{"id":32208,"date":"2024-01-31T02:46:45","date_gmt":"2024-01-31T10:46:45","guid":{"rendered":"https:\/\/symbl.ai\/?p=32208"},"modified":"2024-06-12T05:48:20","modified_gmt":"2024-06-12T12:48:20","slug":"building-a-rag-based-conversational-application-with-the-nebula-llm","status":"publish","type":"post","link":"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/","title":{"rendered":"Building a RAG-based Conversational Application with the Nebula LLM"},"content":{"rendered":"\n<p><a href=\"https:\/\/symbl.ai\/developers\/blog\/implementing-retrieval-augmented-generation-rag-with-nebula-a-comprehensive-guide\/\">Retrieval-Augmented Generation<\/a> (RAG) is a technique that combines retrieval-based and generative AI models to produce highly contextual domain-specific responses. There are numerous applications for RAG: Question &amp; Answering, Summarization, Report Generation, and more. In his recent blog, <a href=\"https:\/\/www.linkedin.com\/in\/yujiantang\/\">Yujian Tang<\/a> (Zilliz) elaborates on the tech stack that is needed to implement a simple conversational RAG application using Symbl.ai\u2019s domain specific foundation model, <a href=\"https:\/\/symbl.ai\/nebula\/\">Nebula<\/a>. Below is a summary of the implementation:<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Technology stack<\/h2>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/symbl.ai\/platform\/nebula\/llm\/\">Nebula LLM<\/a>:<br>Symbl\u2019s Nebula LLM is a domain specific pre-trained foundation model for interaction data. It serves as the generative model replacing OpenAI&#8217;s GPT-3.5 in this project by Zilliz<\/li>\n\n\n\n<li><a href=\"https:\/\/milvus.io\/\">Milvus Vector DB<\/a>:<br>Milvus serves as the vector database for storing vectors derived from conversation data on which similar matching is performed and relevant information is extracted for feeding the Nebula LLM<\/li>\n\n\n\n<li>MPNet V2 Embedding Model from Hugging Face:<br>MPNet V2, an embedding model from Hugging Face, is used in place of OpenAI embeddings to derive embeddings from conversation data and user search queries<\/li>\n\n\n\n<li><a href=\"https:\/\/python.langchain.com\/docs\/integrations\/providers\/symblai_nebula\">LangChain<\/a>:<br>LangChain serves as an orchestration framework. Key components used for creating conversational memory for the application are: the vector store retriever memory, conversation chain, and prompt template object<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">High Level Implementation&nbsp;<\/h2>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Install required libraries such as <a href=\"https:\/\/www.langchain.com\/\">LangChain<\/a>, <a href=\"https:\/\/milvus.io\/blog\/introducing-milvus-lite-lightweight-version-of-milvus.md\">Milvus (Lite)<\/a>, <a href=\"https:\/\/pymilvus.readthedocs.io\/en\/latest\/\">PyMilvus<\/a>, <a href=\"https:\/\/pypi.org\/project\/python-dotenv\/\">python-dotenv<\/a>, and <a href=\"https:\/\/huggingface.co\/sentence-transformers\">Sentence Transformers<\/a><\/li>\n\n\n\n<li>Load API key for Nebula (<a href=\"https:\/\/symbl.ai\/company\/request-a-demo\/\">Register<\/a> to request a key)<\/li>\n\n\n\n<li>Initiate vector database and embedding model&nbsp;&nbsp;<\/li>\n\n\n\n<li>Create a sample conversation and save it to memory as context using <a href=\"https:\/\/python.langchain.com\/docs\/modules\/memory\/types\/vectorstore_retriever_memory\">VectorStoreRetrieverMemory<\/a><\/li>\n\n\n\n<li>Import Nebula LLM by using the API key<\/li>\n\n\n\n<li>Create a prompt template including user query using <a href=\"https:\/\/api.python.langchain.com\/en\/latest\/prompts\/langchain_core.prompts.prompt.PromptTemplate.html#\">PromptTemplate<\/a><\/li>\n\n\n\n<li>Create a conversation chaining the Nebula LLM, memory, and prompt using <a href=\"https:\/\/api.python.langchain.com\/en\/latest\/chains\/langchain.chains.conversation.base.ConversationChain.html#\">ConversationChain<\/a> for asking a question<\/li>\n<\/ul>\n\n\n\n<figure class=\"wp-block-image size-full\"><img decoding=\"async\" width=\"1242\" height=\"496\" src=\"https:\/\/symbl.ai\/wp-content\/uploads\/2024\/01\/image-1.png\" alt=\"\" class=\"wp-image-32211\" srcset=\"https:\/\/symbl.ai\/wp-content\/uploads\/2024\/01\/image-1.png 1242w, https:\/\/symbl.ai\/wp-content\/uploads\/2024\/01\/image-1-980x391.png 980w, https:\/\/symbl.ai\/wp-content\/uploads\/2024\/01\/image-1-480x192.png 480w\" sizes=\"(min-width: 0px) and (max-width: 480px) 480px, (min-width: 