phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-02 08:44:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

removed assertion in ollama.py and fixed typo in the readme

Browse source
This commit is contained in:
Kai Wu 2024-12-03 16:15:47 -08:00
parent 435f34b05e
commit 98c97d3104
2 changed files with 2 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
docs/source/distributions/importing_as_library.md
View file

@ -21,7 +21,7 @@ print(response)
```python
response = await client.inference.chat_completion(
messages=[UserMessage(content="What is the capital of France?", role="user")],
model="Llama3.1-8B-Instruct",
model_id="Llama3.1-8B-Instruct",
stream=False,
)
print("\nChat completion response:")

3
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -13,13 +13,13 @@ from llama_models.datatypes import CoreModelId
from llama_models.llama3.api.chat_format import ChatFormat
from llama_models.llama3.api.datatypes import Message
from llama_models.llama3.api.tokenizer import Tokenizer
from ollama import AsyncClient
from llama_stack.providers.utils.inference.model_registry import (
build_model_alias,
build_model_alias_with_just_provider_model_id,
ModelRegistryHelper,
)
from ollama import AsyncClient
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.providers.datatypes import ModelsProtocolPrivate
@ -180,7 +180,6 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
async def _nonstream_completion(self, request: CompletionRequest) -> AsyncGenerator:
params = await self._get_params(request)
r = await self.client.generate(**params)
assert isinstance(r, dict)
choice = OpenAICompatCompletionChoice(
finish_reason=r["done_reason"] if r["done"] else None,