feat: ReACT agent example #166
Merged
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
yanxi0830
requested review from
ashwinb,
dineshyv,
dltn,
ehhuang,
hardikjshah and
raghotham
as code owners
facebook-github-bot
added
the
CLA Signed
5 tasks
hardikjshah
reviewed
Feb 5, 2025
yanxi0830
commented
Feb 5, 2025
examples/agents/react_agent.py
Outdated
| from llama_stack_client.types.tool_def_param import Parameter | ||
|
|
||
|
|
||
| class TorchtuneTool(ClientTool): |
Contributor
Author
There was a problem hiding this comment.
Will remove ClientTool into decorator in following PR.
Contributor
Author
There was a problem hiding this comment.
hardikjshah
approved these changes
Feb 5, 2025
yanxi0830
added a commit
to llamastack/llama-stack-client-python
that referenced
this pull request
Feb 5, 2025
# What does this PR do? - See llamastack/llama-stack#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.
Contributor
Author
|
Merge until llamastack/llama-stack-client-python#121 is released into pypi package. |
5 tasks
ehhuang
reviewed
Feb 5, 2025
|
|
||
| model = "meta-llama/Llama-3.1-8B-Instruct" | ||
|
|
||
| agent = ReActAgent( |
Contributor
There was a problem hiding this comment.
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.
Contributor
Author
There was a problem hiding this comment.
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.
Contributor
There was a problem hiding this comment.
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.
Contributor
Author
There was a problem hiding this comment.
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
5 tasks
yanxi0830
added a commit
to llamastack/llama-stack-client-python
that referenced
this pull request
Feb 5, 2025
# 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.
Merged
5 tasks
yanxi0830
added a commit
to llamastack/llama-stack-client-python
that referenced
this pull request
Feb 6, 2025
# 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.
5 tasks
yanxi0830
added a commit
to llamastack/llama-stack-client-python
that referenced
this pull request
Feb 7, 2025
# 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.
ashwinb
approved these changes
Feb 7, 2025
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.
What does this PR do?
Feature/Issue validation/testing/test plan
Sources
Please link relevant resources if necessary.
Before submitting
Pull Request section?
to it if that's the case.
Thanks for contributing 🎉!