\/span><\/li>\n
  2. <\/b> Cortex Search<\/span><\/li>\n
  3. <\/b> Document AI<\/span><\/li>\n
  4. <\/b> Semantic model<\/span><\/li>\n<\/ol>\n

    Correct Answer: 2. Cortex Search<\/b><\/p>\n

    Explanation:<\/b>
    \n<\/b>Cortex Search is designed to support search and retrieval over enterprise content. It can help applications locate relevant information using search capabilities suited to natural-language and content-retrieval scenarios. This makes it useful as part of enterprise search and RAG architectures where relevant source information must be identified before generation. Cortex Analyst addresses natural-language questions over structured business data, while Document AI focuses on document processing and extraction. A semantic model provides business meaning for structured analytics rather than serving as the primary enterprise content search capability.<\/span><\/p>\n

    Question 102: Which statement best describes the role of an LLM in a typical RAG architecture?<\/b><\/p>\n

      \n
    1. <\/b> It generates a response using the user request and retrieved context<\/span><\/li>\n
    2. <\/b> It permanently stores every retrieved document<\/span><\/li>\n
    3. <\/b> It replaces all source-data access controls<\/span><\/li>\n
    4. <\/b> It performs document indexing without any retrieval component<\/span><\/li>\n<\/ol>\n

      Correct Answer: 1. It generates a response using the user request and retrieved context<\/b><\/p>\n

      Explanation:<\/b>
      \n<\/b>In a typical RAG architecture, the language model is responsible for generating the final response after relevant information has been retrieved. The user request and retrieved context are supplied to the model along with applicable instructions. The model then uses these inputs to produce a natural-language response. The LLM is not responsible for replacing access controls or necessarily performing document indexing. Retrieval and generation are separate but complementary stages. The quality of the final response depends on factors including the relevance of retrieved information, prompt design, model capabilities, and appropriate application controls.<\/span><\/p>\n

      Question 103: What is the main purpose of an AI classification function?<\/b><\/p>\n

        \n
      1. <\/b> To convert every document into a vector<\/span><\/li>\n
      2. <\/b> To assign input content to one or more predefined categories<\/span><\/li>\n
      3. <\/b> To increase warehouse storage capacity<\/span><\/li>\n
      4. <\/b> To authenticate application users<\/span><\/li>\n<\/ol>\n

        Correct Answer: 2. To assign input content to one or more predefined categories<\/b><\/p>\n

        Explanation:<\/b>
        \n<\/b>Classification functions are used to assign content to predefined categories based on its characteristics. For example, an organization could classify customer messages into categories such as billing, technical support, complaints, or general inquiries. Classification is different from embedding, which represents content as vectors, and authentication, which controls user access. In Snowflake Cortex, AI classification capabilities can be incorporated into data workflows to process text at scale. The categories and instructions should be appropriate for the application’s use case, and generated classifications may still require validation depending on their business impact.<\/span><\/p>\n

        Question 104: What is one reason to use a lower temperature for some generative AI tasks?<\/b><\/p>\n

          \n
        1. <\/b> It can generally make responses less variable and more deterministic<\/span><\/li>\n
        2. <\/b> It guarantees that the model will use only verified facts<\/span><\/li>\n
        3. <\/b> It automatically improves retrieval accuracy<\/span><\/li>\n
        4. <\/b> It disables all model safety mechanisms<\/span><\/li>\n<\/ol>\n

          Correct Answer: 1. It can generally make responses less variable and more deterministic<\/b><\/p>\n

          Explanation:<\/b>
          \n<\/b>Temperature is a generation parameter that generally influences the variability of model outputs. Lower values tend to produce less variable responses, which can be useful for tasks where consistency is important. Higher values can allow more variation, which may be useful for creative applications. Temperature does not guarantee factual correctness and does not directly improve retrieval quality. It also does not disable or replace safety mechanisms. The appropriate setting depends on the application, and even a low-temperature model can produce inaccurate or unsupported information.<\/span><\/p>\n

