MCP Server Framework and Tool Development library for building custom capabilities into agents.
Find a file
Nate Barbettini d37303de6a
Clean up retryable errors (#21)
Clean up logic of retries
2024-08-27 16:19:22 -07:00
.github Introduce arcade run and arcade chat Commands (#15) 2024-08-19 16:17:38 -07:00
arcade Clean up retryable errors (#21) 2024-08-27 16:19:22 -07:00
docker Dockerfiles for Actor container (#18) 2024-08-22 16:28:42 -07:00
examples Retryable errors (#20) 2024-08-22 16:17:15 -07:00
schemas/preview Clean up retryable errors (#21) 2024-08-27 16:19:22 -07:00
toolkits Clean up retryable errors (#21) 2024-08-27 16:19:22 -07:00
.editorconfig MyPy Compliant (#5) 2024-07-16 17:01:38 -07:00
.gitignore Spike FlaskActor and cleanup of BaseActor (#12) 2024-08-05 13:26:56 -07:00
.pre-commit-config.yaml MyPy Compliant (#5) 2024-07-16 17:01:38 -07:00
.prettierrc.toml MyPy Compliant (#5) 2024-07-16 17:01:38 -07:00
CONTRIBUTING.md MyPy Compliant (#5) 2024-07-16 17:01:38 -07:00
cspell.config.yaml Refactor into library approach (#7) 2024-07-23 16:26:54 -07:00
LICENSE Tool SDK, Schemas (#2) 2024-07-14 23:37:46 -07:00
README.md Cleanup examples and README (#8) 2024-07-24 09:10:31 -07:00

Release Build status codecov Commit activity License

Arcade AI

Arcade AI is the developer platform for building tools designed to be used with language models. With Arcade, developers can create, deploy, and easily integrate new tools with language models to enhance their capabilities.

arcade-ai

The arcade-ai package contains:

  • arcade CLI
  • arcade.sdk Tool SDK
  • arcade.actor serving tools with FastAPI, Flask, or Django

Installation

To install the Arcade AI package, execute the following command:

pip install arcade-ai

or install from source:

git clone https://github.com/arcadeai/arcade-ai.git
cd arcade-ai
pip install poetry
poetry install

First steps

Follow these steps if you've cloned the repo and installed the package from source:

cd examples/websearch
poetry install

arcade show arcade_websearch

This will show an output that looks like

┏━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━┳━━━━━━━━━┓ ┃ Name ┃ Description ┃ Toolkit ┃ Version ┃ ┡━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━╇━━━━━━━━━┩ │ SearchGoogle │ Search Google using SerpAPI and return organic search results. │ websearch │ 0.1.0 │ └──────────────┴────────────────────────────────────────────────────────────────┴───────────┴─────────┘

Predict the parameters with a model and run the tool with the predicted parameters. Arcade adds the execute choice to the tool, which allows you to run the tool with the predicted parameters in a single request.

> arcade run arcade_websearch "who is Sam Partee?" --choice "execute"
Running tool: SearchGoogle with params: {'query': 'Sam Partee'}

[{"position": 1, "title": "Sam Partee (@SamPartee) / X", "link": "https://twitter.com/sampartee", "redirect_link":
"https://www.google.com/url?sa=t&source=web&rct=j&opi=89978449&url=https://twitter.com/sampartee&ved=2ahUKEwjBwKiz3b6HAxV1VTABHXL8BZQQFnoECAYQAQ",
"displayed_link": "1.5K+ followers", "thumbnail":
.....
.. (truncated)

Arcade also adds the predict choice to the tool, which allows you to predict the parameters with a model.

> arcade run arcade_websearch "who is Sam Partee?" --choice "predict" # also the default
Running tool: SearchGoogle with params: {'query': 'Sam Partee'}

Sam Partee is a CTO, Co-founder of Arcade AI and former Machine Learning Engineer at companies like RedisInc and HPE_Cray. They have
expertise in AI/ML, vector search, Python, HPC, and are a sports fan.