phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

update inference config to take model and not model_dir

Browse source
This commit is contained in:
Hardik Shah 2024-08-06 15:02:41 -07:00
parent 08c3802f45
commit 039861f1c7
9 changed files with 400 additions and 101 deletions
Download patch file Download diff file Expand all files Collapse all files

10
tests/test_ollama_inference.py
View file

@ -10,14 +10,12 @@ from llama_models.llama3_1.api.datatypes import (
SamplingStrategy,
SystemMessage,
)
from llama_toolchain.inference.api_instance import (
get_inference_api_instance,
)
from llama_toolchain.inference.api.datatypes import (
ChatCompletionResponseEventType,
)
from llama_toolchain.inference.api.endpoints import ChatCompletionRequest
from llama_toolchain.inference.api.config import InferenceConfig, OllamaImplConfig
from llama_toolchain.inference.ollama.config import OllamaImplConfig
from llama_toolchain.inference.ollama.ollama import get_provider_impl
class OllamaInferenceTests(unittest.IsolatedAsyncioTestCase):
@ -30,9 +28,7 @@ class OllamaInferenceTests(unittest.IsolatedAsyncioTestCase):
)
# setup ollama
self.api = await get_inference_api_instance(
InferenceConfig(impl_config=ollama_config)
)
self.api = await get_provider_impl(ollama_config)
await self.api.initialize()
current_date = datetime.now()