![\"Integrating](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2025\/03\/Integrating-Azure-OpenAI-models.png\")
<\/p>\n<\/p>\n
In the previous blog<\/a>, we have explored how to install and configure Azure OpenAI Service, now we will be unlocking its potential further by integrating the appropriate model in your projects by programmatically in Microsoft Dynamics 365 CRM.<\/p>\n Imagine a world where customer service agents don\u2019t have to spend time searching through endless records to find the information they need. Thanks to Azure AI and its integration with Microsoft Dynamics CRM, this is now a reality. Instead of manually digging through customer data, agents can simply ask questions to AI assistant, like \u201cWhat\u2019s the status of this customer\u2019s last order?\u201d or \u201cHas this customer raised any previous support tickets?\u201d and get instant, accurate answers.<\/p>\n This seamless, AI-powered interaction transforms the customer service experience, enabling agents to respond quickly and provide personalized support without the hassle of searching for details. With natural language processing and real-time insights, Azure AI makes it easier than ever for agents to focus on what really matters\u2014solving problems and delighting customers.<\/p>\n Before getting started, ensure you have:<\/p>\n You can follow the steps in the following article, if you are new to this concept and want to learn how to create an Azure OpenAI service & deploy an OpenAI model<\/a>.<\/p>\n Here\u2019s the JavaScript code that will interact with the Azure OpenAI API using jQuery for AJAX requests. The code allows you to retrieve account data dynamically from the CRM, send it along with user queries to GPT-4o Mini, and display the response in a chatbot UI.<\/p>\n In this code:<\/p>\n To upload and integrate a web resource in Dynamics 365 CRM, go to Settings > Solutions<\/strong>, create or select a solution, paste the above code under Web Resources<\/strong>, save and publish it, then navigate to the form, insert the web resource, position it, and publish the form.<\/p>\n Integrating Azure AI Services, specifically the GPT-4o Mini model, into your Dynamics 365 CRM using JavaScript and jQuery can provide a highly interactive and intelligent chatbot feature. By following the steps outlined in this blog, you can easily set up an AI-driven chatbot that leverages real-time data from Dynamics 365 CRM, helping improve user engagement and automate responses to common queries.<\/p>\n","protected":false},"excerpt":{"rendered":" In the previous blog, we have explored how to install and configure Azure OpenAI Service, now we will be unlocking its potential further by integrating the appropriate model in your projects by programmatically in Microsoft Dynamics 365 CRM. Imagine a world where customer service agents don\u2019t have to spend time searching through endless records to\u2026 Read More »<\/a><\/span><\/p>\n","protected":false},"author":15,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"om_disable_all_campaigns":false,"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":""},"categories":[2843,2361],"tags":[3127],"class_list":["post-40612","post","type-post","status-publish","format-standard","hentry","category-azure-openai","category-technical","tag-azure-openai-models"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/posts\/40612","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/users\/15"}],"replies":[{"embeddable":true,"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/comments?post=40612"}],"version-history":[{"count":0,"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/posts\/40612\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/media?parent=40612"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/categories?post=40612"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/tags?post=40612"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}Prerequisites<\/strong><\/h2>\n
\n
Configuration<\/strong><\/h2>\n
