Skip to main content

ArcGIS Pro AI Tools

Project description

ArcGIS Pro AI Toolbox

ArcGIS Pro AI Toolbox logo

PyPI - Downloads

Your GIS, now AI‑supercharged.


Quick Links


Why ArcGIS Pro AI Toolbox?

ArcGIS Pro AI Toolbox is the only BYOK, open‑source plugin that brings conversational AI, code generation, and prompt‑driven geoprocessing natively into ArcGIS Pro—no cloud hop, no proprietary credits.
  • Install in minutes. Prompt, generate, map—directly inside ArcGIS Pro.
  • Preconfigured with OpenRouter out of the box, while still working with OpenAI, Azure, Claude, DeepSeek, local LLMs, and more.
  • BYOK: Bring your own API key, keep your data private.
  • No cloud detour, no extra Esri credits, no code required.

Key Tools

  • Add AI Generated Field: Create rich text from attributes using AI.
  • Get Map Info: Extract map context to JSON for smarter prompts.
  • Generate Python Code: ArcPy snippets tuned to your map.
  • Create AI Feature Layer: Describe data, get a layer.
  • Convert Text to Numeric: Standardize messy columns fast.

Installation

There are two ways to get started with the ArcGIS Pro AI Toolbox:

  1. The Simple Way (Recommended):

    • Download the toolbox directly from the arcgispro_ai website.
    • Set up the required environment variables for your chosen AI provider(s)
    • Add the downloaded .pyt file to ArcGIS Pro and start using the tools immediately.
  2. The Python Way (For Advanced Users):

    • Install the package via pip:
      pip install arcgispro_ai
      
    • Set up the required environment variables for your chosen AI provider(s)
    • Use the tools programmatically or within ArcGIS Pro by referencing the installed package. This requires an import of the toolbox from a path like
       `C:\Users\<username>\AppData\Local\Programs\Python\Python<version>\Lib\site-packages\arcgispro_ai\toolboxes
    

Environment Variables

Set up the required environment variables for your chosen AI provider(s):

setx OPENROUTER_API_KEY "your-key-here"
setx OPENAI_API_KEY "your-key-here"
setx AZURE_OPENAI_API_KEY "your-key-here"
setx ANTHROPIC_API_KEY "your-key-here"
setx DEEPSEEK_API_KEY "your-key-here"

OpenRouter is the default provider for every tool, so configuring OPENROUTER_API_KEY is enough to start running prompts immediately. Set the other environment variables only if you plan to switch to those providers.

For local LLM setup

  • Deploy a compatible LLM server that implements the OpenAI chat completions API. That's up to you to figure out. idk, ask ChatGPT.
  • Make sure to configure the endpoint URL to http://localhost:8000 or you'll have to override it every time you want to run a tool.

Usage

  1. Leave the Source dropdown at OpenRouter (the default) or switch to another provider if you've configured its API key
  2. Configure any provider-specific settings (model, endpoint, etc.)
  3. Enter your prompt or query
  4. Execute the tool

Each tool starts on OpenRouter, so you can run with zero extra configuration. When you choose another provider, make sure its API key and settings are in place before executing the tool.

Supported AI Providers

  • OpenRouter (default): Unified API for multiple models including OpenAI, Gemini, Claude, Llama, and more (requires OPENROUTER_API_KEY)
  • OpenAI: GPT-4 and more (requires OPENAI_API_KEY)
  • Azure OpenAI: Microsoft-hosted (requires AZURE_OPENAI_API_KEY)
  • Claude (Anthropic): (requires ANTHROPIC_API_KEY)
  • DeepSeek: (requires DEEPSEEK_API_KEY)
  • Local LLM: No API key needed, OpenAI-compatible API
  • Wolfram Alpha: For math/computation (requires WOLFRAM_ALPHA_API_KEY)

OpenRouter Details

OpenRouter provides a single API that gives you access to dozens of AI models from various providers:

