mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
chore: update the groq inference impl to use openai-python for openai-compat functions (#3348)
# What does this PR do? update Groq inference provider to use OpenAIMixin for openai-compat endpoints changes on api.groq.com - - json_schema is now supported for specific models, see https://console.groq.com/docs/structured-outputs#supported-models - response_format with streaming is now supported for models that support response_format - groq no longer returns a 400 error if tools are provided and tool_choice is not "required" ## Test Plan ``` $ GROQ_API_KEY=... uv run llama stack build --image-type venv --providers inference=remote::groq --run ... $ LLAMA_STACK_CONFIG=http://localhost:8321 uv run --group test pytest -v -ra --text-model groq/llama-3.3-70b-versatile tests/integration/inference/test_openai_completion.py -k 'not store' ... SKIPPED [3] tests/integration/inference/test_openai_completion.py:44: Model groq/llama-3.3-70b-versatile hosted by remote::groq doesn't support OpenAI completions. SKIPPED [3] tests/integration/inference/test_openai_completion.py:94: Model groq/llama-3.3-70b-versatile hosted by remote::groq doesn't support vllm extra_body parameters. SKIPPED [4] tests/integration/inference/test_openai_completion.py:73: Model groq/llama-3.3-70b-versatile hosted by remote::groq doesn't support n param. SKIPPED [1] tests/integration/inference/test_openai_completion.py💯 Model groq/llama-3.3-70b-versatile hosted by remote::groq doesn't support chat completion calls with base64 encoded files. ======================= 8 passed, 11 skipped, 8 deselected, 2 warnings in 5.13s ======================== ``` --------- Co-authored-by: raghotham <rsm@meta.com>
This commit is contained in:
parent
ecd9d8dc1a
commit
d23607483f
3 changed files with 10 additions and 134 deletions
|
@ -33,8 +33,7 @@ def test_groq_provider_openai_client_caching():
|
|||
with request_provider_data_context(
|
||||
{"x-llamastack-provider-data": json.dumps({inference_adapter.provider_data_api_key_field: api_key})}
|
||||
):
|
||||
openai_client = inference_adapter._get_openai_client()
|
||||
assert openai_client.api_key == api_key
|
||||
assert inference_adapter.client.api_key == api_key
|
||||
|
||||
|
||||
def test_openai_provider_openai_client_caching():
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue