Applying Generative AI in Esri Data Interoperability
Applying Generative AI in Esri Data Interoperability Workflows
Structured data extraction is a key capability of Large Language Models (LLMs). Providers like OpenAI, Anthropic and Gemini offer APIs that transform unstructured content into clean JSON outputs. But LLMs alone aren’t enough. Without robust tools to automate, validate, and scale the process, you’re left with fragile scripts and manual clean-up. That’s where Esri Data Interoperability can help-seamlessly integrating generative AI into real-world data workflows.
- Understanding APIs: RESTful services, HTTP methods (GET, POST, PUT, DELETE), and authentication approaches including API keys, OAuth, and tokens.
- Configuring API and web connections for ArcGIS Online, Enterprise, and external services in Data Interoperability Workbench, including credential management.
- Making requests, configuring headers and parameters for ArcGIS REST APIs and handling response codes and error conditions.
- Parsing responses, extracting nested data and using JSONFlattener and JSONFragmenter to populate geodatabase feature classes.
- Custom Transformers: Building reusable API integration components, parameterising transformers for flexibility and sharing your API integrations.
- API integration: working with public APIs for geocoding, address lookup and data enrichment, connecting to ArcGIS Online and Enterprise REST services and combining data from multiple API sources.
- Handling failures and timeouts, implementing retry logic, logging interactions and managing ArcGIS Online credit rate limis.
Goals
- Effective prompt writing techniques and managing dynamic JSON outputs from AI services.
- A practical comparison of AI models from OpenAI, Gemini, Anthropic and local models using Ollama understanding when to use each.
- Learn how to incorporate custom image recognition using models trained and deployed in Roboflow as part of a data workflow.
- PDF document extraction and conversion into spatially enabled feature class attributes.
- Sentiment analysis and text classification techniques for unstructured text or image content.
Who is this course for?
GIS Analysts, GIS Technical Leads, Data Management Professionals, GIS Application Developers
Preknowledge
Attendees should have a basic working knowledge of the Esri Data Interoperability Extension for ArcGIS Pro, including understanding of readers, writers and transformers.
Attendees should understand how to:
- Run know how to run a Data Interoperability Workspace
- Work with readers and writers for common spatial data formats including Shapefile, GeoJSON and file geodatabase
- Apply basic transformers for data manipulation
This course does not require prior AI or machine learning experience.
Duration
1 day training course
Register now for an Esri Data Interoperability Training course
Please register via the Esri UK Training registration page
Training events:
- Bespoke or Private? Just ask!