{"id":8791,"date":"2024-01-18T15:16:04","date_gmt":"2024-01-18T23:16:04","guid":{"rendered":"https:\/\/live-cometml.pantheonsite.io\/?p=8791"},"modified":"2025-04-24T17:03:29","modified_gmt":"2025-04-24T17:03:29","slug":"logging-yolopandas-with-comet-llm","status":"publish","type":"post","link":"https:\/\/www.comet.com\/site\/blog\/logging-yolopandas-with-comet-llm\/","title":{"rendered":"Logging YOLOPandas \ud83d\udc3c with Comet-LLM\u00a0"},"content":{"rendered":"\n<h3 class=\"wp-block-heading graf graf--h3\"><\/h3>\n\n\n\n<figure class=\"graf graf--figure\">\n<\/figure>\n\n\n\n<figure class=\"wp-block-image aligncenter graf-image\"><img decoding=\"async\" src=\"https:\/\/cdn-images-1.medium.com\/max\/1600\/1*MVt3YITihq6_RilIjOHmrw.jpeg\" alt=\"yolopandas, cometllm, llmops, llms, comet\"\/><figcaption class=\"wp-element-caption\">Source: <a href=\"http:\/\/Unsplash.com\">Unsplash<\/a><\/figcaption><\/figure>\n\n\n\n<figcaption class=\"imageCaption\"><\/figcaption>\n\n\n\n<p class=\"graf graf--p\">I wrote an article on how you can explore your data with YOLOPandas and Comet, and you can find the article <a class=\"markup--anchor markup--p-anchor\" href=\"https:\/\/heartbeat.comet.ml\/llms-exploring-data-with-yolopandas-and-comet-1be6eee3a975\" target=\"_blank\" rel=\"noopener\" data-href=\"https:\/\/heartbeat.comet.ml\/llms-exploring-data-with-yolopandas-and-comet-1be6eee3a975\">here<\/a>. As prompt engineering is fundamentally different from training machine learning models, Comet has released a new SDK tailored for this use case <a class=\"markup--anchor markup--p-anchor\" href=\"https:\/\/www.comet.com\/docs\/v2\/api-and-sdk\/llm-sdk\/overview\/\" target=\"_blank\" rel=\"noopener\" data-href=\"https:\/\/www.comet.com\/docs\/v2\/api-and-sdk\/llm-sdk\/overview\/\">comet-llm<\/a>.<\/p>\n\n\n\n<p class=\"graf graf--p\">Check out the <a class=\"markup--anchor markup--p-anchor\" href=\"https:\/\/heartbeat.comet.ml\/large-language-models-navigating-comet-llmops-tools-915fd1bb8ddb\" target=\"_blank\" rel=\"noopener\" data-href=\"https:\/\/heartbeat.comet.ml\/large-language-models-navigating-comet-llmops-tools-915fd1bb8ddb\">Comet LLMOps tool<\/a>.<\/p>\n\n\n\n<p class=\"graf graf--p\">In this article you will learn how to log the YOLOPandas prompts with comet-llm, keep track of the number of tokens used in USD($), and log your metadata. This is a helpful guide if you want to learn more about LLMs and understand how to use the new comet-llm tool.<\/p>\n\n\n\n<h4 class=\"wp-block-heading graf graf--h4\">Prerequisites<\/h4>\n\n\n\n<ul class=\"wp-block-list postList\">\n<li>YOLOPandas<\/li>\n\n\n\n<li>comet-llm<\/li>\n\n\n\n<li>A Comet account, you can sign up <a class=\"markup--anchor markup--li-anchor\" data-href=\"\/signup\" href=\"\/signup\" target=\"_blank\" rel=\"noopener\">here<\/a>.<\/li>\n<\/ul>\n\n\n\n<p class=\"graf graf--p\"><a class=\"markup--anchor markup--p-anchor\" href=\"https:\/\/github.com\/ccurme\/yolopandas\" target=\"_blank\" rel=\"noopener\" data-href=\"https:\/\/github.com\/ccurme\/yolopandas\">YOLOPandas<\/a> lets you specify commands with natural language and execute them directly on Pandas objects. On the other hand, comet-llm is a tool to log and visualize your LLM prompts and chains. You can use comet-llm to identify effective prompt strategies, streamline your troubleshooting, and ensure reproducible workflows!<\/p>\n\n\n\n<blockquote class=\"wp-block-quote graf graf--pullquote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>Note: Experiment Tracking projects and LLM projects are mutually exclusive (for now). It is not possible to log prompts using the <code class=\"markup--code markup--pullquote-code\">comet_llm<\/code> SDK to an Experiment Management project and it is not possible to log an experiment using the <code class=\"markup--code markup--pullquote-code\">comet_ml<\/code> SDK to a LLM&nbsp;project.