{"id":3514,"date":"2024-10-02T11:24:12","date_gmt":"2024-10-02T05:54:12","guid":{"rendered":"https:\/\/www.rangakrish.com\/?p=3514"},"modified":"2024-10-02T11:24:12","modified_gmt":"2024-10-02T05:54:12","slug":"using-openai-from-mathematica-part-2","status":"publish","type":"post","link":"https:\/\/www.rangakrish.com\/index.php\/2024\/10\/02\/using-openai-from-mathematica-part-2\/","title":{"rendered":"Using OpenAI from Mathematica: Part-2"},"content":{"rendered":"

I had written an earlier article<\/strong><\/em><\/a>\u00a0showing how to use OpenAI<\/strong><\/em> models from Mathematica<\/strong><\/em> ver 14.0.\u00a0 <\/span>Wolfram Mathematica<\/strong><\/em> ver 14.1 was released recently, with several improvements in the area of LLMs. Of course, there are many other core additions as well, but our focus is on LLMs in this article.<\/p>\n

This version supports many vendors other than OpenAI<\/strong><\/em>. For example, Anthropic<\/strong><\/em>, Cohere<\/strong><\/em>, and MistralAI<\/strong><\/em> are also supported.\u00a0 <\/span>We can even use many other open-source models via Groq<\/strong><\/em> and TogetherAI<\/strong><\/em>. That is great news!\u00a0<\/span><\/p>\n

I will be using my OpenAI<\/strong><\/em> account with all the examples discussed in today\u2019s article.<\/p>\n

Let us start with the LLMSynthesize[]<\/strong><\/em> function that we looked at in the previous article. It is the easiest to get started with.<\/p>\n

\"LLMSynthesize<\/a>
LLMSynthesize Function<\/strong><\/figcaption><\/figure>\n

Let us suppose we wanted to generalize this and turn it into a function. Although we can implement a Mathematica<\/strong><\/em> function over LLMSynthesize[]<\/strong><\/em> to take arguments and return values, it is more convenient to use LLMFunction[]<\/strong><\/em> for this.<\/p>\n

\"LLMFunction\"<\/a>
LLMFunction<\/strong><\/figcaption><\/figure>\n

What about those cases where the LLM has to use an external \u201cfunction\u201d<\/strong><\/em> or source<\/strong><\/em> to produce the correct answer? One common use case is retrieving information about some fact that the LLM\u2019s knowledge base (at the time of training) might not have. To keep things simple, I will try to calculate the \u201cFactorial\u201d<\/strong> <\/em>of a number by using Mathematica\u2019s<\/strong><\/em> function instead of relying on the LLM to give me the correct answer.<\/p>\n

For this we use the LLMTool[]<\/strong><\/em> function.\u00a0<\/span><\/p>\n

\"LLMTool<\/a>
LLMTool Function<\/strong><\/figcaption><\/figure>\n

Here we pass the name, a brief description, the argument, and the actual function that does the job.<\/p>\n

Here is how we use it in LLMSynthesize[]<\/strong><\/em>:<\/p>\n

\"Using<\/a>
Using the Tool Function<\/strong><\/figcaption><\/figure>\n

We can wrap this inside a function that takes an integer and passes it to the LLMSynthesize[]<\/strong><\/em> function.<\/p>\n

\"Parameterizing<\/a>
Parameterizing the Tool Call<\/strong><\/figcaption><\/figure>\n

Another cool addition is LLMExampleFunction[]<\/strong><\/em>. This function is capable of generating text with a prompt dynamically generated from a list of examples. Let us check it out.<\/p>\n

\"Learning<\/a>
Learning from Examples<\/strong><\/figcaption><\/figure>\n

Pretty neat, isn\u2019t it?<\/p>\n

There is also the ChatObject[]<\/strong><\/em> that models an ongoing chat with the LLM. It stores the complete conversation along with metadata. Here is how we can use it.<\/p>\n

\"Chat<\/a>
Chat Mode<\/strong><\/figcaption><\/figure>\n

The new version even has support for Semantic Search<\/strong><\/em> and RAG<\/strong><\/em>. More on this in another article.<\/p>\n

Have a Great Day!<\/p>\n","protected":false},"excerpt":{"rendered":"