  • OpenAI models (GPT-4, GPT-3.5, etc.)
  • Google models (Gemini 2.0 Flash, etc.)
  • Anthropic models (Claude 3.5 Sonnet, etc.)
  • Meta models (Llama variants)
  • DeepSeek models
  • And many more

To use OpenRouter:

  1. Sign up for an API key at openrouter.ai
  2. Set your API key:
    setx OPENROUTER_API_KEY "your-openrouter-key"
    
  3. OpenRouter is already selected in every tool—leave the Source dropdown on OpenRouter (or switch back to it) to start using it immediately
  4. The Model dropdown automatically lists the entire OpenRouter catalog (free tiers floated to the top), so just pick the model you want or type its ID manually

Project Structure & Distribution Design

This project is organized for both maintainability and ease of distribution:

  • Modular Source Structure:

    • The codebase is organized into multiple Python modules and packages (see arcgispro_ai/ and arcgispro_ai/toolboxes/).
    • This modular design makes the code easy to maintain, test, and extend.
    • Utility functions, API clients, and tool logic are separated for clarity and reusability.
  • Monolithic .pyt for Distribution:

    • For end users, a single-file, monolithic Python Toolbox (.pyt) is generated (arcgispro_ai.pyt).
    • This file contains all required code inlined—no dependencies on the rest of the repo structure.
    • Users can simply download the .pyt and add it to ArcGIS Pro, with no need to install Python packages or clone the repo.
    • The monolithic .pyt is auto-generated by the build_monolithic_pyt.py script, which inlines all code and strips out internal imports.
    • The version of the .pyt always matches the package version (from setup.py), ensuring consistency with PyPI releases.
  • Release Management:

    • The release.sh script automates the version management and release process.
    • It automatically increments the patch version in setup.py, commits the change, and tags the release.
    • The script creates a Git tag with the new version number and pushes changes to the repository.
    • After pushing, it attempts to open the GitHub release page to facilitate release note creation.
    • This ensures consistent versioning between the codebase, PyPI releases, and GitHub tags.

Summary:

  • Developers benefit from a clean, modular codebase.
  • Users benefit from a simple, single-file download for ArcGIS Pro.
  • Releases are managed systematically with automated versioning.

See build_monolithic_pyt.py for details on how the monolithic .pyt is built.


Contributing

Make an issue or create a branch for your feature or bug fix, and submit a pull request.


Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

arcgispro_ai-0.0.19.tar.gz (2.2 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

arcgispro_ai-0.0.19-py2.py3-none-any.whl (29.2 kB view details)

Uploaded Python 2Python 3

File details

Details for the file arcgispro_ai-0.0.19.tar.gz.

File metadata

  • Download URL: arcgispro_ai-0.0.19.tar.gz
  • Upload date:
  • Size: 2.2 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: python-requests/2.32.5

File hashes

Hashes for arcgispro_ai-0.0.19.tar.gz
Algorithm Hash digest
SHA256 76c42655ef23dc606468c00de29ea5058f797de5663916d0014cf6662b2c029e
MD5 4dc81d05e49d0e4ff88c55911c3c147e
BLAKE2b-256 5663c12d58e3b1e99ea79b67c1fff16a120ff0c4186fc5d3f4c31ec4353746da

See more details on using hashes here.

File details

Details for the file arcgispro_ai-0.0.19-py2.py3-none-any.whl.

File metadata

File hashes

Hashes for arcgispro_ai-0.0.19-py2.py3-none-any.whl
Algorithm Hash digest
SHA256 40438ff0f219e1fcc18cb3a88417c51abb4d1e63d5c33a8dd7db93cc0f1015e9
MD5 d17723352973cf33b3df42e04018b24a
BLAKE2b-256 d917f06a313ae6bf21ffaaad75d900a7f048e46f9070dd0e3364c30ce7cfb9d6

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page