<\/p>\n<\/blockquote>\n\n\n\n<h4 class=\"wp-block-heading graf graf--h4\">Installation<\/h4>\n\n\n\n<p class=\"graf graf--p\">The SDK and YOLOPandas can be installed using the Python package installer\u200a\u2014\u200a <code class=\"markup--code markup--p-code\">pip<\/code><\/p>\n\n\n\n<pre class=\"wp-block-preformatted\"><span class=\"pre--content\">#install CometLLM\npip install comet_llm\n\n#install YOLOPandas\npip install yolopandas<\/span><\/pre>\n\n\n\n<h4 class=\"wp-block-heading graf graf--h4\">Import libraries<\/h4>\n\n\n\n<p class=\"graf graf--p\">After installation, the next steps require you to import both the SDK and the Library into your notebook.<\/p>\n\n\n\n<p><script src=\"https:\/\/gist.github.com\/zenUnicorn\/2ba4b9ee910f29e29c0733ae42c4cd45.js\"><\/script><\/p>\n\n\n\n<p class=\"graf graf--p\">Add your OpenAI API key as an environmental variable, you can find your keys <a class=\"markup--anchor markup--p-anchor\" href=\"https:\/\/platform.openai.com\/api-keys\" target=\"_blank\" rel=\"noopener\" data-href=\"https:\/\/platform.openai.com\/api-keys\">here<\/a>.<\/p>\n\n\n\n<p><script src=\"https:\/\/gist.github.com\/zenUnicorn\/99ac3a3e9a052d92df8cef7b99d88a98.js\"><\/script><\/p>\n\n\n\n<h4 class=\"wp-block-heading graf graf--h4\">Initialize comet-llm<\/h4>\n\n\n\n<p class=\"graf graf--p\">If you don\u2019t have one already, create your <a class=\"markup--anchor markup--p-anchor\" href=\"\/signup\" target=\"_blank\" rel=\"noopener\" data-href=\"\/signup\">free Comet account<\/a> and grab your API Key from the account <a class=\"markup--anchor markup--p-anchor\" href=\"https:\/\/www.comet.com\/account-settings\/apiKeys\" target=\"_blank\" rel=\"noopener\" data-href=\"https:\/\/www.comet.com\/account-settings\/apiKeys\">settings page<\/a>. You will need to also create a new project, make sure to set the project type to Large Language Models and click on the <strong class=\"markup--strong markup--p-strong\">Create<\/strong> button.<\/p>\n\n\n\n<figure class=\"wp-block-image aligncenter graf graf--figure\"><img decoding=\"async\" src=\"https:\/\/cdn-images-1.medium.com\/max\/1600\/1*ajpmD5aFIvA2eIrxFCBWxg.gif\" alt=\"yolopandas, cometllm, llmops, llms, comet\"\/><\/figure>\n\n\n\n<p>&nbsp;<\/p>\n\n\n\n<p><script src=\"https:\/\/gist.github.com\/zenUnicorn\/46b366ca0ace99cd8d98cbef5010ac44.js\"><\/script><\/p>\n\n\n\n<p class=\"graf graf--p\">Paste the code above in your notebook, and let&#8217;s have a look at a quick example of how you can quickly log your prompt using the comet-llm SDK.<\/p>\n\n\n\n<p><script src=\"https:\/\/gist.github.com\/zenUnicorn\/b5c2a04ed54f6d3362c3d3ddf4182c4d.js\"><\/script><\/p>\n\n\n\n<p class=\"graf graf--p\">Through the <code class=\"markup--code markup--p-code\">log_prompt<\/code> function, the prompt, its associated response, and metadata like token usage, total tokens model, etc. were logged to the LLM project dashboard.