phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-06 18:50:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

structured output for /completion API ollama

Browse source
This commit is contained in:
Sixian Yi 2025-01-17 22:41:29 -08:00
parent 3a9468ce9b
commit 1787008251
3 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -172,6 +172,7 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
model=model.provider_resource_id, model=model.provider_resource_id,
content=content, content=content,
sampling_params=sampling_params, sampling_params=sampling_params,
response_format=response_format,
stream=stream, stream=stream,
logprobs=logprobs, logprobs=logprobs,
) )

1
llama_stack/providers/tests/inference/test_text_inference.py
View file

@ -208,7 +208,6 @@ class TestInference:
assert not chunk.logprobs, "Logprobs should be empty" assert not chunk.logprobs, "Logprobs should be empty"
@pytest.mark.asyncio(loop_scope="session") @pytest.mark.asyncio(loop_scope="session")
@pytest.mark.skip("This test is not quite robust")
async def test_completion_structured_output(self, inference_model, inference_stack): async def test_completion_structured_output(self, inference_model, inference_stack):
inference_impl, _ = inference_stack inference_impl, _ = inference_stack

2
tests/client-sdk/inference/test_inference.py
View file

@ -11,7 +11,7 @@ import pytest
from pydantic import BaseModel from pydantic import BaseModel
PROVIDER_TOOL_PROMPT_FORMAT = { PROVIDER_TOOL_PROMPT_FORMAT = {
"remote::ollama": "python_list", "remote::ollama": "json",
"remote::together": "json", "remote::together": "json",
"remote::fireworks": "json", "remote::fireworks": "json",
} }