phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-08 11:07:22 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Another round of simplification and clarity for models/shields/memory_banks stuff

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-09 19:19:26 -07:00
parent 73a0a34e39
commit b55034c0de
27 changed files with 454 additions and 444 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -15,6 +15,7 @@ from llama_models.llama3.api.tokenizer import Tokenizer
from ollama import AsyncClient
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.apis.models import * # noqa: F403
from llama_stack.providers.utils.inference.openai_compat import (
get_sampling_options,
OpenAICompatCompletionChoice,
@ -35,7 +36,7 @@ OLLAMA_SUPPORTED_MODELS = {
}
class OllamaInferenceAdapter(Inference):
class OllamaInferenceAdapter(Inference, Models):
def __init__(self, url: str) -> None:
self.url = url
self.formatter = ChatFormat(Tokenizer.get_instance())