<\/p>\n\n\n\n<figure class=\"wp-block-image aligncenter graf graf--figure\"><img decoding=\"async\" src=\"https:\/\/cdn-images-1.medium.com\/max\/1600\/1*6GyzZnHmOqh1jkQb8VN5GQ.gif\" alt=\"yolopandas, cometllm, llmops, llms, comet\"\/><\/figure>\n\n\n\n<h4 class=\"wp-block-heading graf graf--h4\">Import dataset<\/h4>\n\n\n\n<p class=\"graf graf--p\">The dataset [source: <a class=\"markup--anchor markup--p-anchor\" href=\"https:\/\/www.kaggle.com\/code\/tr1gg3rtrash\/eda-for-your-next-netflix-playlist\/input?select=titles.csv\" target=\"_blank\" rel=\"noopener\" data-href=\"https:\/\/www.kaggle.com\/code\/tr1gg3rtrash\/eda-for-your-next-netflix-playlist\/input?select=titles.csv\">Kaggle<\/a>] contains titles of movies and other information such as: <strong class=\"markup--strong markup--p-strong\">title<\/strong>, <strong class=\"markup--strong markup--p-strong\">type<\/strong>, <strong class=\"markup--strong markup--p-strong\">description<\/strong>, <strong class=\"markup--strong markup--p-strong\">release_year<\/strong>, <strong class=\"markup--strong markup--p-strong\">age_certification<\/strong>, <strong class=\"markup--strong markup--p-strong\">runtime<\/strong>, <strong class=\"markup--strong markup--p-strong\">genres<\/strong>, <strong class=\"markup--strong markup--p-strong\">production_countries<\/strong>, <strong class=\"markup--strong markup--p-strong\">seasons<\/strong>, <strong class=\"markup--strong markup--p-strong\">imdb_id<\/strong>, <strong class=\"markup--strong markup--p-strong\">imdb_score<\/strong>, <strong class=\"markup--strong markup--p-strong\">imdb_votes<\/strong>, <strong class=\"markup--strong markup--p-strong\">tmdb_popularity<\/strong>, and <strong class=\"markup--strong markup--p-strong\">tmdb_score<\/strong>.<\/p>\n\n\n\n<p><script src=\"https:\/\/gist.github.com\/zenUnicorn\/512daaaf94cd1ff500611f7e42752f05.js\"><\/script><\/p>\n\n\n\n<p class=\"graf graf--p\">Let\u2019s query the dataset, for each movie we want to count the number of reviews, average score, and show the five with the highest reviews. Set <strong class=\"markup--strong markup--p-strong\">yolo=True<\/strong> and assign it to a variable.<\/p>\n\n\n\n<pre class=\"wp-block-preformatted\"><span class=\"pre--content\">\nhighest_reviews_prompt = movie_reviews.llm.query(\"for each movie,\ncount the number of reviews and their average score. Show the 5 with\nthe highest reviews,\", yolo=True)<\/span><\/pre>\n\n\n\n<p class=\"graf graf--p\">We will create a function that accepts three parameters\u200a\u2014\u200a<strong class=\"markup--strong markup--p-strong\">user_prompt<\/strong>, <strong class=\"markup--strong markup--p-strong\">tags<\/strong> and <strong class=\"markup--strong markup--p-strong\">metadata<\/strong>.<\/p>\n\n\n\n<p><script src=\"https:\/\/gist.github.com\/zenUnicorn\/090985fd7552f611120641b3e2b85fba.js\"><\/script><\/p>\n\n\n\n<p class=\"graf graf--p\">Finally, we will call the function by passing variables created above into the function.<\/p>\n\n\n\n<p><script src=\"https:\/\/gist.github.com\/zenUnicorn\/b1c9295339d9b21590d89f9ffbbf5830.js\"><\/script><\/p>\n\n\n\n<figure class=\"wp-block-image aligncenter graf graf--figure graf--iframe\"><img decoding=\"async\" src=\"https:\/\/cdn-images-1.medium.com\/max\/1600\/1*hhxAoCuywXwigCyASSxiyw.png\" alt=\"\"\/><\/figure>\n\n\n\n<figure class=\"graf graf--figure\">\n<figcaption class=\"imageCaption\">Logged prompt<\/figcaption>\n<\/figure>\n\n\n\n<h4 class=\"wp-block-heading graf graf--h4\">Logging YOLOPandas cost<\/h4>\n\n\n\n<p class=\"graf graf--p\">To get a better idea of how much each query costs, you can use the function <code class=\"markup--code markup--p-code\">run_query_with_cost<\/code> found in the utils module to compute the cost in $USD broken down by prompt\/completion tokens.<\/p>\n\n\n\n<p class=\"graf graf--p\">The <code class=\"markup--code markup--p-code\">run_query_with_cost<\/code> accepts three parameters, the <strong class=\"markup--strong markup--p-strong\">dataset<\/strong>, your <strong class=\"markup--strong markup--p-strong\">query<\/strong> and <strong class=\"markup--strong markup--p-strong\">yolo=True<\/strong>.