481px) and (max-width: 980px) 980px, (min-width: 981px) 1242px, 100vw\" \/><\/figure>\n\n\n\n<p>Output Image (Reference: <a href=\"https:\/\/zilliz.com\/blog\/building-rag-apps-without-openai-part-I\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/zilliz.com\/blog\/building-rag-apps-without-openai-part-I<\/a>)<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Conclusion<\/h2>\n\n\n\n<p>As businesses and users start focusing on the specificity of output and outcome from LLMs, the use of domain specific models like Nebula is gaining prominence. The <a href=\"https:\/\/docs.symbl.ai\/docs\/nebula-embedding-api\">Nebula Embedding Model<\/a> is also trained on interaction data, and can produce high quality vector embeddings on conversational data and knowledge.<\/p>\n\n\n\n<p>You can read about the full implementation of this RAG-based conversational system, along with code samples,&nbsp; at the blog published by <a href=\"https:\/\/zilliz.com\/blog\/building-rag-apps-without-openai-part-I\">Zilliz<\/a>.&nbsp;<\/p>\n\n\n\n<p>\u00a0<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Retrieval-Augmented Generation (RAG) is a technique that combines retrieval-based and generative AI models to produce highly contextual domain-specific responses. There are numerous applications for RAG: Question &amp; Answering, Summarization, Report Generation, and more. In his recent blog, Yujian Tang (Zilliz) elaborates on the tech stack that is needed to implement a simple conversational RAG application [&hellip;]<\/p>\n","protected":false},"author":88,"featured_media":32213,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"_et_pb_use_builder":"off","_et_pb_old_content":"","_et_gb_content_width":"","inline_featured_image":false,"ub_ctt_via":"","footnotes":""},"categories":[163],"tags":[],"class_list":["post-32208","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-ml"],"acf":[],"featured_image_src":"https:\/\/symbl.ai\/wp-content\/uploads\/2024\/01\/Building-a-RAG-based-Conversational-Application-with-the-Nebula-LLM.jpg","author_info":{"display_name":"Kartik Talamadupula","author_link":"https:\/\/symbl.ai\/developers\/blog\/author\/kartik-talamadupula\/"},"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v23.9 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Building a RAG-based Conversational Application with Nebula LLM | Symbl.ai<\/title>\n<meta name=\"description\" content=\"This blog elaborates on the tech stack that is needed to implement a simple conversational RAG application using Symbl.ai\u2019s Nebula LLM.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Building a RAG-based Conversational Application with Nebula LLM | Symbl.ai\" \/>\n<meta property=\"og:description\" content=\"This blog elaborates on the tech stack that is needed to implement a simple conversational RAG application using Symbl.ai\u2019s Nebula LLM.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/\" \/>\n<meta property=\"og:site_name\" content=\"Symbl.ai\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/symbldotai\/\" \/>\n<meta property=\"article:published_time\" content=\"2024-01-31T10:46:45+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-06-12T12:48:20+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/symbl.ai\/wp-content\/uploads\/2024\/01\/Building-a-RAG-based-Conversational-Application-with-the-Nebula-LLM.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1920\" \/>\n\t<meta property=\"og:image:height\" content=\"1080\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Kartik Talamadupula\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Kartik Talamadupula\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/\"},\"author\":{\"name\":\"Kartik Talamadupula\",\"@id\":\"https:\/\/symbl.ai\/#\/schema\/person\/5b8f27220e867eb05a9055e8558989e7\"},\"headline\":\"Building a RAG-based Conversational Application with the Nebula LLM\",\"datePublished\":\"2024-01-31T10:46:45+00:00\",\"dateModified\":\"2024-06-12T12:48:20+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/\"},\"wordCount\":368,\"publisher\":{\"@id\":\"https:\/\/symbl.ai\/#organization\"},\"image\":{\"@id\":\"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/symbl.ai\/wp-content\/uploads\/2024\/01\/Building-a-RAG-based-Conversational-Application-with-the-Nebula-LLM.jpg\",\"articleSection\":[\"AI\/ML\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/\",\"url\":\"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/\",\"name\":\"Building a RAG-based Conversational Application with Nebula LLM | Symbl.ai\",\"isPartOf\":{\"@id\":\"https:\/\/symbl.ai\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/symbl.ai\/wp-content\/uploads\/2024\/01\/Building-a-RAG-based-Conversational-Application-with-the-Nebula-LLM.jpg\",\"datePublished\":\"2024-01-31T10:46:45+00:00\",\"dateModified\":\"2024-06-12T12:48:20+00:00\",\"description\":\"This blog elaborates on the tech stack that is needed to implement a simple conversational RAG application using Symbl.ai\u2019s Nebula LLM.