fix(test): update client-sdk tests to handle tool format parametrization better #1287
Conversation
This file contains 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
ashwinb
requested review from
yanxi0830,
hardikjshah,
dltn,
raghotham,
dineshyv,
vladimirivic,
sixianyi0721,
ehhuang and
terrytangyuan
as code owners
facebook-github-bot
added
the
CLA Signed
ashwinb
commented
Feb 27, 2025
| type="text", | ||
| text=content, | ||
| ) | ||
| return content | ||
| elif isinstance(content, TextContentItem): | ||
| return OpenAIChatCompletionContentPartTextParam( |
There was a problem hiding this comment.
actually there is a tricky bug here also. our InterleavedContent type is Union[str, InterleavedContentItem, List[InterleavedContentItem] but OpenAI's does not have the second piece. this method (at the end), needs to wrap the value into an array if it is not an instance of str -- will fix.
ehhuang
approved these changes
Feb 27, 2025
| tc = TestCase(test_case) | ||
|
|
||
| response = client_with_models.inference.chat_completion( | ||
| model_id=text_model_id, | ||
| messages=tc["messages"], | ||
| tools=tc["tools"], | ||
| tool_config={"tool_choice": "none", "tool_prompt_format": provider_tool_format}, | ||
| tool_config={"tool_choice": "none", "tool_prompt_format": tool_prompt_format}, |
There was a problem hiding this comment.
doens't just leaving this unspecified work?
There was a problem hiding this comment.
you mean for all these tests?
There was a problem hiding this comment.
yeah, jeebuz I could have avoided all this work? I feel like a doofus.
ashwinb
force-pushed
the
models_in_test
branch
from
8a70887 to
6079e72
Compare
srikanthbachala20
pushed a commit
to srikanthbachala20/llama-stack
that referenced
this pull request
Feb 27, 2025
…ion better (meta-llama#1287) # What does this PR do? Tool format depends on the model. @ehhuang introduced a `get_default_tool_prompt_format` function for this purpose. We should use that instead of hacky model ID matching we had before. Secondly, non llama models don't have this concept so testing with those models should work as is. [//]: # (If resolving an issue, uncomment and update the line below) [//]: # (Closes #[issue-number]) ## Test Plan ```bash for distro in fireworks ollama; do LLAMA_STACK_CONFIG=$distro \ pytest -s -v tests/client-sdk/inference/test_text_inference.py \ --inference-model=meta-llama/Llama-3.2-3B-Instruct \ --vision-inference-model="" done LLAMA_STACK_CONFIG=dev \ pytest -s -v tests/client-sdk/inference/test_text_inference.py \ --inference-model=openai/gpt-4o \ --vision-inference-model="" ``` [//]: # (## Documentation)
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?
Tool format depends on the model. @ehhuang introduced a
get_default_tool_prompt_formatfunction for this purpose. We should use that instead of hacky model ID matching we had before.Secondly, non llama models don't have this concept so testing with those models should work as is.
Test Plan