<\/p>\n\n\n\n<p>&nbsp;<\/p>\n\n\n\n<p><script src=\"https:\/\/gist.github.com\/zenUnicorn\/15ff99d373cff1fea509e480bd128878.js\"><\/script><\/p>\n\n\n\n<figure class=\"wp-block-image aligncenter graf graf--figure\"><img decoding=\"async\" src=\"https:\/\/cdn-images-1.medium.com\/max\/1600\/1*WaH68K8-eOjwTXLdE89SLQ.png\" alt=\"\"\/><\/figure>\n\n\n\n<p class=\"graf graf--p\">The <code class=\"markup--code markup--p-code\">run_query_with_cost<\/code> function outputs the <strong class=\"markup--strong markup--p-strong\">total tokens<\/strong>, <strong class=\"markup--strong markup--p-strong\">prompt tokens<\/strong>, <strong class=\"markup--strong markup--p-strong\">completion tokens<\/strong> and the <strong class=\"markup--strong markup--p-strong\">total cost (USD)<\/strong>. We will write a function to log the prompt to Comet-LLM and add these metrics as metadata.<\/p>\n\n\n\n<p><script src=\"https:\/\/gist.github.com\/zenUnicorn\/110a8ea2e61013df3e3a9959f4fb3ef2.js\"><\/script><\/p>\n\n\n\n<p>&nbsp;<\/p>\n\n\n\n<figure class=\"wp-block-image aligncenter graf graf--figure\"><img decoding=\"async\" src=\"https:\/\/cdn-images-1.medium.com\/max\/1600\/1*M5Lh24-XjWc6U7Vgb0Mo3A.png\" alt=\"\"\/><figcaption class=\"wp-element-caption\">Logged prompt<\/figcaption><\/figure>\n\n\n\n<p class=\"graf graf--p\">As you can see, we were able to log our YOLOPandas prompt, metadata and the running cost for each prompt to Comet using the comt-llm SDK. You can also log your prompt template and variables and can be viewed in the table sidebar by clicking on a specific row.<\/p>\n\n\n\n<p class=\"graf graf--p\">You can view a demo project <a class=\"markup--anchor markup--p-anchor\" href=\"https:\/\/www.comet.com\/examples\/llm-project-demo\/prompts\" target=\"_blank\" rel=\"noopener\" data-href=\"https:\/\/www.comet.com\/examples\/llm-project-demo\/prompts\">here<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>I wrote an article on how you can explore your data with YOLOPandas and Comet, and you can find the article here. As prompt engineering is fundamentally different from training machine learning models, Comet has released a new SDK tailored for this use case comet-llm. Check out the Comet LLMOps tool. In this article you [&hellip;]<\/p>\n","protected":false},"author":22,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"customer_name":"","customer_description":"","customer_industry":"","customer_technologies":"","customer_logo":"","_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[65,7],"tags":[40,14,64,15,71,52,31,34],"coauthors":[143],"class_list":["post-8791","post","type-post","status-publish","format-standard","hentry","category-llmops","category-tutorials","tag-comet","tag-comet-ml","tag-cometllm","tag-deep-learning-experiment-management","tag-language-models","tag-llm","tag-llmops","tag-prompt-engineering"],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v25.9 (Yoast SEO v25.9) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Logging YOLOPandas \ud83d\udc3c with Comet-LLM\u00a0 - Comet<\/title>\n<meta name=\"description\" content=\"Learn how to log YOLOPandas prompts with comet-llm, keep track of the number of tokens used in USD($), and log your metadata.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.comet.com\/site\/blog\/logging-yolopandas-with-comet-llm\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Logging YOLOPandas \ud83d\udc3c with Comet-LLM\u00a0\" \/>\n<meta property=\"og:description\" content=\"Learn how to log YOLOPandas prompts with comet-llm, keep track of the number of tokens used in USD($), and log your metadata.