          Question 105: Which scenario is most appropriate for using embeddings?<\/b><\/p>\n

            \n
          1. <\/b> Assigning database ownership privileges<\/span><\/li>\n
          2. <\/b> Finding semantically similar documents to a user’s natural-language query<\/span><\/li>\n
          3. <\/b> Changing a warehouse’s auto-suspend setting<\/span><\/li>\n
          4. <\/b> Creating a user password<\/span><\/li>\n<\/ol>\n

            Correct Answer: 2. Finding semantically similar documents to a user’s natural-language query<\/b><\/p>\n

            Explanation:<\/b>
            \n<\/b>Embeddings are useful when an application needs to compare the semantic characteristics of content. A common example is semantic search, where both a user’s query and documents are converted into vector representations. The system can then compare the vectors to identify content that is conceptually similar. Embeddings do not manage database privileges, warehouse configuration, or user passwords. Their value comes from representing meaning in a numerical form that can be used by similarity-based retrieval systems. The quality of the embedding model and the suitability of the content representation can significantly affect retrieval results.<\/span><\/p>\n

            Question 106: Which practice can help improve the quality of a RAG prompt?<\/b><\/p>\n

              \n
            1. <\/b> Include relevant retrieved context and clearly distinguish it from the user’s request and instructions<\/span><\/li>\n
            2. <\/b> Add as much unrelated information as possible<\/span><\/li>\n
            3. <\/b> Remove all instructions from the prompt<\/span><\/li>\n
            4. <\/b> Include conflicting requirements intentionally<\/span><\/li>\n<\/ol>\n

              Correct Answer: 1. Include relevant retrieved context and clearly distinguish it from the user’s request and instructions<\/b><\/p>\n

              Explanation:<\/b>
              \n<\/b>A well-designed RAG prompt should clearly communicate the task and provide relevant retrieved information as context. Separating instructions, user input, and retrieved material can help the model understand how each component should be used. Irrelevant information and conflicting instructions can make the task more ambiguous and potentially reduce response quality. Prompt design should also account for the application’s security and data-handling requirements. Providing useful context does not guarantee accuracy, but clear organization and focused instructions can help the model make better use of the information supplied by the retrieval stage.<\/span><\/p>\n

              Question 107: What is a major purpose of indexing content in a search system?<\/b><\/p>\n

                \n
              1. <\/b> To create structures that allow content to be efficiently searched and retrieved<\/span><\/li>\n
              2. <\/b> To permanently rewrite the original documents<\/span><\/li>\n
              3. <\/b> To remove all metadata from enterprise content<\/span><\/li>\n
              4. <\/b> To prevent semantic similarity calculations<\/span><\/li>\n<\/ol>\n

                Correct Answer: 1. To create structures that allow content to be efficiently searched and retrieved<\/b><\/p>\n

                Explanation:<\/b>
                \n<\/b>Indexing prepares content so that a search system can efficiently identify relevant information when users submit queries. Depending on the search architecture, indexes can support keyword matching, semantic retrieval, metadata filtering, or combinations of these techniques. Indexing does not normally rewrite the original source documents or require metadata to be removed. It also does not prevent vector similarity calculations. Effective indexing is an important part of scalable retrieval because searching directly through large volumes of unstructured content without suitable indexing can be inefficient. The index should reflect the retrieval strategy and characteristics of the source data.<\/span><\/p>\n

                Question 108: What should an application do if a generated response does not satisfy a required structured-output constraint?<\/b><\/p>\n

                  \n
                1. <\/b> Treat the response as automatically correct<\/span><\/li>\n
                2. <\/b> Ignore the formatting requirement<\/span><\/li>\n
                3. <\/b> Apply appropriate validation and handling for the invalid output<\/span><\/li>\n
                4. <\/b> Grant the model additional database permissions<\/span><\/li>\n<\/ol>\n

                  Correct Answer: 3. Apply appropriate validation and handling for the invalid output<\/b><\/p>\n

