"},{"ID":6911,"user_firstname":"Rohit","user_lastname":"Singh","nickname":"Rohit Singh","user_nicename":"rsinghesri-com","display_name":"Rohit Singh","user_email":"rsingh@esri.com","user_url":"","user_registered":"2018-03-02 00:19:00","user_description":"Rohit Singh is Director of Esri\u2019s R&D Center in New Delhi, leading the design and development of Geospatial AI capabilities across the ArcGIS platform. He has played a key role in the development of ArcGIS API for Python, ArcGIS Java Engine API, and the Linux enablement of ArcGIS. An alumnus of IIT Kharagpur, Rohit holds an MS in Computer Science with specialization in AI from Georgia Tech.","user_avatar":"
"}],"short_description":"Connect ArcGIS Pro with third party AI models using secure connection file to integrate cloud-based text, imagery, and multimodal analysis.","flexible_content":[{"acf_fc_layout":"content","content":"In recent years, hosted AI services have quickly become the main way for organizations to access and use deep learning models. Instead of downloading and running models locally, many now rely on cloud platforms such as OpenAI, Azure, Hugging Face, Google, AWS, and Anthropic to deliver ready-to-use language, vision, and multimodal models. These services remove the need for complex local infrastructure, instantly provide access to the latest model updates, and effortlessly scale as data volumes grow.<\/p>\n
For GIS professionals, this shift means that powerful AI capabilities can be integrated directly into mapping and spatial workflows when there\u2019s a secure and efficient way to connect ArcGIS Pro with these third party hosted models. ArcGIS Pro includes powerful built-in tools for deep learning, which traditionally required models to be downloaded and run locally. Nowadays, many models, such as OpenAI\u2019s GPT for text analysis or Google\u2019s Gemini for imagery and multimodal analysis, can only be accessed remotely through secure cloud APIs. \u00a0These third-party LLMs and cloud AI services can be integrated with ArcGIS Pro by creating custom deep learning packages. Such packages can use Python raster functions<\/a> for imagery analysis and Python NLP functions<\/a> for text analysis, allowing these third party hosted AI services to be called directly within your workflows. To securely connect to those models, you need credentials and configuration details.<\/p>\n This is where the Create AI Service Connection File<\/strong> tool becomes essential: it allows you to create a reusable .ais file that stores endpoint information, API tokens, and model details. Once created, this file can be used by third-party models inside ArcGIS Pro to securely connect to third party AI services\u2014just as they would to a local deep learning model\u2014without repeatedly entering sensitive credentials.<\/p>\n \u00a0<\/span><\/p>\n When working with the third party AI models, every provider\u2014whether it\u2019s OpenAI, Azure, AWS, Hugging Face, Google, or Anthropic\u2014 requires some combination of credentials and settings. It could be an API key, a model ID, or even the region where the service is running. \u00a0Entering them manually each time you use a third party AI model is inefficient and can lead to errors.<\/p>\n The Create AI Service Connection File tool in ArcGIS Pro solves this problem. It lets you create a file that keeps tracks all configuration details for a given service. General information, such as the model\u2019s name or endpoint, is written into the file, while sensitive information, such as API keys, is securely stored in the Windows Credential Manager. This design ensures your keys remain safe, won\u2019t appear in logs, and can only be used from your account on that machine.<\/p>\n To see how the service connection file works, consider a scenario where you want to use a third party AI model, such as an Azure OpenAI deployment, in ArcGIS Pro. Instead of manually entering your endpoint and credentials every time, you can create a connection file for the service.<\/p>\n When setting up Azure as your provider, the tool will ask you for the following information:<\/p>\n The first three values are stored directly in the .ais file, while the API key is treated as sensitive information. It\u2019s never written to the file; instead, it\u2019s stored in Windows Credential Manager and referenced securely. <\/span>\u00a0<\/span><\/p>\n Here\u2019s a simplified example of what the resulting .ais file might look like for Azure:<\/p>\n"},{"acf_fc_layout":"content","content":" In the “token” field does not contain your real API key; instead, it contains a random GUID (globally unique identifier) that\u2019s automatically generated when the key is stored in Windows Credential Manager.