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.comet.com\/site\/blog\/logging-yolopandas-with-comet-llm\/\" \/>\n<meta property=\"og:site_name\" content=\"Comet\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/cometdotml\" \/>\n<meta property=\"article:published_time\" content=\"2024-01-18T23:16:04+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-04-24T17:03:29+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/cdn-images-1.medium.com\/max\/1600\/1*MVt3YITihq6_RilIjOHmrw.jpeg\" \/>\n<meta name=\"author\" content=\"Shittu Olumide Ayodeji\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@anmorgan2414\" \/>\n<meta name=\"twitter:site\" content=\"@Cometml\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Shittu Olumide Ayodeji\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Logging YOLOPandas \ud83d\udc3c with Comet-LLM\u00a0 - Comet","description":"Learn how to log YOLOPandas prompts with comet-llm, keep track of the number of tokens used in USD($), and log your metadata.","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:\/\/www.comet.com\/site\/blog\/logging-yolopandas-with-comet-llm\/","og_locale":"en_US","og_type":"article","og_title":"Logging YOLOPandas \ud83d\udc3c with Comet-LLM\u00a0","og_description":"Learn how to log YOLOPandas prompts with comet-llm, keep track of the number of tokens used in USD($), and log your metadata.","og_url":"https:\/\/www.comet.com\/site\/blog\/logging-yolopandas-with-comet-llm\/","og_site_name":"Comet","article_publisher":"https:\/\/www.facebook.com\/cometdotml","article_published_time":"2024-01-18T23:16:04+00:00","article_modified_time":"2025-04-24T17:03:29+00:00","og_image":[{"url":"https:\/\/cdn-images-1.medium.com\/max\/1600\/1*MVt3YITihq6_RilIjOHmrw.jpeg","type":"","width":"","height":""}],"author":"Shittu Olumide Ayodeji","twitter_card":"summary_large_image","twitter_creator":"@anmorgan2414","twitter_site":"@Cometml","twitter_misc":{"Written by":"Shittu Olumide Ayodeji","Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.comet.com\/site\/blog\/logging-yolopandas-with-comet-llm\/#article","isPartOf":{"@id":"https:\/\/www.comet.com\/site\/blog\/logging-yolopandas-with-comet-llm\/"},"author":{"name":"Abby Morgan","@id":"https:\/\/www.comet.com\/site\/#\/schema\/person\/826ee39a2e30cf9d8d73155de09bb7b2"},"headline":"Logging YOLOPandas \ud83d\udc3c with Comet-LLM\u00a0","datePublished":"2024-01-18T23:16:04+00:00","dateModified":"2025-04-24T17:03:29+00:00","mainEntityOfPage":{"@id":"https:\/\/www.comet.com\/site\/blog\/logging-yolopandas-with-comet-llm\/"},"wordCount":604,"publisher":{"@id":"https:\/\/www.comet.com\/site\/#organization"},"image":{"@id":"https:\/\/www.comet.com\/site\/blog\/logging-yolopandas-with-comet-llm\/#primaryimage"},"thumbnailUrl":"https:\/\/cdn-images-1.medium.com\/max\/1600\/1*MVt3YITihq6_RilIjOHmrw.jpeg","keywords":["Comet","Comet ML","CometLLM","Deep Learning Experiment Management","Language Models","LLM","LLMOps","Prompt Engineering"],"articleSection":["LLMOps","Tutorials"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.comet.com\/site\/blog\/logging-yolopandas-with-comet-llm\/","url":"https:\/\/www.comet.com\/site\/blog\/logging-yolopandas-with-comet-llm\/","name":"Logging YOLOPandas \ud83d\udc3c with Comet-LLM\u00a0 - Comet","isPartOf":{"@id":"https:\/\/www.comet.com\/site\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.comet.com\/site\/blog\/logging-yolopandas-with-comet-llm\/#primaryimage"},"image":{"@id":"https:\/\/www.comet.com\/site\/blog\/logging-yolopandas-with-comet-llm\/#primaryimage"},"thumbnailUrl":"https:\/\/cdn-images-1.medium.com\/max\/1600\/1*MVt3YITihq6_RilIjOHmrw.jpeg","datePublished":"2024-01-18T23:16:04+00:00","dateModified":"2025-04-24T17:03:29+00:00","description":"Learn