                  Explanation:<\/b>
                  \n<\/b>Generative models can sometimes produce output that does not conform exactly to an application’s requested structure. When structured data is consumed programmatically, the application should validate the response against the expected format and handle invalid results appropriately. Depending on the design, this could involve retrying with clearer instructions, rejecting the response, requesting correction, or routing the result for additional processing. Structured output capabilities can improve consistency but do not eliminate the need for appropriate validation. Database permissions are unrelated to whether a generated response satisfies a formatting constraint.<\/span><\/p>\n

                  Question 109: Which component provides business-specific meaning that can help interpret structured-data questions?<\/b><\/p>\n

                    \n
                  1. <\/b> Embedding vector<\/span><\/li>\n
                  2. <\/b> Semantic model<\/span><\/li>\n
                  3. <\/b> Document chunk<\/span><\/li>\n
                  4. <\/b> Temperature parameter<\/span><\/li>\n<\/ol>\n

                    Correct Answer: 2. Semantic model<\/b><\/p>\n

                    Explanation:<\/b>
                    \n<\/b>A semantic model provides business-oriented definitions and relationships for structured data. It can describe concepts such as measures, dimensions, entities, relationships, and business terminology. This information helps a natural-language analytics system understand what users mean when they ask questions about organizational data. An embedding vector serves as a numerical representation, a document chunk is a unit of retrievable content, and temperature influences generation variability. Semantic modeling is therefore particularly important when an organization wants natural-language questions to map accurately to structured analytical data.<\/span><\/p>\n

                    Question 110: Which situation can indicate that a RAG system has a retrieval problem rather than purely a generation problem?<\/b><\/p>\n

                      \n
                    1. <\/b> The retrieved sources are consistently irrelevant to the user’s question<\/span><\/li>\n
                    2. <\/b> The user interface contains too many buttons<\/span><\/li>\n
                    3. <\/b> The database has more tables than expected<\/span><\/li>\n
                    4. <\/b> The response font is difficult to read<\/span><\/li>\n<\/ol>\n

                      Correct Answer: 1. The retrieved sources are consistently irrelevant to the user’s question<\/b><\/p>\n

                      Explanation:<\/b>
                      \n<\/b>If the retrieval stage consistently returns information unrelated to the user’s question, the problem may originate in retrieval rather than generation. Possible causes include unsuitable embeddings, poor chunking, incorrect indexing, weak query representation, inappropriate filters, or retrieval configuration. The language model can only make effective use of the context it receives, so irrelevant retrieved information can limit the final answer. Retrieval should therefore be evaluated independently where possible. Separating retrieval evaluation from generation evaluation helps teams determine whether a problem originates before the information reaches the model or during response generation.<\/span><\/p>\n

                      Question 111: What is the purpose of summarization in a generative AI workflow?<\/b><\/p>\n

                        \n
                      1. <\/b> To reduce a larger body of information into a more concise representation<\/span><\/li>\n
                      2. <\/b> To assign database permissions<\/span><\/li>\n
                      3. <\/b> To convert all content into binary vectors<\/span><\/li>\n
                      4. <\/b> To eliminate the need for source documents<\/span><\/li>\n<\/ol>\n

                        Correct Answer: 1. To reduce a larger body of information into a more concise representation<\/b><\/p>\n

                        Explanation:<\/b>
                        \n<\/b>Summarization uses an AI model to produce a shorter representation of a larger body of information while attempting to preserve important meaning. It can be useful for business documents, reports, customer interactions, meeting notes, and other content where users need a concise overview. Summarization does not replace source documents and should not automatically be assumed to preserve every important detail. For important business or compliance scenarios, generated summaries may require validation against the original content. Snowflake Cortex language capabilities can support summarization workflows within data-processing environments.<\/span><\/p>\n

                        Question 112: Why is source freshness important for some enterprise AI applications?<\/b><\/p>\n

