[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-573258-105":3,"detail-sidebar-cat-1-en-105":80,"doc-detail-573258-en":126},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":73,"head_meta":75,"extra_data":77,"updated_unix":79},105,"en","genai-with-knime-analytics-platform-cheat-sheet","GenAI with KNIME Analytics Platform - Cheat Sheet","","Cheat sheet covering GenAI concepts and how to apply them within KNIME Analytics Platform using the KNIME AI Assistant (K-AI). Explains what GenAI and LLMs are, outlines core prompting and prompt engineering practices, and describes node-based capabilities such as workflow generation from natural language, expression-based data operations, and code snippet support. Details authentication to AI providers, embedding for conversational context, and governance features including evaluation, scanning, and data anonymization for safer deployment of LLM and RAG systems.",{"@graph":14,"@context":72},[15,34,55],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/template/","Template",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/template/presentations/","Presentations",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/template/genai-with-knime-analytics-platform-cheat-sheet/573258/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/genai-with-knime-analytics-platform-cheat-sheet/573258.png","ImageObject",442,249,{"name":42,"@type":43},"Đào","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-18","2026-10-13",true,{"@type":52,"interactionType":53,"userInteractionCount":30},"InteractionCounter",{"@type":54},"ViewAction",{"@type":56,"mainEntity":57},"FAQPage",[58,64,68],{"name":59,"@type":60,"acceptedAnswer":61},"What is KNIME AI Assistant (K-AI) and what can it do in KNIME?","Question",{"text":62,"@type":63},"K-AI enriches KNIME Analytics Platform with built-in AI support, including natural-language Q&A about KNIME, workflow building from descriptions, and assistance for data operations and code generation.","Answer",{"name":65,"@type":60,"acceptedAnswer":66},"How does prompt engineering improve LLM outputs?",{"text":67,"@type":63},"Prompt engineering focuses on designing clear, specific instructions, placing the request at the start, providing examples, and avoiding ambiguities, jargon, or assumptions.",{"name":69,"@type":60,"acceptedAnswer":70},"What governance capabilities are included for GenAI and RAG systems?",{"text":71,"@type":63},"GenAI governance features include vulnerability and risk detection in LLMs and RAG-based systems, evaluation with generated test sets, compliance-related controls, bias handling, and protecting data privacy through anonymization.","https://schema.org",{"og:url":32,"og:type":74,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":76,"canonical":32},"index,follow",{"doc_id":78,"site_id":7},573258,1792015747,{"code":4,"msg":81,"data":82},"success",[83,87,92,97,102,107,112,117,122],{"id":84,"doc_module":22,"doc_module_name":25,"category_name":29,"show_sort_weight":85,"slug":86},11,90,"presentations",{"id":88,"doc_module":22,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},12,"Resumes",80,"resumes",{"id":93,"doc_module":22,"doc_module_name":25,"category_name":94,"show_sort_weight":95,"slug":96},14,"Invoices",70,"invoices",{"id":98,"doc_module":22,"doc_module_name":25,"category_name":99,"show_sort_weight":100,"slug":101},15,"Posters",60,"posters",{"id":103,"doc_module":22,"doc_module_name":25,"category_name":104,"show_sort_weight":105,"slug":106},16,"Social Media",50,"social-media",{"id":108,"doc_module":22,"doc_module_name":25,"category_name":109,"show_sort_weight":110,"slug":111},17,"Forms",40,"forms",{"id":113,"doc_module":22,"doc_module_name":25,"category_name":114,"show_sort_weight":115,"slug":116},18,"Letters",30,"letters",{"id":118,"doc_module":22,"doc_module_name":25,"category_name":119,"show_sort_weight":120,"slug":121},21,"Paper Templates",5,"papers-templates",{"id":123,"doc_module":22,"doc_module_name":25,"category_name":124,"show_sort_weight":4,"slug":125},158,"General","general-158",{"code":4,"msg":81,"data":127},{"doc_id":78,"user_id":128,"nickname":42,"user_avatar":129,"doc_module":22,"category_id":84,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":130,"file_id":131,"file_url":132,"file_type":133,"file_size":134,"view_count":30,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":26,"language":135,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":136,"faqs":137,"seo_title":138,"seo_description":12,"update_tm":139,"read_time":22},1374402968488,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","Cheat sheet: GenAI with KNIME Analytics Platform  \n| \u003Cbr>GenAI & LLMs |  |  |  |  |  |  |  |  |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- |\n| GenAI refers to artificial intelligence that can create content such as text, images, audio, code, and more, typically using advanced machine learning models. LLMs are a class of multipurpose and multimodal deep neural networks