<\/p>\n Once your connection file is created, you don\u2019t need to worry about manually managing the API key. You can simply load the .ais file using the arcgis.learn API in your Python raster (or NLP) function<\/p>\n"},{"acf_fc_layout":"content","content":" This code securely fetches the stored key, reads the model parameters, and prepares them for use in your workflow.<\/p>\n In addition to Azure, the Create AI Service Connection File tool supports a wide range of provider. While each service has its own set of parameters, the overall structure remains the same: general details are stored in the .ais file, and sensitive credentials are replaced with a GUID that points back to your Windows Credential Manager.<\/p>\n If your provider isn\u2019t listed, you can define your own. For instance:<\/p>\n \u00a0<\/strong><\/p>\n In ArcGIS Pro, custom deep learning packages (DLPKs) serve as an extensibility feature, enabling you to securely connect to external AI services and integrate them directly into your workflows. By leveraging these DLPKs, you can enhance geospatial analysis with state-of-the-art AI capabilities without leaving the ArcGIS Pro environment.<\/p>\n \u00a0<\/strong><\/p>\n In a custom deep learning package, the getConfiguration method can retrieve connection details from the AI service connection file and establish a secure connection to the third party hosted AI service. This method is responsible for:<\/p>\n The example below demonstrates how to read a connection file and establish a connection to an Azure OpenAI service.<\/p>\n <\/p>\n"},{"acf_fc_layout":"content","content":" “”” “”” # Load the AI service connection file provided by the user # Extract relevant connection details # Initialize the client for interacting with the hosted Azure OpenAI service # Return kwargs so other methods can access additional parameters if needed<\/p>\n <\/p>\n"},{"acf_fc_layout":"content","content":" Once the getConfiguration method retrieves the connection details and establishes a secure\u00a0connection to the third party AI service, the model is ready to perform inference. The predict<\/em> method can now use the parameters and credentials stored during getConfiguration to send input data to the service and receive predictions.<\/p>\n \u00a0<\/strong><\/p>\n ArcGIS Pro\u2019s support for third-party AI models transforms how GIS professionals work with text, imagery, and spatial data. With the connection file handling authentication, you can tap into third party AI services to run entity extraction, image classification, and more while keeping your attention where it belongs\u2014on the analysis.<\/p>\n"}],"related_articles":[{"ID":2734992,"post_author":"350252","post_date":"2025-05-15 01:05:38","post_date_gmt":"2025-05-15 08:05:38","post_content":"","post_title":"Boosting GeoAI Model Performance with Test Time Augmentation","post_excerpt":"","post_status":"publish","comment_status":"open","ping_status":"closed","post_password":"","post_name":"boosting-geoai-model-performance-with-test-time-augmentation","to_ping":"","pinged":"","post_modified":"2025-05-30 07:18:20","post_modified_gmt":"2025-05-30 14:18:20","post_content_filtered":"","post_parent":0,"guid":"https:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&p=2734992","menu_order":0,"post_type":"blog","post_mime_type":"","comment_count":"0","filter":"raw"},{"ID":2945812,"post_author":"254042","post_date":"2025-11-18 09:45:06","post_date_gmt":"2025-11-18 17:45:06","post_content":"","post_title":"What's New for GeoAI in the ArcGIS Pro 3.6 Image Analyst Extension","post_excerpt":"","post_status":"publish","comment_status":"open","ping_status":"closed","post_password":"","post_name":"whats-new-for-geoai-in-the-arcgis-pro-3-6-image-analyst-extension","to_ping":"","pinged":"","post_modified":"2025-12-22 13:44:27","post_modified_gmt":"2025-12-22 21:44:27","post_content_filtered":"","post_parent":0,"guid":"https:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&p=2945812","menu_order":0,"post_type":"blog","post_mime_type":"","comment_count":"0","filter":"raw"},{"ID":2515452,"post_author":"348302","post_date":"2024-10-10 07:00:37","post_date_gmt":"2024-10-10 14:00:37","post_content":"","post_title":"New Pretrained Geospatial AI Models for Disaster Response","post_excerpt":"","post_status":"publish","comment_status":"open","ping_status":"closed","post_password":"","post_name":"new-pretrained-geospatial-ai-models-for-disaster-response","to_ping":"","pinged":"","post_modified":"2024-10-10 09:24:23","post_modified_gmt":"2024-10-10 16:24:23","post_content_filtered":"","post_parent":0,"guid":"https:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&p=2515452","menu_order":0,"post_type":"blog","post_mime_type":"","comment_count":"0","filter":"raw"}],"show_article_image":false,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/11\/banner_mg1_84.png","wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/11\/banner_mg1910.png"},"yoast_head":"\nAI Service connection file<\/strong><\/h2>\n