\",\"breadcrumb\":{\"@id\":\"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/#primaryimage\",\"url\":\"https:\/\/symbl.ai\/wp-content\/uploads\/2024\/01\/Building-a-RAG-based-Conversational-Application-with-the-Nebula-LLM.jpg\",\"contentUrl\":\"https:\/\/symbl.ai\/wp-content\/uploads\/2024\/01\/Building-a-RAG-based-Conversational-Application-with-the-Nebula-LLM.jpg\",\"width\":1920,\"height\":1080,\"caption\":\"RAG with Nebula Blog Cover\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/symbl.ai\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Building a RAG-based Conversational Application with the Nebula LLM\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/symbl.ai\/#website\",\"url\":\"https:\/\/symbl.ai\/\",\"name\":\"Symbl.ai\",\"description\":\"LLM for Conversation Data\",\"publisher\":{\"@id\":\"https:\/\/symbl.ai\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/symbl.ai\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/symbl.ai\/#organization\",\"name\":\"Symbl.ai\",\"url\":\"https:\/\/symbl.ai\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/symbl.ai\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/symbl.ai\/wp-content\/uploads\/2020\/07\/Symbl-Logo.svg\",\"contentUrl\":\"https:\/\/symbl.ai\/wp-content\/uploads\/2020\/07\/Symbl-Logo.svg\",\"width\":180,\"height\":40,\"caption\":\"Symbl.ai\"},\"image\":{\"@id\":\"https:\/\/symbl.ai\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.facebook.com\/symbldotai\/\",\"https:\/\/x.com\/symbldotai\",\"https:\/\/www.instagram.com\/symbldotai\/\",\"https:\/\/www.linkedin.com\/company\/symblai\/\",\"https:\/\/www.youtube.com\/channel\/UCpqOyNdFI0kASCZL-eCnkcA\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/symbl.ai\/#\/schema\/person\/5b8f27220e867eb05a9055e8558989e7\",\"name\":\"Kartik Talamadupula\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/symbl.ai\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/symbl.ai\/wp-content\/uploads\/2023\/08\/Kartik-Talamadupula-96x96.jpeg\",\"contentUrl\":\"https:\/\/symbl.ai\/wp-content\/uploads\/2023\/08\/Kartik-Talamadupula-96x96.jpeg\",\"caption\":\"Kartik Talamadupula\"},\"description\":\"Kartik Talamadupula is a research scientist who has spent over a decade applying AI techniques to business problems in automation, human-AI collaboration, and NLP.\",\"url\":\"https:\/\/symbl.ai\/developers\/blog\/author\/kartik-talamadupula\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Building a RAG-based Conversational Application with Nebula LLM | Symbl.ai","description":"This blog elaborates on the tech stack that is needed to implement a simple conversational RAG application using Symbl.ai\u2019s Nebula LLM.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/","og_locale":"en_US","og_type":"article","og_title":"Building a RAG-based Conversational Application with Nebula LLM | Symbl.ai","og_description":"This blog elaborates on the tech stack that is needed to implement a simple conversational RAG application using Symbl.ai\u2019s Nebula LLM.","og_url":"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/","og_site_name":"Symbl.ai","article_publisher":"https:\/\/www.facebook.com\/symbldotai\/","article_published_time":"2024-01-31T10:46:45+00:00","article_modified_time":"2024-06-12T12:48:20+00:00","og_image":[{"width":1920,"height":1080,"url":"https:\/\/symbl.ai\/wp-content\/uploads\/2024\/01\/Building-a-RAG-based-Conversational-Application-with-the-Nebula-LLM.jpg","type":"image\/jpeg"}],"author":"Kartik Talamadupula","twitter_misc":{"Written by":"Kartik Talamadupula","Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/#article","isPartOf":{"@id":"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/"},"author":{"name":"Kartik Talamadupula","@id":"https:\/\/symbl.ai\/#\/schema\/person\/5b8f27220e867eb05a9055e8558989e7"},"headline":"Building a RAG-based Conversational Application with the Nebula