trained on vast and diverse datasets, making them capable of understanding and generating natural language and other types of content to perform a wide range of tasks (e.g., text completion, summarization, image editing, speech-to-text, etc.) . Most LLMs are based on a transformer architecture and can capture complex relationships in data with multiple neural network layers and billions of fine-tunable parameters, which are further enhanced by an attention mechanism. \"Large\" refers precisely to the billions of parameters trained to accurately predict the next word in a sequence based on the previous ones. |  |  |  |  |  |  |  | \u003Cbr>\u003Cbr>KNIME AI Assistant\u003Cbr>K-AI is an extension for KNIME Analytics Platform that enriches the software with built-in AI-powered support. Its key features include:\u003Cbr>Q&A — K-AI understands and responds to questions about KNIME Software in natural language. Users can seek help about data operations, node configuration, KNIME resources, or features.\u003Cbr>Build — K-AI generates workflows based on natural language descriptions. Users can describe what they want to achieve, and the AI Assistant will automatically build the corresponding workflow using the appropriate nodes, connections and configurations. —\u003Cbr>Data operations and code generation K-AI is a built-in feature of the Expression node to help users with generic row-by-row data manipulation based on natural language descriptions. K-AI is also available in the Python Integration and the Generic ECharts View node, enabling users to seek help for the generation of Python or JavaScript code snippets. |\n| \u003Cbr>Authenticate |  |  |  |  |  | \u003Cbr> Prompt   Model prompters \u003Cbr>Dedicated nodes to prompt an LLM.\u003Cbr>\u003Cbr>\u003Cbr>Prompt engineering\u003Cbr>Involves designing and refining input instructions to guide the model towards generating desired responses. Common best practices include formulating clear and specific instructions, placing the request at the start, providing examples, and avoiding ambiguities, jargon, or assuming knowledge.\u003Cbr>\u003Cbr>Perform operations on String values in columns, such as joining two or more strings, extracting substrings, formatting strings, implementing RegEx, and more. Most operations are also available in the Expressions node, which additionally supports if and switch conditions, and integrates an AI assistant to help compile functions.\u003Cbr>\u003Cbr>Sends a separate prompt to the LLM for each row in the input table and outputs the corresponding response. It processes rows independently, so the model doesn't retain memory of prior rows or responses.\u003Cbr>Text Embedder\u003Cbr>\u003Cbr>\u003Cbr>Takes a text as input and generatesa dense vector of floating-point numbers capturing the semantic meaning of the text.\u003Cbr>Is suitable for a conversational interaction between the human and AI. It requires a prompt and allows adding a conversation history, so that for each prompt, it generates a response with knowledge of previous interactions. Optionally, the node supports tool calling by passing a table containing tool definitions as JSON objects. |  |  |\n| Dedicated nodes to authenticate to an AI provider. Authentication requires credentials, which can be set at the workflow level or created within the workflow. Output encrypted credentials (i.e., username and/or password) as a flow variable, which can be used to authenticate to an AI provider. | | \u003Cbr>Closed source |  |  |  |  |  |  |\n|  |  | OpenAI\u003Cbr>Authenticator\u003Cbr>\u003Cbr>| Authenticates to all OpenAI models by selecting a valid OpenAI API key. It also allows you to specify abase URL to set the destination of the API request (e.g., to sp","cbCaiuLp2iTgACzG","https://ap.wps.com/l/cbCaiuLp2iTgACzG","pdf",9372910,"English","# GenAI & LLMs\n## KNIME AI Assistant (K-AI)\n## Prompting and Prompt Engineering\n## Authentication to AI Providers\n## Embeddings\n## GenAI Governance and Evaluation\n## Data Anonymization","[{\"question\":\"What is KNIME AI Assistant (K-AI) and what can it do in KNIME?\",\"answer\":\"K-AI enriches KNIME Analytics Platform with built-in AI support, including natural-language Q\\u0026A about KNIME, workflow building from descriptions, and assistance for data operations and code generation.\"},{\"question\":\"How does prompt engineering improve LLM outputs?\",\"answer\":\"Prompt engineering focuses on designing clear, specific instructions, placing the request at the start, providing examples, and avoiding ambiguities, jargon, or assumptions.\"},{\"question\":\"What governance capabilities are included for GenAI and RAG systems?\",\"answer\":\"GenAI governance features include vulnerability and risk detection in LLMs and RAG-based systems, evaluation with generated test sets, compliance-related controls, bias handling, and protecting data privacy through anonymization.\"}]","GenAI with KNIME Analytics Platform - Cheat Sheet | PDF",1791935818]