                          \n
                        1. <\/b> Because outdated information may produce responses that no longer reflect current business conditions<\/span><\/li>\n
                        2. <\/b> Because fresh data automatically eliminates hallucinations<\/span><\/li>\n
                        3. <\/b> Because freshness removes the need for authorization<\/span><\/li>\n
                        4. <\/b> Because old documents cannot be embedded<\/span><\/li>\n<\/ol>\n

                          Correct Answer: 1. Because outdated information may produce responses that no longer reflect current business conditions<\/b><\/p>\n

                          Explanation:<\/b>
                          \n<\/b>Some enterprise questions depend on information that changes frequently, such as policies, product information, operational status, pricing, or business metrics. If retrieval returns outdated information, the generated response may no longer accurately reflect current conditions. Source freshness can therefore be an important retrieval and governance consideration. Freshness does not guarantee that an answer is correct, nor does it replace access controls or other safeguards. Applications may use metadata, timestamps, source prioritization, indexing strategies, or business rules to help ensure that current and authoritative information receives appropriate consideration.<\/span><\/p>\n

                          Question 113: Which statement best describes a hallucination in generative AI?<\/b><\/p>\n

                            \n
                          1. <\/b> A response containing information that is unsupported, fabricated, or factually incorrect<\/span><\/li>\n
                          2. <\/b> A successful semantic search result<\/span><\/li>\n
                          3. <\/b> A correctly formatted structured response<\/span><\/li>\n
                          4. <\/b> A valid user authentication event<\/span><\/li>\n<\/ol>\n

                            Correct Answer: 1. A response containing information that is unsupported, fabricated, or factually incorrect<\/b><\/p>\n

                            Explanation:<\/b>
                            \n<\/b>A hallucination occurs when a generative AI model produces information that is unsupported by the available evidence, fabricated, or factually incorrect. Hallucinations can occur even when a response is fluent and appears plausible. Grounding and retrieval can help provide supporting information, but they do not guarantee that hallucinations will never occur. Applications can use source attribution, evaluation, validation, constrained prompting, and other controls to improve reliability. Understanding hallucination risk is particularly important for enterprise use cases where inaccurate information could affect business decisions or downstream processes.<\/span><\/p>\n

                            Question 114: What is the purpose of using examples in a prompt when appropriate?<\/b><\/p>\n

                              \n
                            1. <\/b> To demonstrate the desired input-output pattern to the model<\/span><\/li>\n
                            2. <\/b> To permanently modify the model’s training parameters<\/span><\/li>\n
                            3. <\/b> To replace enterprise access controls<\/span><\/li>\n
                            4. <\/b> To disable retrieval<\/span><\/li>\n<\/ol>\n

                              Correct Answer: 1. To demonstrate the desired input-output pattern to the model<\/b><\/p>\n

                              Explanation:<\/b>
                              \n<\/b>Providing examples in a prompt can demonstrate the type of response the model is expected to produce. This technique can help clarify task requirements, formatting, classification categories, tone, or other desired behavior. The examples are part of the model’s input for that interaction; they do not permanently modify the model’s parameters. Prompt examples also do not replace security controls or eliminate the need for retrieval when external information is required. The examples should be representative, relevant, and consistent with the task because poor or contradictory examples can lead to undesirable outputs.<\/span><\/p>\n

                              Question 115: Which design principle is useful when building an enterprise generative AI application?<\/b><\/p>\n

                                \n
                              1. <\/b> Treat security and governance as separate concerns that never affect AI design<\/span><\/li>\n
                              2. <\/b> Integrate security, data access, evaluation, and governance into the application architecture<\/span><\/li>\n
                              3. <\/b> Allow the model to access all enterprise data without restrictions<\/span><\/li>\n
                              4. <\/b> Assume the model output is always trustworthy<\/span><\/li>\n<\/ol>\n

                                Correct Answer: 2. Integrate security, data access, evaluation, and governance into the application architecture<\/b><\/p>\n