LLM","datePublished":"2024-01-31T10:46:45+00:00","dateModified":"2024-06-12T12:48:20+00:00","mainEntityOfPage":{"@id":"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/"},"wordCount":368,"publisher":{"@id":"https:\/\/symbl.ai\/#organization"},"image":{"@id":"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/#primaryimage"},"thumbnailUrl":"https:\/\/symbl.ai\/wp-content\/uploads\/2024\/01\/Building-a-RAG-based-Conversational-Application-with-the-Nebula-LLM.jpg","articleSection":["AI\/ML"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/","url":"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/","name":"Building a RAG-based Conversational Application with Nebula LLM | Symbl.ai","isPartOf":{"@id":"https:\/\/symbl.ai\/#website"},"primaryImageOfPage":{"@id":"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/#primaryimage"},"image":{"@id":"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/#primaryimage"},"thumbnailUrl":"https:\/\/symbl.ai\/wp-content\/uploads\/2024\/01\/Building-a-RAG-based-Conversational-Application-with-the-Nebula-LLM.jpg","datePublished":"2024-01-31T10:46:45+00:00","dateModified":"2024-06-12T12:48:20+00:00","description":"This blog elaborates on the tech stack that is needed to implement a simple conversational RAG application using Symbl.ai\u2019s Nebula LLM.","breadcrumb":{"@id":"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/#primaryimage","url":"https:\/\/symbl.ai\/wp-content\/uploads\/2024\/01\/Building-a-RAG-based-Conversational-Application-with-the-Nebula-LLM.jpg","contentUrl":"https:\/\/symbl.ai\/wp-content\/uploads\/2024\/01\/Building-a-RAG-based-Conversational-Application-with-the-Nebula-LLM.jpg","width":1920,"height":1080,"caption":"RAG with Nebula Blog Cover"},{"@type":"BreadcrumbList","@id":"https:\/\/symbl.ai\/developers\/blog\/building-a-rag-based-conversational-application-with-the-nebula-llm\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/symbl.ai\/"},{"@type":"ListItem","position":2,"name":"Building a RAG-based Conversational Application with the Nebula LLM"}]},{"@type":"WebSite","@id":"https:\/\/symbl.ai\/#website","url":"https:\/\/symbl.ai\/","name":"Symbl.ai","description":"LLM for Conversation Data","publisher":{"@id":"https:\/\/symbl.ai\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/symbl.ai\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/symbl.ai\/#organization","name":"Symbl.ai","url":"https:\/\/symbl.ai\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/symbl.ai\/#\/schema\/logo\/image\/","url":"https:\/\/symbl.ai\/wp-content\/uploads\/2020\/07\/Symbl-Logo.svg","contentUrl":"https:\/\/symbl.ai\/wp-content\/uploads\/2020\/07\/Symbl-Logo.svg","width":180,"height":40,"caption":"Symbl.ai"},"image":{"@id":"https:\/\/symbl.ai\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/symbldotai\/","https:\/\/x.com\/symbldotai","https:\/\/www.instagram.com\/symbldotai\/","https:\/\/www.linkedin.com\/company\/symblai\/","https:\/\/www.youtube.com\/channel\/UCpqOyNdFI0kASCZL-eCnkcA"]},{"@type":"Person","@id":"https:\/\/symbl.ai\/#\/schema\/person\/5b8f27220e867eb05a9055e8558989e7","name":"Kartik Talamadupula","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/symbl.ai\/#\/schema\/person\/image\/","url":"https:\/\/symbl.ai\/wp-content\/uploads\/2023\/08\/Kartik-Talamadupula-96x96.jpeg","contentUrl":"https:\/\/symbl.ai\/wp-content\/uploads\/2023\/08\/Kartik-Talamadupula-96x96.jpeg","caption":"Kartik Talamadupula"},"description":"Kartik Talamadupula is a research scientist who has spent over a decade applying AI techniques to business problems in automation, human-AI collaboration, and NLP.","url":"https:\/\/symbl.ai\/developers\/blog\/author\/kartik-talamadupula\/"}]}},"_links":{"self":[{"href":"https:\/\/symbl.ai\/wp-json\/wp\/v2\/posts\/32208","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/symbl.ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/symbl.ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/symbl.ai\/wp-json\/wp\/v2\/users\/88"}],"replies":[{"embeddable":true,"href":"https:\/\/symbl.ai\/wp-json\/wp\/v2\/comments?post=32208"}],"version-history":[{"count":0,"href":"https:\/\/symbl.ai\/wp-json\/wp\/v2\/posts\/32208\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/symbl.ai\/wp-json\/wp\/v2\/media\/32213"}],"wp:attachment":[{"href":"https:\/\/symbl.ai\/wp-json\/wp\/v2\/media?parent=32208"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/symbl.ai\/wp-json\/wp\/v2\/categories?post=32208"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/symbl.ai\/wp-json\/wp\/v2\/tags?post=32208"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}