Update OpenAI agents guide python #645
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
app/en/guides/agent-frameworks/openai-agents/use-arcade-with-openai-agents/page.mdx
Show resolved
Hide resolved
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
|
|
||
| # Setup Arcade with OpenAI Agents SDK | ||
|
|
||
| The [OpenAI Agents SDK](https://openai.github.io/openai-agents-python/) is a popular Python library for building AI agents. It is built on top of the OpenAI API, and provides a simple interface for building agents. |
Contributor
There was a problem hiding this comment.
Google.Passive: Changed 'is built' to 'builds' for active voice and removed condescending 'simple'
Suggested change
| The [OpenAI Agents SDK](https://openai.github.io/openai-agents-python/) is a popular Python library for building AI agents. It is built on top of the OpenAI API, and provides a simple interface for building agents. | |
| The [OpenAI Agents SDK](https://openai.github.io/openai-agents-python/) is a popular Python library for building AI agents. It builds on top of the OpenAI API, and provides an interface for building agents. |
| <GuideOverview> | ||
| <GuideOverview.Outcomes> | ||
|
|
||
| Learn how to integrate Arcade tools using OpenAI Agents primitives. You will implement a CLI agent that can user Arcade tools to help the user with their requests. Tools that require authorization will be handled automatically by the harness, so users don't need to worry about it. |
Contributor
There was a problem hiding this comment.
Google.Passive: Changed passive 'will be handled' to active voice 'handles'
Suggested change
| Learn how to integrate Arcade tools using OpenAI Agents primitives. You will implement a CLI agent that can user Arcade tools to help the user with their requests. Tools that require authorization will be handled automatically by the harness, so users don't need to worry about it. | |
| Learn how to integrate Arcade tools using OpenAI Agents primitives. You will implement a CLI agent that can user Arcade tools to help the user with their requests. The harness handles tools that require authorization automatically, so users don't need to worry about it. |
|
|
||
| ## The agent architecture you will build in this guide | ||
|
|
||
| The OpenAI Agents SDK provides an [Agent](https://openai.github.io/openai-agents-python/ref/agent/#agents.agent.Agent) class that implements a ReAct agent. It provides a simple interface for you to define the system prompt, the model, the tools, and possible sub-agents that can be used with handoffs. In this guide, you will manually keep track of the agent's history and state, and use the `run` method to invoke the agent in an agentic loop. |
Contributor
There was a problem hiding this comment.
alex.Condescending: Removed condescending 'simple' and changed passive 'that can be used' to active voice 'for handoffs'
Suggested change
| The OpenAI Agents SDK provides an [Agent](https://openai.github.io/openai-agents-python/ref/agent/#agents.agent.Agent) class that implements a ReAct agent. It provides a simple interface for you to define the system prompt, the model, the tools, and possible sub-agents that can be used with handoffs. In this guide, you will manually keep track of the agent's history and state, and use the `run` method to invoke the agent in an agentic loop. | |
| The OpenAI Agents SDK provides an [Agent](https://openai.github.io/openai-agents-python/ref/agent/#agents.agent.Agent) class that implements a ReAct agent. It provides an interface for you to define the system prompt, the model, the tools, and possible sub-agents for handoffs. In this guide, you will manually keep track of the agent's history and state, and use the `run` method to invoke the agent in an agentic loop. |
| import json | ||
| ``` | ||
|
|
||
| This is quite a number of imports, let's break them down: |
Contributor
There was a problem hiding this comment.
write-good.Weasel: Removed weasel word 'quite' and avoided first-person plural 'let's'
Suggested change
| This is quite a number of imports, let's break them down: | |
| This is a number of imports, here's a breakdown: |
|
|
||
| Here you get the Arcade tools you want the agent to use, and transform them into OpenAI Agents tools. The first step is to initialize the Arcade client, and get the tools you want to use. Since OpenAI is itself an inference provider, the Arcade API provides a convenient endpoint to get the tools in the OpenAI format, which is also the format expected by the OpenAI Agents framework. | ||
|
|
||
| This helper function is fairly long, here's a breakdown of what it does for clarity: |
Contributor
There was a problem hiding this comment.
write-good.Weasel: Removed weasel word 'fairly'
Suggested change
| This helper function is fairly long, here's a breakdown of what it does for clarity: | |
| This helper function is long, here's a breakdown of what it does for clarity: |
| - Get the tools from the configured MCP Servers | ||
| - Create an agent with the configured tools | ||
| - Initialize the conversation | ||
| - Run the loop! |
Contributor
There was a problem hiding this comment.
Google.Exclamation: Removed exclamation point
Suggested change
| - Run the loop! | |
| - Run the loop |
| - Initialize the conversation | ||
| - Run the loop! | ||
|
|
||
| The loop is a simple while loop that captures the user input, appends it to the conversation history, and then runs the agent. The agent's response is then appended to the conversation history, and the loop continues. |
Contributor
There was a problem hiding this comment.
alex.Condescending: Removed condescending 'simple'
Suggested change
| The loop is a simple while loop that captures the user input, appends it to the conversation history, and then runs the agent. The agent's response is then appended to the conversation history, and the loop continues. | |
| The loop is a while loop that captures the user input, appends it to the conversation history, and then runs the agent. The agent's response is then appended to the conversation history, and the loop continues. |
|
|
||
| # initialize the conversation | ||
| history: list[TResponseInputItem] = [] | ||
| # run the loop! |
Contributor
There was a problem hiding this comment.
Google.Exclamation: Removed exclamation point
Suggested change
| # run the loop! | |
| # run the loop |
|
|
||
| # initialize the conversation | ||
| history: list[TResponseInputItem] = [] | ||
| # run the loop! |
Contributor
There was a problem hiding this comment.
Google.Exclamation: Removed exclamation point
Suggested change
| # run the loop! | |
| # run the loop |
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Preview here: https://docs-git-mateo-dev-143-update-openai-agents-qu-dad705-arcade-ai.vercel.app/en/guides/agent-frameworks/openai-agents/use-arcade-with-openai-agents
New version of the OpenAI agents SDK and Arcade tutorial. We now:
Note
Adds a new guide and restructures OpenAI Agents docs
use-arcade-with-openai-agentsguide: builds a CLI agent using OpenAI Agents SDK (Python), implements an agentic loop, transforms Arcade tools to AgentsFunctionTools, and handles JIT tool authorization viaarcadepy.use-arcade-toolsanduser-auth-interrupts; cleans up references.Navigation and references updates
_meta.tsxand overview “Next steps” to point to the new guide and tidy copy.public/llms.txtto drop old links and add the new OpenAI Agents SDK guide entry.Written by Cursor Bugbot for commit 7b73c15. This will update automatically on new commits. Configure here.