how to log YOLOPandas prompts with comet-llm, keep track of the number of tokens used in USD($), and log your metadata.","breadcrumb":{"@id":"https:\/\/www.comet.com\/site\/blog\/logging-yolopandas-with-comet-llm\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.comet.com\/site\/blog\/logging-yolopandas-with-comet-llm\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.comet.com\/site\/blog\/logging-yolopandas-with-comet-llm\/#primaryimage","url":"https:\/\/cdn-images-1.medium.com\/max\/1600\/1*MVt3YITihq6_RilIjOHmrw.jpeg","contentUrl":"https:\/\/cdn-images-1.medium.com\/max\/1600\/1*MVt3YITihq6_RilIjOHmrw.jpeg"},{"@type":"BreadcrumbList","@id":"https:\/\/www.comet.com\/site\/blog\/logging-yolopandas-with-comet-llm\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.comet.com\/site\/"},{"@type":"ListItem","position":2,"name":"Logging YOLOPandas \ud83d\udc3c with Comet-LLM\u00a0"}]},{"@type":"WebSite","@id":"https:\/\/www.comet.com\/site\/#website","url":"https:\/\/www.comet.com\/site\/","name":"Comet","description":"Build Better Models Faster","publisher":{"@id":"https:\/\/www.comet.com\/site\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.comet.com\/site\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.comet.com\/site\/#organization","name":"Comet ML, Inc.","alternateName":"Comet","url":"https:\/\/www.comet.com\/site\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.comet.com\/site\/#\/schema\/logo\/image\/","url":"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2025\/01\/logo_comet_square.png","contentUrl":"https:\/\/www.comet.com\/site\/wp-content\/uploads\/2025\/01\/logo_comet_square.png","width":310,"height":310,"caption":"Comet ML, Inc."},"image":{"@id":"https:\/\/www.comet.com\/site\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/cometdotml","https:\/\/x.com\/Cometml","https:\/\/www.youtube.com\/channel\/UCmN63HKvfXSCS-UwVwmK8Hw"]},{"@type":"Person","@id":"https:\/\/www.comet.com\/site\/#\/schema\/person\/826ee39a2e30cf9d8d73155de09bb7b2","name":"Abby Morgan","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.comet.com\/site\/#\/schema\/person\/image\/dbbf1ae921ee179c768f508340415946","url":"https:\/\/secure.gravatar.com\/avatar\/28d4934d14261b4afe12e226f0eaa57c4fb0c2761ad4586eb9a5bec3b8160bc9?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/28d4934d14261b4afe12e226f0eaa57c4fb0c2761ad4586eb9a5bec3b8160bc9?s=96&d=mm&r=g","caption":"Abby Morgan"},"description":"AI\/ML Growth Engineer @ Comet","sameAs":["https:\/\/www.comet.com\/","https:\/\/www.linkedin.com\/in\/anmorgan24\/","https:\/\/x.com\/anmorgan2414"],"url":"https:\/\/www.comet.com\/site\/blog\/author\/abigailmcomet-com\/"}]}},"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/posts\/8791","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/users\/22"}],"replies":[{"embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/comments?post=8791"}],"version-history":[{"count":1,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/posts\/8791\/revisions"}],"predecessor-version":[{"id":15401,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/posts\/8791\/revisions\/15401"}],"wp:attachment":[{"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/media?parent=8791"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/categories?post=8791"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/tags?post=8791"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/www.comet.com\/site\/wp-json\/wp\/v2\/coauthors?post=8791"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}