feat: ReACT agent example by yanxi0830 · Pull Request #166 · llamastack/llama-stack-apps

yanxi0830 · 2025-02-04T19:59:31Z

What does this PR do?

llama-stack-apps example for ReACT agent
For details, see https://github.com/meta-llama/llama-stack/discussions/975

Feature/Issue validation/testing/test plan

python -m examples.agents.react_agent

Sources

Please link relevant resources if necessary.

Before submitting

This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
Did you read the contributor guideline,
Pull Request section?
Was this discussed/approved via a Github issue? Please add a link
to it if that's the case.
Did you make sure to update the documentation with your changes?
Did you write any new necessary tests?

Thanks for contributing 🎉!

examples/agents/react_agent.py

yanxi0830 · 2025-02-05T21:06:12Z

examples/agents/react_agent.py

+from llama_stack_client.types.tool_def_param import Parameter
+
+
+class TorchtuneTool(ClientTool):


Will remove ClientTool into decorator in following PR.

Added in llamastack/llama-stack-client-python#127

# What does this PR do? - See https://github.com/meta-llama/llama-stack/discussions/975 **Changes** ✅ Bugfix ToolResponseMessage role ✅ Add ReACT default prompt + default output parser ✅ Add ReACTAgent wrapper 🚧 Remove ClientTool and simplify it as a decorator (separate PR, including llama-stack-apps) ✅ Make agent able to return structured outputs - Note that some remote provider do not support response_format structured outputs, add it as an optional flag when calling `ReActAgent` wrapper. ## Test Plan see test in llamastack/llama-stack-apps#166 ## Sources Please link relevant resources if necessary. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Ran pre-commit to handle lint / formatting issues. - [ ] Read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [ ] Updated relevant documentation. - [ ] Wrote necessary unit or integration tests.

yanxi0830 · 2025-02-05T23:24:55Z

Merge until llamastack/llama-stack-client-python#121 is released into pypi package.

ehhuang · 2025-02-05T23:33:32Z

examples/agents/react_agent.py

+
+    model = "meta-llama/Llama-3.1-8B-Instruct"
+
+    agent = ReActAgent(


What's your thinking behind having ReActAgent vs ReActAgentConfig + Agent? I seems that the former hides some configurations that were available, e.g. max_infer_iters? And the latter is consistent with how Agent is used.

ReActAgent is a simple wrapper and helper class that hides the configuration needed to create a ReActAgentConfig + Agent, otherwise they are the same. We can override configurations with custom_agent_config, and that brings it the same as using Agent.

Isn't it just as simple with ReActAgentConfig + Agent? Just one extra line to instantiate the Agent? Then we don't need custom_agent_config.

Yeah, I guess its the difference b/w:

agent = ReActAgent(client, model, builtin_toolgroups, client_tools)

v.s.

agent_config = get_react_agent_config(builtin_toolgroups, client_tools, json_response_format) agent = Agent(client, agent_config, client_tools, output_parser=ReActOutputParser())

former hides agent_config & output_parser, while latter needs users to know about output_parser, I guess its a matter of how much we want to hide from users

# What does this PR do? - address comments in #121 ## Test Plan - see llamastack/llama-stack-apps#166 ## Sources Please link relevant resources if necessary. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Ran pre-commit to handle lint / formatting issues. - [ ] Read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [ ] Updated relevant documentation. - [ ] Wrote necessary unit or integration tests.

# What does this PR do? - Add decorator for on callables for defining client side custom tools - Addresses: llamastack/llama-stack#948 ## Test Plan Usage: ```python @client_tool def add(x: int, y: int) -> int: '''Add 2 integer numbers :param x: integer 1 :param y: integer 2 :returns: sum of x + y ''' return x + y ``` `add` will be a ClientTool that can be passed - Working example in: llamastack/llama-stack-apps#166 ## Sources Please link relevant resources if necessary. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Ran pre-commit to handle lint / formatting issues. - [ ] Read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [ ] Updated relevant documentation. - [ ] Wrote necessary unit or integration tests.

# What does this PR do? - See discussion in #121 (comment) ## Test Plan test with llamastack/llama-stack-apps#166 ``` LLAMA_STACK_BASE_URL=http://localhost:8321 pytest -v tests/client-sdk/agents/test_agents.py::test_override_system_message_behavior --inference-model "meta-llama/Llama-3.3-70B-Instruct" ``` <img width="1697" alt="image" src="https://github.com/user-attachments/assets/c036cbf6-9fc1-4064-82af-fa1984300653" /> ## Sources Please link relevant resources if necessary. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Ran pre-commit to handle lint / formatting issues. - [ ] Read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [ ] Updated relevant documentation. - [ ] Wrote necessary unit or integration tests.