I had written an earlier article\u00a0showing how to use OpenAI models from Mathematica ver 14.0.\u00a0 Wolfram Mathematica ver 14.1 was released recently, with several improvements in the area of LLMs. Of course, there are many other core additions as well, but our focus is on LLMs in this article. This version supports many vendors other […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"advanced_seo_description":"","jetpack_seo_html_title":"","jetpack_seo_noindex":false,"jetpack_post_was_ever_published":false,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[72,388,17],"tags":[401,354],"class_list":["post-3514","post","type-post","status-publish","format-standard","hentry","category-mathematica","category-openai","category-programming","tag-mathematica-14-1","tag-openai"],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/p9OLnF-UG","jetpack-related-posts":[{"id":3545,"url":"https:\/\/www.rangakrish.com\/index.php\/2024\/11\/09\/semantic-search-in-wolfram-mathematica\/","url_meta":{"origin":3514,"position":0},"title":"Semantic Search in Wolfram Mathematica","author":"admin","date":"November 9, 2024","format":false,"excerpt":"In an earlier article, I explained how to use OpenAI from Wolfram Mathematica ver 14.1. This latest release of Wolfram supports Semantic Search as well. In today\u2019s article, let me discuss this feature. As in the case of using LLMs, using Semantic Search requires an account with one of the\u2026","rel":"","context":"In "Mathematica"","block_context":{"text":"Mathematica","link":"https:\/\/www.rangakrish.com\/index.php\/category\/mathematica\/"},"img":{"alt_text":"Remedy Description","src":"https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2024\/11\/image1-300x225.png?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2024\/11\/image1-300x225.png?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2024\/11\/image1-300x225.png?resize=525%2C300&ssl=1 1.5x"},"classes":[]},{"id":3381,"url":"https:\/\/www.rangakrish.com\/index.php\/2024\/05\/20\/using-openai-from-mathematica\/","url_meta":{"origin":3514,"position":1},"title":"Using OpenAI from Mathematica","author":"admin","date":"May 20, 2024","format":false,"excerpt":"Mathematica was among the first to integrate with OpenAI. The functionality is nicely exposed in terms of a few pre-defined functions. Let us explore some of the functionality in today\u2019s article. The simplest way to get started is to use LLMSynthesize\u00a0function: It can take a few seconds before you get\u2026","rel":"","context":"In "Mathematica"","block_context":{"text":"Mathematica","link":"https:\/\/www.rangakrish.com\/index.php\/category\/mathematica\/"},"img":{"alt_text":"LLMSynthesize Function","src":"https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2024\/05\/Example1-300x27.png?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2024\/05\/Example1-300x27.png?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2024\/05\/Example1-300x27.png?resize=525%2C300&ssl=1 1.5x"},"classes":[]},{"id":3626,"url":"https:\/\/www.rangakrish.com\/index.php\/2025\/02\/21\/using-openai-from-mathematica-part-3\/","url_meta":{"origin":3514,"position":2},"title":"Using OpenAI from Mathematica: Part-3","author":"admin","date":"February 21, 2025","format":false,"excerpt":"Let us continue our discussion on using Mathematica to interact with OpenAI (you may want to go through the earlier article as well). The simplest function to interact with the LLM is LLMSynthesize[]. As you might have guessed, this is a \u201csync\u201d (non-streaming) call. What if you expect a long\u2026","rel":"","context":"In "Mathematica"","block_context":{"text":"Mathematica","link":"https:\/\/www.rangakrish.com\/index.php\/category\/mathematica\/"},"img":{"alt_text":"Basic LLMSynthesize","src":"https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2025\/02\/fig1-300x21.png?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2025\/02\/fig1-300x21.png?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2025\/02\/fig1-300x21.png?resize=525%2C300&ssl=1 1.5x"},"classes":[]},{"id":3050,"url":"https:\/\/www.rangakrish.com\/index.php\/2023\/03\/16\/building-a-xojo-app-to-interact-with-openai-api\/","url_meta":{"origin":3514,"position":3},"title":"Building a Xojo App to Interact with OpenAI API","author":"admin","date":"March 16, 2023","format":false,"excerpt":"A few weeks ago I registered with OpenAI to access its services through API and created a secret Key for my use. I then decided to build a simple application to try out the \u201cChat\u201d and \u201cCompletion\u201d models. Since I have several tools at my disposal (RAD Studio, LispWorks, Allegro\u2026","rel":"","context":"In "OpenAI"","block_context":{"text":"OpenAI","link":"https:\/\/www.rangakrish.com\/index.php\/category\/openai\/"},"img":{"alt_text":"Initial Screen","src":"https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2023\/03\/Initial-Screen-300x232.png?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":3599,"url":"https:\/\/www.rangakrish.com\/index.php\/2025\/01\/20\/using-openai-from-allegro-common-lisp\/","url_meta":{"origin":3514,"position":4},"title":"Using OpenAI from Allegro Common Lisp","author":"admin","date":"January 20, 2025","format":false,"excerpt":"Allegro Common Lisp ver 11.0\u00a0introduced support for OpenAI LLMs. In this article, let us look at some of the functions for interacting with OpenAI. First we need to specify basic parameters such as the API key, LLM to use, Temperature, etc. I have defined a convenient function configure-openai to do\u2026","rel":"","context":"In "LISP"","block_context":{"text":"LISP","link":"https:\/\/www.rangakrish.com\/index.php\/category\/lisp\/"},"img":{"alt_text":"Configuring the LLM","src":"https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2025\/01\/fig1-300x101.jpg?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":3614,"url":"https:\/\/www.rangakrish.com\/index.php\/2025\/02\/04\/interacting-with-openai-api-using-golang\/","url_meta":{"origin":3514,"position":5},"title":"Interacting with OpenAI API using Golang","author":"admin","date":"February 4, 2025","format":false,"excerpt":"I normally use Python\u2019s LangChain framework to communicate with OpenAI API. For a change, I wanted to see if Go has any libraries to access OpenAI and other LLMs. Interestingly I found that LangChainGo\u00a0is a port of LangChain for Golang! I decided to implement a simple Completetion request in both\u2026","rel":"","context":"In "Golang"","block_context":{"text":"Golang","link":"https:\/\/www.rangakrish.com\/index.php\/category\/golang\/"},"img":{"alt_text":"Non-streaming Mode","src":"https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2025\/02\/code1-300x227.png?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2025\/02\/code1-300x227.png?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/www.rangakrish.com\/wp-content\/uploads\/2025\/02\/code1-300x227.png?resize=525%2C300&ssl=1 1.5x"},"classes":[]}],"_links":{"self":[{"href":"https:\/\/www.rangakrish.com\/index.php\/wp-json\/wp\/v2\/posts\/3514","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.rangakrish.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.rangakrish.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.rangakrish.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.rangakrish.com\/index.php\/wp-json\/wp\/v2\/comments?post=3514"}],"version-history":[{"count":0,"href":"https:\/\/www.rangakrish.com\/index.php\/wp-json\/wp\/v2\/posts\/3514\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.rangakrish.com\/index.php\/wp-json\/wp\/v2\/media?parent=3514"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.rangakrish.com\/index.php\/wp-json\/wp\/v2\/categories?post=3514"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.rangakrish.com\/index.php\/wp-json\/wp\/v2\/tags?post=3514"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}