Create a connection file<\/strong><\/h3>\n
Required information<\/strong> <\/span><\/h3>\n
\n
\nExample: https:\/\/mytestazureopenai.openai.azure.com\/<\/li>\n
\nExample: gpt-4o<\/li>\n
\nExample: 2024-05-01<\/li>\nCreate AI Service Connection File tool<\/strong><\/h2>\n"},{"acf_fc_layout":"image","image":{"ID":2948621,"id":2948621,"title":"tool_ui","filename":"Picture1-4.png","filesize":36827,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/11\/Picture1-4.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/use-hosted-ai-services-with-arcgis-pro\/picture1-157","alt":"Create AI Service Connection tool","author":"421001","description":"Create AI Service Connection tool","caption":"Create AI Service Connection tool","name":"picture1-157","status":"inherit","uploaded_to":2948618,"date":"2025-11-17 06:41:25","modified":"2025-11-17 06:42:02","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":288,"height":458,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/11\/Picture1-4-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/11\/Picture1-4.png","medium-width":164,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/11\/Picture1-4.png","medium_large-width":288,"medium_large-height":458,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/11\/Picture1-4.png","large-width":288,"large-height":458,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/11\/Picture1-4.png","1536x1536-width":288,"1536x1536-height":458,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/11\/Picture1-4.png","2048x2048-width":288,"2048x2048-height":458,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/11\/Picture1-4.png","card_image-width":288,"card_image-height":458,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/11\/Picture1-4.png","wide_image-width":288,"wide_image-height":458}},"image_position":"center","orientation":"horizontal","hyperlink":"https:\/\/pro.arcgis.com\/en\/pro-app\/latest\/tool-reference\/data-management\/create-ai-service-connection-file.htm"},{"acf_fc_layout":"content","content":"
Output connection file<\/strong><\/h2>\n
{
\n\"version\": \"1.0\",
\n\"serviceProvider\": \"Azure\",
\n\"protocol\": \"https\",
\n\"host\": \"mytestazureopenai.openai.azure.com\/\",
\n\"authenticationScheme\": \"accessToken\",
\n\"authenticationProperties\": {
\n\"parameterType\": \"header\",
\n\"parameterName\": \"azure_api_key\"
\n},
\n\"authenticationSecrets\": {\"token\": \" \"},
\n\"serviceProviderProperties\": {
\n\"deployment_name\": \"gpt-4o\",
\n\"api_version\" : \"2024-05-01\"
\n}
\n}<\/code><\/p>\n"},{"acf_fc_layout":"content","content":"Retrieving credentials in Python<\/strong><\/h2>\n
from arcgis.learn import AIServiceConnection
\nconn = AIServiceConnection(\"azure_openai.ais\")
\nparams = conn.get_dict()
\napi_key = params[\"authenticationSecrets\"][\"token\"]
\nprint(api_key)
\n<\/code><\/p>\n"},{"acf_fc_layout":"content","content":"Other service providers<\/strong><\/h2>\n
\n
\n
\n
\n
\n
\n
\n
\n
Third-party AI model integration<\/strong><\/h2>\n
Establishing connections<\/strong><\/h3>\n
\n
def getConfiguration(self, **kwargs):<\/code><\/p>\n
\nRetrieves connection details from the AI Service Connection File
\nand establishes a connection to the third party hosted AI service.<\/p>\n
\n# Import required modules
\nfrom arcgis.learn import AIServiceConnection
\nfrom openai import AzureOpenAI<\/p>\n
\ncon = AIServiceConnection(kwargs[“ai_connection_file”])
\ncfg = con.get_dict()<\/p>\n
\nself.azure_endpoint = cfg[“serviceProviderProperties”][“endpoint_uri”]
\nself.api_key = cfg[“authenticationSecrets”][“token”] # Secure token reference
\nself.api_version = cfg[“serviceProviderProperties”][“api_version”]
\nself.deployment_name = cfg[“serviceProviderProperties”][“deployment_name”]<\/p>\n
\nself.client = AzureOpenAI(
\nazure_endpoint=self.azure_endpoint,
\napi_key=self.api_key,
\napi_version=self.api_version
\n)<\/p>\nConclusion<\/strong><\/h2>\n