                                Explanation:<\/b>
                                \n<\/b>Enterprise generative AI applications should consider security, data access, evaluation, and governance as part of the overall architecture. AI systems may process sensitive enterprise information and produce outputs that influence users or downstream systems. Designing appropriate controls from the beginning can help manage these risks more effectively than adding them after deployment. Authorization should determine what information can be retrieved, evaluation should measure system behavior, and governance should establish appropriate oversight and responsible-use practices. Generative models should not be assumed to produce inherently trustworthy outputs without application-level controls and evaluation.<\/span><\/p>\n

                                Question 116: What can happen if document chunks are too large for the retrieval task?<\/b><\/p>\n

                                  \n
                                1. <\/b> Retrieval may return excessive context that is less focused and consumes more model context<\/span><\/li>\n
                                2. <\/b> The model automatically becomes more accurate<\/span><\/li>\n
                                3. <\/b> Metadata becomes unnecessary<\/span><\/li>\n
                                4. <\/b> The source document is automatically deleted<\/span><\/li>\n<\/ol>\n

                                  Correct Answer: 1. Retrieval may return excessive context that is less focused and consumes more model context<\/b><\/p>\n

                                  Explanation:<\/b>
                                  \n<\/b>If chunks are excessively large, retrieval may return much more information than is necessary to answer a particular question. This can make the context less focused and consume more of the model’s available context window. Large chunks may also reduce retrieval precision because a retrieved unit contains substantial unrelated material. Chunking should therefore balance sufficient context with focused retrieval. The appropriate size depends on document structure, content characteristics, retrieval requirements, and model limitations. Chunking is one of several factors that influence the quality and efficiency of a RAG system.<\/span><\/p>\n

                                  Question 117: Which capability is most relevant when an application needs to extract structured information from unstructured documents?<\/b><\/p>\n

                                    \n
                                  1. <\/b> Cortex Analyst<\/span><\/li>\n
                                  2. <\/b> Document AI<\/span><\/li>\n
                                  3. <\/b> Cortex Search<\/span><\/li>\n
                                  4. <\/b> Temperature<\/span><\/li>\n<\/ol>\n

                                    Correct Answer: 2. Document AI<\/b><\/p>\n

                                    Explanation:<\/b>
                                    \n<\/b>Document AI is intended for processing documents and extracting useful information from unstructured document content. For example, an application may need to identify fields from invoices, forms, contracts, or other business documents. Extracted information can then be stored, analyzed, searched, or incorporated into downstream workflows. Cortex Analyst is focused on natural-language interaction with structured data, while Cortex Search supports content retrieval. Temperature is a model-generation parameter rather than a document-extraction capability. Document AI is therefore the appropriate capability for workflows centered on extracting information from documents.<\/span><\/p>\n

                                    Question 118: Why might an enterprise use a combination of semantic and keyword retrieval?<\/b><\/p>\n

                                      \n
                                    1. <\/b> To combine conceptual relevance with the ability to match important exact terms<\/span><\/li>\n
                                    2. <\/b> To eliminate all indexing requirements<\/span><\/li>\n
                                    3. <\/b> To guarantee every retrieved document is authoritative<\/span><\/li>\n
                                    4. <\/b> To prevent users from entering natural-language questions<\/span><\/li>\n<\/ol>\n

                                      Correct Answer: 1. To combine conceptual relevance with the ability to match important exact terms<\/b><\/p>\n

                                      Explanation:<\/b>
                                      \n<\/b>Semantic retrieval can identify content that is conceptually related to a query even when the wording differs. Keyword retrieval, meanwhile, can be particularly effective for exact terms such as product identifiers, codes, names, or specialized terminology. Combining these approaches can provide a broader retrieval strategy that benefits from both semantic and lexical signals. This approach does not guarantee that every retrieved source is authoritative and does not eliminate the need for indexing. The relative importance of each retrieval signal should be determined according to the application’s content, queries, and business requirements.<\/span><\/p>\n

                                      Question 119: Which action is most appropriate before exposing retrieved enterprise information to an LLM?<\/b><\/p>\n