1. Creating a Service & Deploying a model:<\/strong><\/h3>\n
2. Access the API Key & Url :<\/strong><\/h3>\n
\n
![\"Azure](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2025\/03\/1Azure-OpenAI-models.png\")
<\/p>\n3. JavaScript Code for GPT-4o mini Integration: <\/strong><\/h3>\n
\/\/ Define the Azure OpenAI API endpoint and API key\r\n\r\nvar apiKey = \"YOUR_API_KEY\"; \/\/ Replace with your Azure OpenAI API key\r\n\r\nvar endpoint = \"YOUR_ENDPOINT_URL\"; \/\/ Replace with your Azure OpenAI API \u00a0endpoint\r\n\r\nvar model = \"gpt-4o-mini\"; \/\/Replace with the appropriate model\r\n\r\n\/\/ System message to guide the assistant's behaviour\r\n\r\nvar systemMessage = {\r\n\r\nrole: 'system',\r\n\r\ncontent: \"The intelligent assistant is designed to interpret user prompts and deliver \r\ntailored responses for general queries. For general inquiries, such as informational or exploratory questions, the assistant utilizes its internal knowledge base to provide accurate, fact-based answers derived from historical data.\"\r\n\r\n};\r\n\r\n\/\/ Function to get the current Account ID dynamically from the CRM form\r\n\r\nfunction getAccountId() {\r\n\r\nvar formContext = parent.Xrm.Page || window.formContext;\r\n\r\nvar accountId = formContext.data.entity.getId();\r\n\r\nreturn accountId ? accountId.replace(\/[{}]\/g, '') : null;\r\n\r\n}\r\n\r\n\/\/ Function to retrieve account data using jQuery AJAX\r\n\r\nfunction retrieveAccountData(accountId) {\r\n\r\nvar serverUrl = parent.Xrm.Utility.getGlobalContext().getClientUrl();\r\n\r\nvar query = `${serverUrl}\/api\/data\/v9.2\/accounts?$filter=accountid eq '${accountId}'`;\r\n\r\nreturn $.ajax({\r\n\r\nurl: query,\r\n\r\nmethod: \"GET\",\r\n\r\nheaders: { \"Accept\": \"application\/json\" },\r\n\r\ndataType: \"json\"\r\n\r\n}).then(response => response, error => {\r\n\r\nconsole.error('Error retrieving account data:', error);\r\n\r\nreturn null;\r\n\r\n});\r\n\r\n}\r\n\r\n\/\/ Function to send request to OpenAI API using jQuery AJAX\r\n\r\nfunction getGPTResponse(query, accountData) {\r\n\r\nvar requestBody = {\r\n\r\nmodel: model,\r\n\r\nmessages: [\r\n\r\nsystemMessage,\r\n\r\n{ role: \"user\", content: `Here is some information about the account: ${JSON.stringify(accountData)}. ${query}` }\r\n\r\n]\r\n\r\n};\r\n\r\nreturn $.ajax({\r\n\r\nurl: endpoint,\r\n\r\nmethod: \"POST\",\r\n\r\nheaders: {\r\n\r\n\"Content-Type\": \"application\/json\",\r\n\r\n\"api-key\": apiKey\r\n\r\n},\r\n\r\ndata: JSON.stringify(requestBody),\r\n\r\ndataType: \"json\"\r\n\r\n}).then(response => response.choices[0].message.content, error => {\r\n\r\nconsole.log(\"Error calling OpenAI API:\", error);\r\n\r\nreturn \"Sorry, I couldn't process your request.\";\r\n\r\n});\r\n\r\n}\r\n\r\n\/\/ Function to send the user query and get a response\r\n\r\nfunction sendQuery() {\r\n\r\nvar userQuery = $('#user-input').val();\r\n\r\nif (!userQuery) return;\r\n\r\n\/\/ Display user query in chat box\r\n\r\nvar chatBox = $('#chat-box');\r\n\r\nchatBox.append(`<div><b>You:<\/b> ${userQuery}<\/div>`);\r\n\r\n\/\/ Get Account ID dynamically\r\n\r\nvar accountId = getAccountId();\r\n\r\nif (!accountId) {\r\n\r\nalert(\"No account ID found.\");\r\n\r\nreturn;\r\n\r\n}\r\n\r\n\/\/ Retrieve account data, then send it to OpenAI API\r\n\r\nretrieveAccountData(accountId).then(accountData => {\r\n\r\nreturn getGPTResponse(userQuery, accountData);\r\n\r\n}).then(response => {\r\n\r\nchatBox.append(`<div><b>Bot:<\/b> ${response}<\/div>`);\r\n\r\n$('#user-input').val('');\r\n\r\nchatBox.scrollTop(chatBox[0].scrollHeight);\r\n\r\n});\r\n\r\n}\r\n\r\n\/\/ Bind the send button click event\r\n\r\n$(document).ready(() => {\r\n\r\n$('#send-btn').on('click', sendQuery);\r\n\r\n});<\/pre>\n\n
4. Integrate the agent in CRM dynamics 365.<\/strong><\/h3>\n
5. Test the Chatbot (<\/strong>Once everything is set up, test the integration):<\/h3>\n
\n
![\"Azure](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2025\/03\/2Azure-OpenAI-models.png\")
<\/p>\nConclusion<\/strong><\/h3>\n