yanxi0830 added 4 commits February 3, 2025 15:59

react agent

e8dc718

tmp

de94244

example

1a493a9

update example

e28b16e

yanxi0830 requested review from ashwinb, dineshyv, dltn, ehhuang, hardikjshah and raghotham as code owners February 4, 2025 19:59

facebook-github-bot added the CLA Signed This label is managed by the Meta Open Source bot. label Feb 4, 2025

yanxi0830 marked this pull request as draft February 4, 2025 19:59

yanxi0830 mentioned this pull request Feb 4, 2025

[RFC] Agent Categorization + ReACT Agent OutputParser llamastack/llama-stack#955

Closed

yanxi0830 changed the title ~~[WIP] ReACT agent example~~ [RFC] ReACT agent example Feb 4, 2025

yanxi0830 marked this pull request as ready for review February 4, 2025 20:03

yanxi0830 mentioned this pull request Feb 4, 2025

[RFC] Client Agent SDK OutputParser llamastack/llama-stack-client-python#121

Merged

5 tasks

refactor

a8ac2f5

hardikjshah reviewed Feb 5, 2025

View reviewed changes

examples/agents/react_agent.py Outdated Show resolved Hide resolved

examples/agents/react_agent.py Outdated Show resolved Hide resolved

examples/agents/react_agent.py Outdated Show resolved Hide resolved

yanxi0830 added 5 commits February 5, 2025 10:31

use sdk

c205e6a

use sdk

9364c5b

wip builtin tool

ea4cf42

enable builtin tool

3f81f87

use sdk react

695a192

yanxi0830 commented Feb 5, 2025

View reviewed changes

hardikjshah approved these changes Feb 5, 2025

View reviewed changes

yanxi0830 mentioned this pull request Feb 5, 2025

minor fix ups llamastack/llama-stack-client-python#122

Closed

5 tasks

ehhuang reviewed Feb 5, 2025

View reviewed changes

yanxi0830 mentioned this pull request Feb 5, 2025

minor fix up react_agent llamastack/llama-stack-client-python#123

Merged

5 tasks

tool decorator working

f955808

yanxi0830 mentioned this pull request Feb 6, 2025

[SDK] add tool decorator helper for custom client tools llamastack/llama-stack-client-python#127

Merged

5 tasks

update agent

fc4fae7

yanxi0830 mentioned this pull request Feb 7, 2025

OutputParser -> ToolParser refactor llamastack/llama-stack-client-python#130

Merged

5 tasks

ashwinb changed the title ~~[RFC] ReACT agent example~~ feat: ReACT agent example Feb 7, 2025

ashwinb approved these changes Feb 7, 2025

View reviewed changes

ashwinb merged commit 37c4100 into main Feb 7, 2025
1 check passed

ashwinb deleted the react_agent branch February 7, 2025 22:06

This was referenced Feb 26, 2025

Add Reflexion Agent Implementation redhat-et/agent-frameworks#27

Closed

feat: Implement Reflexion Prompting Template llamastack/llama-stack#1389

Closed

raghotham mentioned this pull request Jan 13, 2026

Discussion #975: [RFC] Agent Categorization + ReACT Agent OutputParser llamastack/llama-stack#4582

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat: ReACT agent example#166

feat: ReACT agent example#166
ashwinb merged 12 commits intomainfrom
react_agent

yanxi0830 commented Feb 4, 2025 •

edited

Loading

Uh oh!

Uh oh!

Uh oh!

Uh oh!

yanxi0830 Feb 5, 2025

Uh oh!

yanxi0830 Feb 6, 2025

Uh oh!

yanxi0830 commented Feb 5, 2025

Uh oh!

ehhuang Feb 5, 2025

Uh oh!

yanxi0830 Feb 5, 2025

Uh oh!

ehhuang Feb 5, 2025

Uh oh!

yanxi0830 Feb 6, 2025 •

edited

Loading

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

5 participants

		from llama_stack_client.types.tool_def_param import Parameter


		class TorchtuneTool(ClientTool):


		model = "meta-llama/Llama-3.1-8B-Instruct"

		agent = ReActAgent(

Conversation

yanxi0830 commented Feb 4, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

What does this PR do?

Feature/Issue validation/testing/test plan

Sources

Before submitting

Uh oh!

Uh oh!

Uh oh!

Uh oh!

yanxi0830 Feb 5, 2025

Choose a reason for hiding this comment

Uh oh!

yanxi0830 Feb 6, 2025

Choose a reason for hiding this comment

Uh oh!

yanxi0830 commented Feb 5, 2025

Uh oh!

ehhuang Feb 5, 2025

Choose a reason for hiding this comment

Uh oh!

yanxi0830 Feb 5, 2025

Choose a reason for hiding this comment

Uh oh!

ehhuang Feb 5, 2025

Choose a reason for hiding this comment

Uh oh!

yanxi0830 Feb 6, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

5 participants

yanxi0830 commented Feb 4, 2025 •

edited

Loading

yanxi0830 Feb 6, 2025 •

edited

Loading