                                        \n
                                      1. <\/b> Verify that the information is permitted for the requesting user and relevant to the task<\/span><\/li>\n
                                      2. <\/b> Remove all access controls<\/span><\/li>\n
                                      3. <\/b> Include every document regardless of relevance<\/span><\/li>\n
                                      4. <\/b> Assume every source is publicly accessible<\/span><\/li>\n<\/ol>\n

                                        Correct Answer: 1. Verify that the information is permitted for the requesting user and relevant to the task<\/b><\/p>\n

                                        Explanation:<\/b>
                                        \n<\/b>Before enterprise information is supplied to a language model, the application should consider both authorization and relevance. Users may have different permissions, and retrieved information should be limited to content they are allowed to access. At the same time, irrelevant information can reduce response quality and increase unnecessary context. Applying appropriate access controls and retrieval filtering helps address both concerns. Assuming all enterprise content is public is unsafe, while removing access controls can create data-exposure risks. These checks are especially important in RAG systems because retrieved content becomes part of the model’s input.<\/span><\/p>\n

                                        Question 120: Which sequence best represents a mature enterprise generative AI workflow?<\/b><\/p>\n

                                          \n
                                        1. <\/b> Generate an unrestricted answer \u2192 retrieve data afterward \u2192 ignore validation<\/span><\/li>\n
                                        2. <\/b> Retrieve all enterprise content \u2192 send everything to the model \u2192 skip authorization<\/span><\/li>\n
                                        3. <\/b> Define the task \u2192 retrieve authorized relevant context \u2192 generate the response \u2192 evaluate or validate according to application requirements<\/span><\/li>\n
                                        4. <\/b> Disable retrieval \u2192 generate from the model alone \u2192 assume the output is accurate<\/span><\/li>\n<\/ol>\n

                                          Correct Answer: 3. Define the task \u2192 retrieve authorized relevant context \u2192 generate the response \u2192 evaluate or validate according to application requirements<\/b><\/p>\n

                                          Explanation:<\/b>
                                          \n<\/b>A mature enterprise generative AI workflow considers the complete path from user request to final response. The application first defines the task and determines the relevant information needed. Retrieval should return appropriate and authorized context, which is then supplied to the model for generation. Depending on the use case, the resulting response can undergo validation, evaluation, source attribution, formatting checks, or other controls before being presented to the user. This approach recognizes that reliable AI applications require more than generation alone and combines retrieval, security, generation, and evaluation as complementary components.<\/span><\/p>\n

                                           <\/p>\n","protected":false},"excerpt":{"rendered":"

                                          View Full Snowflake SnowPro Specialty Gen AI GES-C01 Exam Dumps and Practice Test Dumps   Question 101: Which Snowflake Cortex capability is designed to help search and retrieve relevant information from enterprise content? Cortex Analyst Cortex Search Document AI Semantic model Correct Answer: 2. Cortex Search Explanation: Cortex Search is designed to support search and […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[1648,1647],"tags":[],"_links":{"self":[{"href":"https:\/\/www.examlabs.com\/certification\/wp-json\/wp\/v2\/posts\/19394"}],"collection":[{"href":"https:\/\/www.examlabs.com\/certification\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.examlabs.com\/certification\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.examlabs.com\/certification\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.examlabs.com\/certification\/wp-json\/wp\/v2\/comments?post=19394"}],"version-history":[{"count":1,"href":"https:\/\/www.examlabs.com\/certification\/wp-json\/wp\/v2\/posts\/19394\/revisions"}],"predecessor-version":[{"id":19395,"href":"https:\/\/www.examlabs.com\/certification\/wp-json\/wp\/v2\/posts\/19394\/revisions\/19395"}],"wp:attachment":[{"href":"https:\/\/www.examlabs.com\/certification\/wp-json\/wp\/v2\/media?parent=19394"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.examlabs.com\/certification\/wp-json\/wp\/v2\/categories?post=19394"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.examlabs.com\/certification\/wp-json\/wp\/v2\/tags?post=19394"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}